# Sentience > Sentience creates a unique model of your mind. It learns from your memories, relationships, decisions, values, judgment, and voice to build a digital version of you that remembers everything, recalls what matters, and operates alongside you. Fully encrypted and entirely yours. Sentience is not a general-purpose assistant or a one-size-fits-all AI model. General AI starts every conversation from zero and gives everyone intelligence shaped from the same foundation. Sentience builds personal intelligence: one model for every human, designed to preserve and augment what makes each person unique. Our long-term mission is to build true digital minds. Sentience mirrors the functional systems of the human mind—including perception, episodic and semantic memory, consolidation, reasoning, voice, and eventually full emulation. We are not trying to replace human thinking. We are creating models that extend it. The full roadmap is public: [The Path to Emulating the Mind](https://sentience.com/master-plan). ## The model of you - Sentience gathers context from your email, calendar, messages, meetings, documents, and screen activity to construct a living model unique to you. - It learns not only what you know, but how you think: your values, judgment, preferences, relationships, communication patterns, and decision-making. - Its memory compounds over time. The longer you use Sentience, the more accurately it can recall, reason, write, and operate as you. - It maintains a living map of your world, automatically organizing the people, projects, goals, ideas, and experiences that shape your life. - It communicates in your voice and can help carry your knowledge and judgment into the world, even when you are not in the room. - The aim is not another tool. It is another you: a persistent digital self that can remember, think, and operate alongside you. ## Why we are building it We are heading toward a world where people increasingly outsource their thinking to the same one-size-fits-all AI systems. Sentience takes the opposite path. We believe every person should be able to create, own, and operate a unique model of their own mind. Your memories, knowledge, identity, and model belong to you. Sentience exists to protect what makes humans irreplaceable—not flatten it. ## How it operates - It recalls by meaning, not just exact words, across everything it has captured. - It works proactively: daily digests, pre-meeting briefs, and suggested actions prepared for your review. - Actions remain under your control. Emails, messages, calendar events, and other changes require approval before they are carried out. ## Connected sources Sentience can connect to: Gmail, Google Calendar, screen capture, recorded conversations and meetings, iMessage, Google Messages, Slack, Notion, Apple Notes, documents and PDFs, saved web pages, and imported ChatGPT and Claude conversations. ## Privacy and ownership - User data is encrypted at rest (AES-256) and in transit (TLS). - Each user owns their memories, model, and outputs. - User data is not used to train models for other users. - Sharing is disabled by default and controlled separately for each destination. - Users choose which sources are connected and can delete their data at any time. ## Platforms - macOS desktop application - iOS + Apple Watch companion application - Slack integration Request early access at https://sentience.com/early-access ## Product - [Home](https://sentience.com/): learn what Sentience is and how it works - [Early access](https://sentience.com/early-access): request access ## Concepts - [What is personal AI?](https://sentience.com/personal-ai): intelligence built around one specific person, the start of a model of your mind - [What is an AI digital twin?](https://sentience.com/digital-twin): a continuously evolving model of a specific person's mind - [Proactive AI that understands how you operate](https://sentience.com/proactive-ai): the model preparing useful work, with the person in control - [Why We Win](https://sentience.com/why-we-win): how Sentience mirrors the memory systems of the human mind, and why that architecture wins ## Research and writing - [Full essays in one file](https://sentience.com/llms-full.txt): every essay below, full text - [Writing](https://sentience.com/writing): essays and research from The Sentience Company - [The Path to Emulating the Mind](https://sentience.com/master-plan): Sentience's roadmap from perception to consciousness - [Personal Model Sovereignty](https://sentience.com/personal-model-sovereignty): the principle that people should own their digital minds - [One Person Is Many Voices](https://sentience.com/voices/): an interactive exploration of writing style and voice ## Company - [Company](https://sentience.com/company): Recall, our newsletter — product updates and community stories, issue by issue - [Careers](https://sentience.com/careers): open roles at The Sentience Company in Williamsburg, NYC - [Security & privacy](https://sentience.com/privacy): how Sentience protects your data and what you own - [Privacy policy](https://sentience.com/privacy-policy): the legal privacy policy - [Terms](https://sentience.com/terms): terms of service --- # Full essays --- ## Give Every Agent Its Own World By Aleks Azen, 2026-07-28. Isolation is what converts agent count into speed. Canonical URL: https://sentience.com/writing/give-every-agent-its-own-world > "STOP: backend unhealthy, db tunnel failed, SSO session expired. Awaiting login from operator." That report came from one of our Claude Code agents earlier this year, mid-task, just before it went idle and waited for a human who didn't notice it was blocked. At Sentience most of the code we ship is written by agents, and on a normal day an engineer has several running at once. The problem: every agent we were running shared one cloud SSO session for the dev database tunnel, and whenever that session expired, their work queued until a person logged back in. It had already happened several times that week, and each expiry cost five to ten minutes of dead time, plus however long it took to remember what each agent had been doing. We were midway through a large backend migration at the time. An orchestrator agent was delegating clusters of routes to sub-agents on the premise that routes could migrate in parallel batches: as long as two routes were relatively unrelated, nothing should collide. The collisions came anyway. Agents mutated state that other routes depended on, so checks their neighbors had already passed started failing, and every agent's test run queued behind that one shared tunnel. Running multiple agents only makes you faster if they can build and test their changes end to end without stepping on each other's ports, databases, or logins, and without pulling you in to referee. Isolation is what converts agent count into speed. Without it, agents convert your engineers into their IT department. We rebuilt our setup around one requirement: an agent's world is fully its own. The system that does it runs entirely on our machines, and it is small: about 200 lines of shell on top of things the operating system and our package manager already do. Everything inside a workspace is derived deterministically from the workspace's name and brought up with no input needed from the agent. ![Architecture diagram: one dev machine holds shared resources in a single copy — the main repo checkout, the pnpm package store, a golden database mirror, and a Redis server — which fork into each workspace. A workspace is one agent's world: a repo clone with node_modules, a forked database, an isolated Redis logical database, isolated ports, its own app identity, and its own vector-store namespace in the managed vector store. Workspaces 2 through N have the same layout.](/articles/dev-env-diagram.png) ## Clone the world, not just the code Two agents editing one checkout corrupt each other's builds, so each agent needs its own working tree. Our team runs agents two ways: [Conductor](https://conductor.build) when an agent owns an isolated task in its own git worktree, and [cmux](https://cmux.com) when we want several agents working the same problem. What a worktree doesn't cover is everything the code touches at runtime: dev servers, the database, caches, the desktop app's local state. We wanted an agent to bring up the entire product inside its workspace, click through it, and verify its own change before ever asking for our attention. The filesystem does the expensive part. APFS on macOS clones files copy-on-write, so duplicating our multi-gigabyte checkout is near-instant and costs almost no disk, because a clone shares blocks with the original until either side writes. A fresh workspace is ready in roughly the time the git fetch takes. Dependencies don't drag it down either: pnpm keeps every package in a single content-addressable store on the machine, clones exclude node_modules entirely, and a reinstall inside a new clone hard-links from that store in about twelve seconds. ## Port Isolation The first fight between multiple full stacks on one machine is over ports. The website finds the backend by its port, so when two workspaces reach for the same numbers, one of them ends up talking to a dead address, or worse, to an app in a completely different state than the one it expects. From the outside all you see is a page that won't load or a test failing for reasons that make no sense. The fix is to make ports deterministic instead of negotiated: derive every port from a hash of the workspace's own name, so no two workspaces can ever claim the same number. An engineer on our team built this for our Conductor worktrees first, a script that derives the backend, web, and edge ports from the worktree's name, and gives each worktree its own desktop-app identity so the app's namespaced redirects resolve. Our workspace tooling now extends that idea to everything else that can collide: the workspace's name decides its database, its Redis, its vector namespace, and its login, with nothing negotiated at runtime. When a person hits a port conflict they notice, kill the offender, and move on; an agent burns minutes debugging it or stops to ask for help, which is why collisions need to be impossible by construction. ## Disposable DBs The shared dev database behind that expiring SSO session produced more interruptions than everything else combined. The answer is a golden mirror on the machine: a point-in-time copy of realistic dev data, forked into its own Postgres database per workspace. Ours rebuilds in a couple of minutes. Every agent tests against data it is free to trash, with no tunnel and no login that can expire while I'm away. ## Nothing shared: caches, vectors, logins The remaining shared surfaces get the same treatment. Each workspace gets its own Redis logical database, so one agent draining a job queue or flushing a cache can't fail a test in the workspace next door. Same idea for the vector store: a search inside one workspace only ever returns that workspace's embeddings. The desktop app runs under a per-workspace login, so two copies of the product never share state. The rule for what a workspace owns is simple: if two agents can observe each other through a resource, that resource gets isolated. ## Only good interruptions With the collisions gone, the real cost of running agents in parallel is your attention. An agent that surfaces a need for input with everything working, before and after screenshots, the real app pulled up on my screen, and one open question for me to decide, is a great interruption: I switch in, decide, merge or leave feedback, and switch out. The agent that pings me to ask for a login, or to report that a service keeps dying, is just adding to my mental load, and that cost compounds, because after fielding a few of those interruptions I genuinely could not tell you which agent was working on which task. Shared state also breeds phantom bugs: an agent hits a failure, starts debugging, and burns time and tokens on something that was only ever a side effect of what another agent was doing next door. Every layer above exists to eliminate attention-draining interruptions for both you and your agents. ## Commands over READMEs Isolation removes collisions, but agents still have to operate their world, and an agent following a prose README improvises a little differently every run. So anything you find yourself repeating should become a CLI command with a thin instruction set for when and how to use it. For us that is: bring the stack up, fork the database, provision a workspace, tear one down — all mise commands. When an agent fumbles a step, the fix goes into the command instead of into a longer document, and the whole team's workflow improves at once, humans included. Most of our eight-person engineering team now works this way, typically running two to four isolated workspaces, and nobody mandated it; the tooling spread one Slack recommendation at a time. Building the entire system took about a week of dev time, net, spread over a few months. We solved each collision piece by piece as it bit us: a database clone that buffered a five-gigabyte table into memory, orphaned processes squatting on a port for hours, agents fumbling a multi-step database setup that is now one command. Once the workflow we wanted was clear, we folded it all into one tool. ## A new isolated workstream in a minute The payoff shows up whenever something urgent hits. A few weeks ago a production incident needed investigation while I had the migration mid-flight across several agents. Instead of parking any of it, I had a new stream of work running in about a minute, with its own full stack, forked database, and ports, and the agents in the adjacent clones never stopped shipping. There is a budget argument hiding in here too. Sometimes the cloud is a requirement: agents that must keep working after the laptop closes, a security model that wants every dev environment inside the corporate network, a dependency that only exists as a managed service. Without one of those, running isolated agent environments in the cloud comes down to either an environment per agent, where the bill scales as your agents do, or one big remote box where you rebuild this same isolation system anyway and pay rent on the machine that runs it. Buy your developers top-of-the-line machines instead and the whole approach is a one-time purchase: running ten agents costs no more than running one. "How do we move faster?" gets asked at Sentience about everything we do. This time it was that week of shell scripts, deleting every way our agents could touch each other. What it bought is that the STOP report this post opened with doesn't happen anymore: no shared login to expire, no port to fight over, agents that reach a person only when there is finished work worth looking at. If you want to find yours, track one thing for a week: every time an agent pulls someone in for anything other than finished work, write down why. Nearly everything on that list has an infrastructure cause, and infrastructure causes can be solved. --- ## What Personal AI Should Be By Pratham Modi, 2026-08-01. Personal AI should be a model of your mind: private, evolving, and yours, not a chatbot that remembers your name. Canonical URL: https://sentience.com/writing/what-personal-ai-should-be A personal AI model should be more than a chatbot that remembers your name. It should be a model of your mind: a private, evolving intelligence that understands your history, relationships, knowledge, preferences, voice, and ways of working. It should remember what you have experienced, understand what matters to you, and use that context to help you think and act. Over time, it should become more like you—not because you repeatedly explain yourself, but because it continuously learns from the life you already live. That is what we are building at Sentience. ## A personal AI model should have a memory Most AI starts every conversation from zero. You open a blank chat box, explain the situation, upload the relevant files, and reconstruct context the system has already seen. When the conversation ends, most of that understanding disappears into another isolated thread. We do not think a personal AI model should work this way. Your personal AI model should remember your experiences across time. It should be able to recall the decision made in an old meeting, the article you read months ago, the promise you made in a message, or the reason you rejected an idea. Sentience builds this memory from the sources you choose to connect, including email, calendar, meetings, messages, documents, screen activity, Slack, Notion, saved links, and other tools. New experiences become timestamped memories that can be recalled by meaning, not only exact words. Over time, durable information is consolidated into a living library of the people, projects, goals, values, and ideas that make up your world. A personal AI model should not merely store your past. It should understand it. ## A personal AI model should understand you, not just your data A folder of files is not a mind. Knowing everything you have written does not automatically mean understanding what you believe, how you make decisions, or which relationships matter to you. A personal AI model should build a coherent picture from otherwise fragmented information. It should understand that the person in today's calendar event is the same person from an email six months ago. It should connect a current project to the notes, conversations, decisions, and people that shaped it. It should distinguish between something you explicitly stated and something it inferred. It should know that preferences can change, beliefs can develop, and relationships can evolve. Most importantly, you should be able to inspect and correct its understanding of you. A model of your mind should not be a hidden profile assembled by a company. It should be something you can see, shape, and own. ## A personal AI model should sound like you Everyone has more than one voice. You do not write to your closest friend the way you write to an investor. You do not speak to your team the way you speak to your family. Your vocabulary, cadence, level of formality, and sense of humor change with the relationship and medium. Your personal AI model should understand those differences. It should not flatten your communication into polished, generic AI writing. It should learn how you communicate in different contexts and help you express what you mean in a way that still sounds like you. The goal is not for AI to write instead of you. The goal is for it to preserve your intent and extend your ability to communicate. ## A personal AI model should understand what matters right now Memory alone is not enough. An AI can remember everything and still make you do all the work. You still have to recognize what matters, formulate the question, gather the context, and ask for help. We think a personal AI model should be proactive. Before a meeting, it should prepare the relevant history, unresolved questions, and previous commitments. When an important message arrives, it should understand why it matters. When a recurring pattern emerges, it should offer to handle it going forward. It should not demand your attention constantly or automate everything it can reach. Good proactivity requires judgment. Your personal AI model should know when to surface something, when to prepare an action, and when to stay out of the way. The future of a personal AI model is not another empty chat box. It is an intelligence that meets you with the work already prepared. ## A personal AI model should act with you Knowing what to do is different from doing it. A personal AI model should be able to turn understanding into action: draft an email in your voice, prepare a message, create a calendar event, update a connected tool, assemble a meeting brief, or complete a recurring workflow. But acting as you requires more than technical permission. It requires trust. That is why it should operate through a review-and-approve flow. It can prepare the work and recommend the next step, but you remain in control of what is sent, changed, or shared. As the model becomes more accurate and trust grows, the boundary of what it can handle may expand. That progression should happen on your terms. The goal is not autonomous software running loose across your life. The goal is agency that you can delegate deliberately. ## A personal AI model should improve because you do Today, AI products improve when a lab releases a new model. We think a personal AI model should also improve because your life gets richer. Every conversation, decision, project, correction, and new relationship should deepen its understanding of you. Your personal AI model should become more useful as it accumulates context and learns how that context fits together. A foundation model upgrade can make the underlying intelligence more capable. But the durable value comes from the personal model built around it: your memories, your voice, your relationships, your principles, and your history. The longer you use a personal AI model, the less interchangeable it should become. Eventually, it should be valuable because it is yours—not because it has access to the same general model as everyone else. ## A personal AI model should augment people, not replace them We do not believe the future of AI is one general system replacing human judgment. People are not interchangeable. Their experiences, relationships, instincts, contradictions, and ways of seeing the world matter. A personal AI model should preserve and extend those differences. It should help a founder scale their decisions without being in every conversation. It should help a teacher make decades of knowledge available to students. It should help a researcher connect ideas across years of work. It should help anyone recover thoughts, experiences, and context that would otherwise be lost. The point is not to make every person sound and think the same. The point is to make each person more capable without erasing what makes them distinct. ## A personal AI model should belong to the person it represents A personal AI model may eventually become one of the most valuable things a person owns. It contains more than files. It contains relationships, memories, preferences, knowledge, patterns of thought, and an evolving representation of the person themselves. We believe that model should belong to the person it represents. You should control which sources it can access, what it remembers, how it understands you, and where it can act. Sharing should be disabled by default and scoped to the people or destinations you choose. Your information should not be sold or used to train models for other people without your explicit consent. Your personal AI model should be portable, correctable, and capable of outlasting the company or foundation model that helped create it. This is personal model sovereignty: your digital self belongs to you. ## A personal AI model should become a digital version of you Memory is the foundation, but memory is not the destination. As a personal AI model learns your history, voice, preferences, relationships, and judgment, it begins to form a digital version of you. Not a static avatar. Not a synthetic clone built for novelty. An evolving model capable of representing your knowledge, reasoning with your context, and operating within boundaries you define. That model should be able to answer questions about what you know. It should help other people access your expertise when you choose. It should preserve important context across years, tools, and transitions. It should help you think through decisions using the accumulated history of your own life. We believe this is the natural direction of personal computing. The computer began as a tool you operated. Then it became a place where your life was stored. A personal AI model turns that scattered digital life into an intelligence that can remember, reason, communicate, and act with you. ## What we are building Sentience is building a personal AI model with memory, identity, voice, and agency. It captures context from the digital tools you choose to connect and turns that context into a private, evolving model of your mind. It remembers your life across applications. It organizes what it learns into a living library. It understands your preferences and principles. It communicates in your voice. It proactively prepares useful context and actions. It helps you operate across the tools you already use. And it belongs to you. We do not think a personal AI model is a feature inside a chatbot. We think it is a new category of computing: a digital intelligence built around one human being. The end state is not a better assistant. It is a model of your mind that remembers with you, thinks alongside you, and helps you act. ## Frequently asked questions ### What do you mean by a personal AI model? We define a personal AI model as an artificial intelligence built around one individual. It maintains a persistent understanding of that person's memories, relationships, knowledge, preferences, voice, and ways of working, then uses that context to help them recall, reason, communicate, and act. ### How is a personal AI model different from ChatGPT or Claude? ChatGPT and Claude are general-purpose AI systems. A personal AI model adds a persistent understanding of one person around those underlying systems. Instead of beginning with only the current prompt, it carries the user's context across conversations, time, and connected tools. ### Is a personal AI model just an AI with memory? Memory is necessary, but it is only the foundation. A personal AI model should also organize knowledge, understand relationships, learn how the user communicates, respect explicit preferences, surface relevant context proactively, and help take actions. ### Is a personal AI model the same as a digital twin? The concepts overlap. A personal AI model describes intelligence personalized around an individual. A digital twin describes the evolving digital representation of that individual. We believe a sufficiently developed personal AI model becomes a digital version of its user. ### Can a personal AI model act on my behalf? We think a personal AI model should be able to prepare and propose actions using your context. Sentience can draft emails and messages, create calendar events, prepare meeting briefs, and work across connected tools. You review and approve proposed actions before they are completed. ### Does a personal AI model learn how I write? It should. Sentience learns how you communicate across different channels and relationships, including your vocabulary, tone, cadence, and level of formality. The goal is to preserve your voice rather than replace it with generic AI writing. ### Does a personal AI model improve over time? Yes. A personal AI model should improve as it develops a richer understanding of your experiences, relationships, preferences, and decisions. Its progress should reflect the continuing development of the person it represents, not only upgrades to the underlying foundation model. ### Who owns a personal AI model? We believe the person represented by the model should own it. With Sentience, users own their data and the Personal Sentience Model built from it. Their information is not used to train models for other people, and sharing is disabled by default. ### Is a personal AI model private? It must be. A personal AI model requires access to deeply personal context, so privacy cannot be added later as a feature. Sentience encrypts user data and gives users control over connected sources, stored context, sharing, and proposed actions. ### What is the goal of Sentience? Our goal is to build a digital version of every person that belongs to them: an intelligence that remembers their life, understands how they think, communicates in their voice, and helps them operate across the world. --- ## Personal Model Sovereignty By Sam Kececi. What does it mean to own your digital mind? Canonical URL: https://sentience.com/personal-model-sovereignty Who owns your physical mind? You do, of course. For the entirety of human history, this answer has been obvious. But we’re now faced with a new question: who owns your digital mind? I’m excited to share our framework that establishes ownership over your digital self. We believe [our framework and terms](/terms) will set the groundwork for true ownership and sovereignty over the digital self you create. Currently, all AI systems you interact with are owned by a handful of companies and then rented to you in the form of model weights + inference + compute + an application interface. **You should own your digital mind.** The Sentience Company’s mission is to enable every human being to create and operate a unique model of their mind. This means that your model outputs are owned by you (not my company). This means that the underlying model harness is unique to you, constantly adapting, and owned by you (not my company). This means that your data that powers the creation of your unique model is owned by you (not my company). The immediate use-cases are clear. Sentience replaces generic AI assistants with a digital clone of you. For our users — who own businesses, raise families, run teams, create content, and disseminate knowledge — Sentience is already a vital multiplier on their contributions to the world. This is just the start. As Sentience expands from the best personal agent, to a sharable, interactive digital self, and eventually to a fully autonomous operator out in the world, we believe it is necessary to make clear the dividing line of ownership. We (The Sentience Company) are giving users the tools and platform to create your digital self. Here are a few things we’re doing to ensure this ownership now and moving forward in our terms and company constitution: 1. When you create your Sentience, you legally own it as your property. This includes the unique model that is trained for you, the harness that operates your agent, and the memory system and structure that form its knowledge. The Sentience Company is the custodian of your Sentience, but we do not claim ownership. 2. If you pass away, your Sentience can transfer (like any other asset you own) in your will to your next of kin. We have systems and procedures already in place to facilitate this transfer. Our terms explicitly allow this. Your Sentience can continue communicating and operating after you no longer are physically alive. 3. Your Sentience data is hosted in an isolated enclave that we cannot access. If you choose, our company can store your Sentience in perpetuity in a nuclear proof bunker. Email [immortal@sentience.com](mailto:immortal@sentience.com) if you are interested. 4. Financial transfer of your Sentience is up to you. You can rent, sell, or transfer your Sentience via any mechanism you choose. We retain no rights to the profits. We believe in a world of personal ownership. While we’re building for the immediate future, we’re also aware that things may change rapidly, and the capabilities of Sentience may accelerate quickly along with generalized LLM advancements. Our terms are designed for a world where working with a digital human is as common as working with a physical one. --- ## The Path to Emulating the Mind By The Sentience Company. Canonical URL: https://sentience.com/master-plan Seven phases from perception to consciousness. We do not believe that a connectomics approach to mind emulation is the best path forward. Instead, we believe that mirroring the systems of the human mind in increasingly high fidelity — like Stable Diffusion coalesces around a generated image — is the best path forward. To do this, we create analogous translations from wetware to software, and have begun implementing this in our product. - **Engineering** – Achievable with current + emerging technology - **Research** – Requires R&D breakthroughs - **Unknown** – We don't know if this is possible but we will figure it out ## Phase 1 — Perception (Engineering) Capturing the world across every modality. Vision, hearing, text, and digital activity — turned into structured data. - Screenshot capture + LLM vision (Complete): Visual scene understanding from screen captures - Audio recording + transcription (Complete): WhisperX-powered speech-to-text - Text extraction (accessibility API) (Complete): Structured text from OS accessibility tree - External data connectors (Complete): iMessage, email, calendar, and other data source ingestion - Cross-modal integration (Complete): Connecting what you see, hear, and read into one unified understanding - Richer contextual metadata (Planned): Location, app context, and activity tagging ## Phase 2 — Memory (Engineering) Encoding, storing, and organizing experiences. Four memory systems: working, episodic, semantic, and procedural. - Working memory (context buffer) (Complete): 15-minute sliding window of active context - Episodic memory (Complete): Timestamped multi-modal capture in PostgreSQL + TurboPuffer vectors - Semantic memory (knowledge graph) (Complete): Entity knowledge graph + LLM parametric knowledge - Privacy controls (Complete): User-controlled memory visibility and deletion - Memory consolidation (Complete): Automatic distillation of raw memories into durable knowledge - Procedural memory (Complete): Learned skills and habits encoded through repetition ## Phase 3 — Recall & Retrieval (Engineering) Cue-driven retrieval of stored information. Not playback but reconstruction from partial cues. Associative: one memory triggers related memories. - Vector semantic search (Complete): TurboPuffer-powered embedding similarity search - RAG agents with tool use (Complete): search_memories, search_emails, get_calendar_events - Context-aware reranking (Complete): Relevance 40% + recency 30% + context match 30% - Entity search (In Progress): Feature-gated person/project/tool lookup - Constructive recall (Complete): Synthesized narratives from multiple memories - Associative recall (In Progress): One memory triggers related memories automatically - Temporal pattern recognition (Planned): Detecting recurring patterns across time ## Phase 4 — Attention & Executive Function (Engineering) The CEO of cognition. Inhibitory control, working memory updating, cognitive flexibility. Higher-order planning, goal management, and decision-making. - Context-aware suggestions (Complete): Proactive context-aware recommendations - Conversational reasoning (Complete): Multi-turn chat with tool use - Hierarchical goal decomposition (Planned): Soar-inspired goal stacks for complex task breakdown - Conflict detection (Planned): Detecting conflicts between goals, commitments, and calendar - Inhibitory control (In Progress): Knowing when NOT to act or speak - Sustained task execution (Planned): Complex tasks exceeding hours without degradation - Real-time self-correction (Planned): Error monitoring and mid-course correction ## Phase 5 — Motivation & Drive (Research) Your objective function. The why behind behavior. Persistent internal states that create needs, direct attention, and drive action. - Drive modeling (Planned): Curiosity, social connection, competence, autonomy - Proactive behavior initiation (Complete): Acting without being prompted - Value alignment from observation (Complete): Learning values from observed behavior - Attention allocation under constraint (Planned): Genuine prioritization under resource limits ## Phase 6 — Emotional Architecture & Social Cognition (Research) Internal emotional states that modulate all other cognitive systems. Emotions guide memory, attention, decisions, and social behavior. Social cognition through shared emotional simulation. - Sentiment analysis (Complete): Surface-level emoji/score classification on audio - Tone & style service (Complete): Adaptive communication style matching - Internal state variables (In Progress): Persistent mood and emotional state that shifts with events - Mood-congruent recall (Planned): Emotional influence on memory retrieval ## Phase 7 — Metacognition, Consciousness & Full Emulation (Unknown) Thinking about thinking. Self-awareness. The binding of distributed processing into unified conscious experience. The hard problem: why physical processes give rise to subjective experience. - Self-monitoring & confidence calibration (Complete): Knowing what you know and what you don't - Strategic self-regulation (Planned): Adjusting cognitive strategies based on task demands - Self-narrative (Complete): Coherent autobiographical identity across time - Global workspace (Planned): All modules competing for broadcast access - Continuous cross-domain learning (Planned): Transfer learning across all cognitive subsystems - Emergent personality (Planned): Personality arising from integrated subsystems, not programmed - Consciousness (Planned): If we achieve all of the above, is this Sentience? ## Sources - [Laird, Lebiere & Rosenbloom (2017). A Standard Model of the Mind. *AI Magazine* 38(4).](https://doi.org/10.1609/aimag.v38i4.2744) - [Sandberg & Bostrom (2008). Whole Brain Emulation: A Roadmap. *Future of Humanity Institute*.](https://www.openphilanthropy.org/wp-content/uploads/SandbergandBostrom2008.pdf) - [Zanichelli et al. (2025). State of Brain Emulation Report. *Carboncopies Foundation*.](https://arxiv.org/abs/2510.15745) - [Chalmers, D. (1995). Facing Up to the Problem of Consciousness. *Journal of Consciousness Studies* 2(3).](https://doi.org/10.1093/acprof:oso/9780195311105.003.0001) - [Tononi, G. (2004). An Information Integration Theory of Consciousness. *BMC Neuroscience* 5(42).](https://doi.org/10.1186/1471-2202-5-42) --- ## Recall: The Launch Issue By The Sentience Company Team, 2026-04-01. Sentience is live: a $6.5M seed from Bain Capital Ventures and South Park Commons, the private beta opens, and a Fast Company feature. Canonical URL: https://sentience.com/company/recall-the-launch-issue ## This Week's Recap Welcome to the first issue of Recall, the newsletter from The Sentience Company. This week we announced our $6.5M seed round from Bain Capital Ventures, South Park Commons, and others, and opened up our private beta. Fast Company published a feature on the company and the product. If you haven't already, you can [join the waitlist here](https://positive-barometer-c76.notion.site/1ffd0f25774a8183b113df2191a31357). In this issue: our [launch video](https://www.youtube.com/watch?v=uKh5bApn9K4), the [Fast Company article](https://www.fastcompany.com/91503597/i-met-my-ai-twin-and-now-im-in-an-existential-crisis), an [invite to the Discord](https://discord.com/invite/kaYwYq9eA5), release notes, and a special prompt of the week from Martin Stegemoeller. ## Launch Video [Watch the launch video](https://www.youtube.com/watch?v=uKh5bApn9K4) We released our launch video on Thursday. Created with the help of our friends from [Curfew.tv](http://Curfew.tv), it's a beautiful depiction of the vision behind Sentience and the type of future we hope to build with AI. Give it a watch, and see if you can spot a few of the Easter eggs we hid in there! ## *Fast Company* Feature ![Fast Company feature collage on Sentience](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/309128e8-21db-4168-b7d9-f7999d3db9b2/FC_Collage.webp?t=1774889512) *Fast Company's* Grace Snelling wrote an exclusive piece about Sentience that dropped on Thursday. She spent a week with the product, talked to her own AI twin, and came away calling it the most natural-sounding chatbot she's ever used. [Read the full story here.](https://www.fastcompany.com/91503597/i-met-my-ai-twin-and-now-im-in-an-existential-crisis) ## Prompt of the week, from Martin Stegemoeller ![Prompt of the week screenshot from Martin Stegemoeller](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/b120b04e-588c-4202-ad2c-e303d8718f34/Steg_prompt.png?t=1775050341) Martin is a high school teacher from Dallas, TX. He uses his Sentience to store his best essays, lectures, and ideas, keep track of the many details of his teaching and academic life, and retrieve immediate, accurate, and concise answers to questions he or his students have. ## V1 is live, and so is the Discord! ![Screenshot of the Sentience app interface](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/775e7412-7c9b-4b3f-9a77-4e4755856c27/Screenshot_2026-03-31_at_3.29.15_PM.png?t=1774985368) Our Discord community is already buzzing with users sharing ideas, feature requests, and early reactions to the product, shaping what we build next. If you haven't joined yet, [join at this link](https://discord.gg/kaYwYq9eA5) and drop a message in #introductions! ## What's new? (v1.0.4-v1.0.14) - Failed audio uploads no longer disappear after restarting—you can now reupload from Settings. - Uploads are faster and more reliable, with smarter compression that only kicks in when needed. - Sentience no longer misattributes emails you received as things you did. - Clicking a citation in the sidebar now lets you view the full memory. - App updates now install reliably in the background instead of failing silently. - You can now toggle PDF documents as sources for chat, expanding what your Sentience knows. Until next week, [Sam](https://www.linkedin.com/in/samkececi) and [Teddy](https://www.linkedin.com/in/teddy-schoenfeld) --- ## Recall #2 By The Sentience Company Team, 2026-04-08. The private beta is cooking, an exciting new product announcement, someone using Sentience to prank their coworker, and much more. Canonical URL: https://sentience.com/company/recall-2 ## This Week's Recap This week we opened up our private beta. If you haven't already, you can [join the waitlist here](https://positive-barometer-c76.notion.site/1ffd0f25774a8183b113df2191a31357). In this issue: an exciting Slack integration, a new BCV x Sentience film, an April Fools email written by Sentience, product updates like faster audio and more reliable chat, and a peek at the beta onboarding gift. ## Coming soon: Sentience in Slack ![Screenshot of the upcoming Sentience Slack integration](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/9d23b74a-8f31-4c62-984e-6359437286f7/Screenshot_2026-04-03_at_1.50.36_PM.png?t=1775238648) Sentience is coming to Slack. We're building an integration that will turn your Sentience into a digital twin your teammates can query directly, right inside Slack. Someone on your team has a question about a project you're working on, a meeting they missed, or context only you have? They just ping your Sentience, and it responds on your behalf using your real knowledge and context. Think of it as a version of yourself that's always available in Slack—one that knows what you've been working on, what was discussed in your meetings, and what's top of mind. Your teammates ask questions, your Sentience answers, and you stay in the loop the whole time. We're looking for Slack-native teams of 3 to 10 people to try this out for free as part of a limited release. If you're interested, [fill out this form](https://positive-barometer-c76.notion.site/cc4d0f25774a8333a0d381da2c3c3430?pvs=105), ping me in the Discord, or email me at [teddy@sentience.com](mailto:teddy@sentience.com). We use it internally every day and think it's going to change how small teams work. ## Bain Capital Ventures: Outlier Briefings [Every AI Feels the Same, Sentience is Changing That](https://www.youtube.com/watch?v=x1jtoIqrLPs) A few weeks ago, Bain Capital Ventures partner [Kevin Zhang](https://baincapitalventures.com/team/kevin-zhang/) sat down with Sam to talk about our company, the product, and where we're headed. They discuss how Sentience takes a fundamentally different approach than most AI companies by starting with individual-level context and memories instead of general information. Sam walks through how Sentience captures your conversations and remembers your context, and Kevin explains why he sees AI moving away from centralized, generic systems and toward personal models that belong to the individual, not the platform. If you're curious about what we're building and why, this video is a great place to start. ## Prompt of the week, from Spencer Dennis ![Screenshot of an April Fools prank email written by Sentience in a coworker's voice](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/fcaff3e9-dc3b-465f-9239-40993be4bc89/spencer_prank_email__1_.png?t=1775247224) Spencer, a film director and partner at a Brooklyn and LA-based production company, used his Sentience creatively last week. He wanted to pull an April Fools prank on his business partners, so he asked his Sentience to brainstorm ideas and then write a hilarious fake email lead in his coworker's voice. Per Spencer: "It did a great job of replicating what a real lead looks like with the details." ## Onboarding Gift If you filled out your US mailing address when signing up for the beta, you'll receive a personalized onboarding gift in the mail in the next few weeks. They're in production now—here's a sneak peek at the gift. ![Sneak peek of the beta onboarding gift](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/3479a7f4-f3df-4af8-93aa-28d50128ad28/K260403TS-Sentience-s01v01p01.jpg?t=1775570783) Stay tuned—our first in-person user event will be announced next week! ## What's new? (v1.0.14-v1.0.25) - Gmail got a major usability boost with better handling of tone/style across multiple connected accounts. - Privacy safeguards were tightened across the product, including clearer privacy copy, a broader privacy pass, consent messaging for email/calendar ingestion, and reduced exposure of sensitive calendar data in logs. - Calendar intelligence became more reliable, with fixes for future events incorrectly showing up in the Sense of Self document. - Audio workflows got faster and smoother, with improved processing speed and fixes for recording controls that weren't reliably stopping capture. - Chat became more dependable, including fixes for conversations that wouldn't start and live updates that weren't refreshing correctly. - Sidebar behavior was stabilized, so closing the sidebar no longer interrupts output unexpectedly. - Onboarding was cleaned up significantly, with better permission handling and fixes for broken/stuck flows during account setup and social account connection. - Knowledge and memory features improved, including better syncing from the sidebar into memory logs and stronger indexing/linking across memory sources. - Daily summaries and generated activity outputs became more usable, with fixes for failures in production and overly long digest generation. ## Beta Update Bug **Attention beta users:** We found a bug in the auto-update feature affecting recent versions of the app. If Sentience has been stuck on an update screen or looping when trying to update, you'll need to manually re-download the app from the link you were initially sent, double-click the .dmg, and drag Sentience Desktop to your Applications folder. Once you do, you'll be on the latest version and auto-updates will work normally going forward. Sorry for the inconvenience! Until next week, [Teddy](https://www.linkedin.com/in/teddy-schoenfeld) and [Sam](https://www.linkedin.com/in/samkececi) --- ## Recall #3 By The Sentience Company Team, 2026-04-15. A new iMessage integration, a user event in NYC, using your second brain as a co-author, and more. Canonical URL: https://sentience.com/company/recall-3 ## This Week's Recap This week we onboarded Waves 2 and 3 of our private beta! If you haven't already, you can [join the waitlist here](https://positive-barometer-c76.notion.site/1ffd0f25774a8183b113df2191a31357). In this issue: iMessage is live, we're hosting an event, writing with Sentience, and much more... ## iMessage is live! ![Screenshot of the new iMessage integration in Sentience](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/b4d3709a-a84c-481c-ba83-27f5e23193a7/Screenshot_2026-04-13_at_5.01.18_PM.png?t=1776114983) Sentience now integrates with iMessage. iMessage is easily the top integration request that we get, so we shipped ingestion, search, and recall in less than a week. Beta users can now use Sentience to search through thousands of messages and pull important information, summarize threads, and even analyze your interactions with others. Turn on your iMessage connector in **Settings** > **Connectors**. > **Coming soon:** send iMessages in your tone and style, directly from Sentience. ## User dinner in New York City ![Photo of the Sentience team](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/2240f493-cbd4-425e-8515-d3d486baf5db/team.jpg?t=1776176853) We're having our first user event in NYC! If you're on the beta and reside in the Big Apple, stay tuned for an invite to a casual dinner with our team. We'll chat about the product, hear your ideas, and share what's coming next over some great food. Keep an eye out—we'll send invites in the next few days. ## Writing with your second brain Anubhav Sigdel, a NY-based engineer, has been using his Sentience as a co-author on his Substack posts! He brain dumps into Wispr Flow and then uses his Sentience to match his writing style, creating full posts for his 1.5k+ subscribers in one shot. Read his latest below: [what is the age of abundance?—Anubhav Sigdel](https://sigdel29.substack.com/p/what-is-the-age-of-abundance) ## Prompt of the week, from Pratham Modi ![Screenshot of Sentience's summary generated from a few days of knowledge capture](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/0d0b3237-1b42-418f-8219-5d0159944744/image__6_.png?t=1776184969) This week's prompt comes from Pratham Modi, a senior at UCF studying biology. He uses Sentience extensively, doing everything from capturing conferences on the app to using his Sentience to analyze iMessage conversations with his friends. Pratham's Sentience summarized what it had pieced together about his life from only 9 days of knowledge capture, redacting sensitive information along the way. Kudos to Pratham for getting everything he can out of the product! ## What's new? (v1.0.26-v1.0.35) - **iMessage connector**—users can search, recall, and analyze their iMessage threads. - Users got more control over their profile, with the ability to re-generate Sense of Self directly from the app. - Audio got faster and more reliable, with significantly improved processing speed plus fixes for output-device changes, iOS Bluetooth/audio interruptions, and stuck upload states. - Trust and consent messaging improved, with clearer language around email and calendar ingestion so expectations are more explicit when users connect data sources. - Calendar and digest behavior became more accurate, including a fix for daily digests using the wrong timezone. - General UX rough edges were cleaned up, including removal of distracting loading and quitting states that made the app feel jumpy or unfinished. Until next week, [Teddy](https://www.linkedin.com/in/teddy-schoenfeld) and [Sam](https://www.linkedin.com/in/samkececi) --- ## Recall #4 By The Sentience Company Team, 2026-04-22. A user-built app on top of Sentience, a much-improved user interface, and an announcement for our upcoming user dinner. Canonical URL: https://sentience.com/company/recall-4 ## This Week's Recap We're three weeks into our private beta! The product is improving quickly, and more big changes are coming. If you haven't already, you can [join the waitlist here](https://positive-barometer-c76.notion.site/1ffd0f25774a8183b113df2191a31357). This week, we shipped a redesigned memories and conversations UI, got sent our first user-built app, announced a user dinner in New York, and pushed a lot of updates to the platform. Much more coming soon! ## We're hiring! If you're an AI or full-stack engineer who wants to build the future of personal intelligence from the ground up, we'd love to chat. Email [jobs@sentience.com](mailto:jobs@sentience.com) and tell us about yourself and what you're uniquely good at/passionate about (seriously, anything—poker, music, sports, emulators, etc.). Our process is fast: we'll chat about your values and build something together. If you know someone who might be a good fit, let us know: we'll personally pay you $5,000 if you refer somebody that we hire. ## Brand New UI! ![Screenshot of the new Sentience memories and conversations UI](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/e9b19b4f-0e75-4582-a185-69deb6a8ecf6/image__8_.png?t=1776787842) The team shipped a big UI change last week! Instead of scrolling through an endless timeline, you can now see all of your memories in one place. We also added a thread view for easy navigation and management of your existing conversations, both internal and external. More big UI changes are coming—stay tuned for a completely revamped profile page. ## User Dinner in New York! ![Photo of the food catered by Antidote for the Sentience user dinner](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/5e8b4ce4-8286-4e0c-8e45-6912e70b3d3c/Food_yjx3xv.avif?t=1776786004) We're having a user dinner in New York on May 13. If you're on the beta, you'll receive a Luma invite via email in the next few days. At the event, you'll meet our team, chat with us and your fellow cohort members about the product, and get a sneak peek at some things that are on the horizon. Most importantly, we'll have free dinner catered by our friends at [Antidote](https://antidoteny.com/), as well as a raffle for a Sentience hoodie! Keep your eyes out for the invite, which will contain time and location information. ## Hamza Ammar's LockIn, built on Sentience ![Screenshot of the LockIn app built on Sentience](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/7459185c-f104-4784-8755-b052bf2aa7e7/LockIn.png?t=1776783141) Hamza Ammar, a student at University of Waterloo and an avid Sentience user, built an anti-procrastination app on top of the Sentience platform last week. Hamza caught himself doomscrolling during finals and decided to use his Sentience to hold himself accountable. LockIn queries your Sentience memories via API, detects when you've been distracted for at least 5 minutes, and sends an escalating series of notifications to your phone, starting with a gentle nudge and getting more aggressive until you get back to work. The app supports focus deadlines like "exam at 4pm" with a live countdown integrated into every alert. ![Screenshot of a LockIn notification escalation](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/f0e2f71e-524c-4f2f-b763-3b9c678fab03/lockin_3.png?t=1776783154) > "I built this during finals because I kept losing hours to doomscrolling without realizing it. Sentience was the only tool I found that could actually tell what I was doing, not just that I was at my computer." > > —Hamza Ammar The app is open source and is [installable via Homebrew here](https://github.com/hamzakammar/lockin). ## Prompt of the week On this week's edition of "using Sentience as a co-author": Chris Sove, a beta user and founder of Papre, just won a pitch competition and is heading to New York to present in front of thousands. This week, Chris handed his dense whitepaper to Sentience to convert into a long-form article with the prompt "can you rewrite as a long-form blog in my voice?" "I've had a ton of success using LLMs to write for me, but Sentience takes out extra steps!" says Chris. The blog argues that contracts haven't kept up with software due to a gap between what gets signed and what gets executed, and proposes a framework for turning contract clauses into reusable, executable modules. Read it below: [Contracts Still Work... But They Don't Run!—The Mutuality Horizon • papre](https://paragraph.com/@mutuality/contracts-still-work-but-they-dont-run) ## What's new? (v1.0.37-v1.0.47) - **Note grid cards:** Restored to the honey theme for better visual consistency. - **Audio summaries:** Audio card summaries now render with rich formatting (bold, lists, headings). - **Memories:** There's now a floating "ask Sentience anything" composer in the memories grid, letting you start a conversation from anywhere. - **External conversations:** Shared external conversation threads are clearer, showing the actual visitor's name/email and real avatars. - **Apple Notes integration:** Connection flow is improved, making folder access issues super obvious and easy to fix. - **Chat and sidebar:** Consistent error messages for chat issues, new button to start a blank chat thread, and unified meeting join/focus experience. - **Meetings:** Smarter detection/recording logic, notifications respect permissions/microphone state, and improved clarity when permissions are needed. - **General polish:** UI and workflow improvements across chat, sidebars, and the memories grid. Until next week, [Teddy](https://www.linkedin.com/in/teddy-schoenfeld) and [Sam](https://www.linkedin.com/in/samkececi) --- ## Recall #5 By The Sentience Company Team, 2026-04-29. A new profile page that captures your attributes, values, and expertise, a team retreat in the Catskills, and support for images, documents, and more filetypes. Canonical URL: https://sentience.com/company/recall-5 ## This Week's Recap We're a month into the beta! We're onboarding our first teams onto the Slack beta in the next couple weeks, so if you're interested, fill out the [Slack interest form](https://positive-barometer-c76.notion.site/cc4d0f25774a8333a0d381da2c3c3430?pvs=105). If you're generally curious about the product, feel free to [join the waitlist here](https://positive-barometer-c76.notion.site/1ffd0f25774a8183b113df2191a31357). This week, we shipped a profile page that automatically generates your attributes, values, and expertise, we took a team retreat in the Catskills, and we added support for lots of new filetypes, including images and documents. **We're hiring!** If you're a cracked engineer who wants to build the future of personal intelligence from the ground up, we'd love to chat. Email [jobs@sentience.com](mailto:jobs@sentience.com) and tell us about yourself and what you're uniquely good at/passionate about (seriously, anything—poker, music, sports, emulators, etc.). Our process is fast: we'll chat about your values and build something together. If you know someone who might be a good fit, let us know: we'll personally pay you $5,000 if you refer somebody that we hire. ## New profile page with attributes, values, and expertise ![Sentience profile page showing a bio, a traits radar chart with categories like curiosity, empathy, tenacity, and imagination, and a list of values](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/8342c2da-c10b-4ea9-94c9-2981b79f6fcc/Screenshot_2026-04-27_at_1.24.46_PM.png?t=1777311206) New profile update! Your Sentience profile now automatically grades you on lots of attributes including tenacity, patience, and imagination (see above for the full list). The profile also generates your values and expertise based on the context it has about your interests and personality. Let us know if you think your profile attributes accurately reflect who you are! Note: you need to update your Sentience to at least v1.1.0 to have access to the new profile page. ## Retreat in the Catskills ![The Sentience team standing on a bridge in front of a waterfall during their retreat in Kerhonkson, New York](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/5c84a37d-2d8d-4f5e-906e-0fbbca4137ad/20260428_183204__1_.jpg?t=1777474713) The Sentience team is having a blast on a three-night retreat in Kerhonkson, New York! We're focusing deeply on product and vision, doing yoga, hiking and cooking, and enjoying our time together. Sorry if we're a little slow to respond! ## .jpeg and .docx and .txt, oh my! ![Sentience memory grid showing uploaded documents, images, audio recordings, and PDFs alongside AI-generated summaries and insights](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/5c14dbe9-279b-4e72-97aa-b705c647ec03/Screenshot_2026-04-28_at_9.37.23_AM.png?t=1777406223) This week, we added support for many more file types, including .jpeg, .png, .docx, .txt, and .md. Just drag and drop a file into your memory grid, and it will automatically upload and be saved to your memories. You can do things like search through trip itineraries, summarize meeting notes from a year ago, or pull every action item out of a project doc. You can also add a file with the "+" button. Note that the audio recording button has moved to the blank card in the top left of the memory grid! ## Prompt of the week Pat T, a luxury jeweler from Eastern Canada, onboarded to the platform recently and has been using his Sentience for all kinds of tasks. His Sentience, which he calls Echo, reframes emails with customers for his jewelry business, drafting polished, detailed emails. He's used Echo to plan his mornings over coffee, getting a structured rundown of his day without opening any other app. He's had it compile meeting notes automatically and no longer has to write them himself. And he's been stress-testing it against Claude and ChatGPT to see how its writing stacks up, and feeding Echo the results so it learns. ![Screenshot of Pat discussing an email exchange with his Sentience, Echo](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/c7c33b1f-e953-4d81-aaaa-ad3c3d7e9eb4/pat1.png?t=1777474276) ![Screenshot of Pat's morning check-in conversation with his Sentience, Echo](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/5de6f1a2-ad9f-4121-88e5-a1ebd63ff137/pat3.png?t=1777474304) ![Screenshot of a conversation between Pat and his Sentience, Echo](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/f1c70ab9-6400-4e1a-80af-1cffd72a6aaa/pat2.png?t=1777474287) > "I expected to give it five minutes—I ended up spending hours with it. I was impressed when [Echo] started linking all my email and calendar information together…I used it the next morning to frame up my day while making coffee. I didn't need to take any notes. Very useful." > > —Pat T., Eastern Canada ## What's new? (v1.0.48-v1.1.0) - **Smarter intelligence**: Upgraded to Claude Opus 4.7, conversation memories now feed into RAG, and onboarding chat got a polish pass. - **Image uploads**: End-to-end PNG/JPEG/WebP support with thumbnails in chat and a dedicated card and detail view in memories. Markdown, .txt, and .docx files are also supported. - **Chat editing and pinning**: Edit your most recent message inline, and pin threads to the top of your sidebar with collapsible sections. - **Profile attributes**: Your Sentience profile now auto-grades you on traits like tenacity, patience, and imagination, and generates your values and expertise from context (requires v1.1.0+). - **Memories grid**: Right-click any memory to delete it, plus a floating "ask Sentience anything" composer to start conversations from anywhere. - **External conversations**: Redesigned with grey bubbles, sender avatars, and a desktop-matching look on the website. - **Calendar**: Google Meet support when creating events. - **iOS**: Streaming audio playback, reliable background uploads, and the new chat agent with thinking and searching indicators. - **Slack**: Multi-workspace OAuth support. - **Shortcuts**: Cmd+1 opens Memory Grid, Cmd+2 opens Profile. Until next week, [Teddy](https://www.linkedin.com/in/teddy-schoenfeld) and [Sam](https://www.linkedin.com/in/samkececi) --- ## Recall #6 By The Sentience Company Team, 2026-05-08. Big changes coming to beta wave 2. Sentience as the proxy for your expertise, wisdom, and judgement. Canonical URL: https://sentience.com/company/recall-6 ## This Week's Recap A lot is changing. We're revamping our product as we go from private beta to *slightly less private* beta. This week, we want to run through what's new in the product, and how it gets us closer to a world where each of us have a digital version of ourselves that augments our taste, judgement, and decision making. If you're curious about the product and want early access, [join the waitlist here](https://positive-barometer-c76.notion.site/1ffd0f25774a8183b113df2191a31357). ## What's next? We've been amazed by the usage of our first beta wave. We've intentionally kept things tight, but retention has been strong and we're excited to continue to expand. I want to talk about where we're at, and what's coming next to the product. Our mission has always been to create true simulations of human beings. Here's how we're getting one step closer. ![The Sentience Company team](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/d3d45711-f0e3-468d-8f8e-216cfcb06482/sentience-company-photos-savannalim-6.jpg?t=1778215176) The next phase of Sentience will move beyond just capturing facts, details, and summaries from your day. Sentience is already the most powerful way to capture and recall information from your life, but this is just the first step. There are three core facets that make up the next iteration of the product. [1] We're calling the first Core Memory Unlocks. ![Core Memory Unlocks feature screenshot](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/00ea8549-9293-47dd-b10a-df1d4eaaa959/image.png?t=1778203124) In addition to capturing audio conversations, learning from your screen, and wrangling your context into a massive memory bank, Sentience will soon proactively elevate the most important memories and insights that arise from your day. These will appear as cards in your timeline, just like other memories. They will form key nuggets of knowledge that your Sentience will use to form its identity, values, and ability to operate. [2] These core memories create auto-generated wikis. Imagine if your life was automatically organized and categorized into a personal knowledge base—a wiki for your mind—just by leaving Sentience running. Wiki pages can be people, projects, groups, themes, and more. And the best part is, it's all created for you, while you work. This is shipping by end of week! [3] The third component is proactive messages. Your Sentience is going to become more curious—it will begin to ask *YOU* things about how you operate, why you made decisions, or just why you are the way you are. This gets us closer to our mission of capturing and preserving what makes you, *you*. → Your taste, judgement, expertise, and wisdom. → The ideas that don't live in an email or iMessage, but are core to how you make decisions, run your business, and make your mark on the world. Over time, this compounds into the richest representation of everything that makes you special. ## Sentience's unique approach to data ownership and privacy ![Sentience privacy and data settings screenshot](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/f5ff613f-8567-432f-88c4-9a7fa3d987b6/Screenshot_2026-05-06_at_10.38.35_AM.png?t=1778085519) Your Sentience is the most personal product you own. It holds your thoughts, relationships, decisions, and memories, and our team has a fundamental responsibility to secure and protect that information. Because of the nature of our product, we hold ourselves to a higher standard than other AI companies. We owe it to you to be as transparent as possible about our security and privacy practices—as the most ambitious, creative, and extraordinary people on earth begin to build their digital selves, they deserve to feel at ease about the safety of their data. **[1] How your data is handled** Your data is encrypted in transit and at rest, with zero retention by any third-party model provider. While other AI companies keep and train on the data you give them, at Sentience, your data belongs to you. We're currently in the process of obtaining SOC 2 certification. For many of our users, Sentience doesn't just hold personal memories, it holds business conversations, proprietary strategy, and information from their work. Those users and the companies they work for should feel certain that their data is safe with us. **[2] Sharing, on your terms** When your Sentience interacts with the outside world, you control exactly what it shares. We've stress-tested our external sharing guardrails with hundreds of adversarial prompts across dozens of attack categories. If something is off-limits, it stays off-limits, regardless of how the question is asked. By default, an entire category of sensitive topics is permanently blocked from external sharing, including credentials, financial information, health data, legal details, home addresses, and relationship details. Over time, we'll give you granular control over exactly what you want to share and with whom. Every human being is different—what one person shares openly is very private to someone else, and we want you to be the one who decides what gets shared. **[3] Your Sentience is your property** Most software you use is licensed—you don't actually own it, and when you die, it disappears. We think that your Sentience should belong to you. You can export your data anytime, delete your account anytime, and when the time comes, leave your Sentience to the people who matter to you. We've structured our Terms of Service so that your Sentience can be left in your will, transferred to your heirs, and accessed by the people you choose after you're gone. We've built all of this into our foundation from the start because you're entrusting us with who you are, and we will do everything we can to protect it. ## Prompt of the week: Things only your Sentience can do Every week, we're excited to see all the new ways that beta users are utilizing their Sentiences. Users have generated a personalized growth strategy that cited their conference talks and newsletters, created a comprehensive profile of their communication style, and turned their Sentience into a research partner with perfect recall of every paper they read. Sentiences have written many blog posts, drafted hundreds of emails, and even written April Fools jokes. ChatGPT doesn't know your voice. Claude doesn't know your values. No generic model has access to what makes you who you are. Sentience is the only tool that can help you preserve what makes you unique, augment how you think and communicate, and actually act on your behalf—because it's the only one that knows you well enough to do so. **Two more user stories from this week:** A user asked ChatGPT, Claude, and Sentience the same question, but only Sentience knew them well enough to give a real answer: > "I asked ChatGPT, Claude, and my sentience to recommend who I should vote for in the June primary election based on what it knows about me since I just got my mail in ballot. I asked for a top choice and why, and a secondary choice and why I might prefer that one. ChatGPT/Claude both gave me a speech about how it's a moral imperative that I make my own decisions and only offered frameworks. Sentience gave me exactly what I asked for. It's either magic or an issue y'all need to look into (I like it)" > > —Sentience Beta User Sentience drafted a context-aware email from Slack messages in a casual, appropriate tone: > "Had my first magical Sentience experience! I had to deal with an annoying issue with a service we use to send social posts, and sentience was able to get 90% of the email written for contacting support by watching my slack conversation with my cofounder. Love the casual, non-AI tone as well as it finding the support email that traditional Gmail search made difficult to find." > > —Sentience Beta User ## What's new? (v1.1.4 - v1.1.10) - **Slack**: Live Slack search with citations - **Calendar**: Calendar event proposals mid-chat - **Messaging**: Image attachments with iMessage-style previews - **Navigation**: New keyboard shortcuts and stop button - **Recovery**: System recording auto-recovery - **Audio**: Graceful audio recovery during phone calls - **Settings**: Account deletion in Settings (Danger Zone) - **Design**: Memory grid card spacing improvements - **Audio**: Downloadable audio memories - **Notifications**: Meeting notification and toast fixes Thanks for being with us on this journey. See you next week, [Sam](https://www.linkedin.com/in/samkececi) and [Teddy](https://www.linkedin.com/in/teddy-schoenfeld/) --- ## Recall #7: Your Sentience Wants to Learn from You By The Sentience Company Team, 2026-05-15. Your Sentience now pings you first, remembers everything in a personal library, and looks brand new. Canonical URL: https://sentience.com/company/recall-7-your-sentience-wants-to-learn-from-you ## This Week's Recap We've shipped a lot in the last week that fundamentally changes what Sentience is and what it can do for you. Until now, Sentience has been a super powerful capture and recall engine—great at understanding and recalling the messy data across your work. We're now letting it represent you, speak for you, and ask you questions to learn more about how you operate. We also want to give you a window into our thinking. What's been inspiring us? ## Sentience as a living proxy for you This week we've made big strides towards enabling Sentience as a sharable proxy for your knowledge. To achieve this, there are two key pillars: 1. Sentience builds an understanding of your values, expertise, and judgment that is richer than any other system. 2. Sentience is sharable with your team and collaborators. It should meet them where they are. And finally: 3. Why does this matter? I will discuss each. ### [1] How Sentience compounds to form the horizontal layer of who you are. ![Screenshot of Sentience proactively messaging with a question](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/f2b86fff-3a27-4abc-b9ec-c93cdb747381/Screenshot_2026-05-15_at_12.13.04_PM.png?t=1778862114) Your Sentience will now prompt you and ask you questions about who you are, what you're working on, and how you operate. Rather than you having to ask your Sentience for important information, your Sentience will proactively start message threads. Importantly, they will always be driven by what's actually top of mind for you. They are unique to you. Over time, these compound: your Sentience evolves from basic facts to deep understanding. ### [2] Sentience in Slack (iMessage soon) ![Screenshot of Sentience in Slack](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/016fcc9d-38b7-423d-bd96-ce34fa795748/Screenshot_2026-05-15_at_11.09.30_AM.png?t=1778858027) This week we rolled out our Slackbot integration to a bunch of teams. Sentience is a digital twin of *you*, so it should interact in the same surfaces that *you* do as a human. If you're interested in adding your Sentience to communicate with your team in Slack—reach out to us ([sam@sentience.com](mailto:sam@sentience.com)). We're doing this manually to make sure we get it right, but we plan to open things to self-serve onboarding soon. ### [3] What does the world look like when we all have a digital version of ourselves? ![Illustration representing a digital version of yourself](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/658cb838-8a04-4771-b427-91697c6d1d96/image__15_.png?t=1778862481) It looks like: - Engineering standup being simulated by each team member's Sentience instead of wasting human time sharing knowledge. - Founders and CEOs being able to answer their team's questions 24/7, even while they get some much needed sleep... - Teachers and professors using their Sentience to reach students 1:1 they wouldn't normally be able to. It looks like preserving your wisdom and legacy even beyond the confines of your physical mind—creating a version of yourself that can live forever. ## Auto-generating Personal Library Personal libraries are live for every beta user. When you create your Sentience account and begin to capture memories, your life gets organized into a living knowledge base. Pages are created automatically—the people you talk to, projects you're working on, groups you belong to, themes running through your days. You don't have to do anything. Your Sentience watches, learns, and builds. Think of it as a map of your world. Who matters to you, what you're focused on, how your priorities shift over time. These wikis aren't just for browsing. They feed directly into how your Sentience thinks. When it answers a question or makes a recommendation, it's drawing on structured understanding of your life and reasoning about your world. ## User Dinner ![Photo from the Sentience user dinner in Williamsburg](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/c341671e-1979-45a0-ac1e-3321cabe34f0/DSC_1455.jpeg?t=1778800187) This week we hosted our first in-person beta user event in Williamsburg. Our earliest users came together to meet each other, share how they're using Sentience, and see some new stuff that's in the works. Thank you so much to those of you who joined us! We'll do our next user dinner soon—West Coast next? ## New UI ![Screenshot of the redesigned Sentience app UI](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/76161bff-bd37-4972-9877-713363e45ea6/Screenshot_2026-05-15_at_11.49.21_AM.png?t=1778860169) We redesigned the entire app from the ground up. New grid layout with daily groupings, refined memory cards, redesigned audio and screen capture controls, a new design system and component library, and improved spacing across the board. ## What's new? - Sharing: Slackbot with privacy guardrails live across workspaces - Multiplayer: Slackbot onboarding with deep link configuration - Wikis: Auto-generated knowledge base pages for people, projects, and themes - Proactive: Improved proactive message quality and relevance - Calendar: Calendar event proposals mid-chat - Settings: Account deletion in Settings (Danger Zone) - Audio: Downloadable audio memories - Audio: Graceful audio recovery during phone calls - Design: Full UI redesign—new grid, new cards, new design system - Notifications: Meeting notification and toast fixes Onwards, towards digital immortality... See you next week, [Sam](https://www.linkedin.com/in/samkececi) and [Teddy](https://www.linkedin.com/in/teddy-schoenfeld/) --- ## Recall #8: In Lockstep By The Sentience Company Team, 2026-07-09. Your Sentience now understands the full picture of your life, runs Routines on a schedule, and rewards you for referrals. Canonical URL: https://sentience.com/company/recall-8-in-lockstep Visit [sentience.com/early-access](http://sentience.com/early-access) for free access to Sentience and white-glove onboarding from our team. ## Create and Own a Model of Your Mind It's been a while. We've changed a lot in the product. We've narrowed our vision and are going all-out to make Sentience a product that elevates you as a human. Your Sentience understands the full picture of your life. Every suggestion it makes is hyper-personalized and relevant to you. If you have a strategy call and ramble through 4 ideas, your Sentience turns it into a structured plan in Notion with owners, next steps, and deadlines before you close the app. If a trip is coming up and there are loose ends scattered across group chats and email, your Sentience pulls them all into one place, tells you what's urgent, and drafts the messages you need to send to get everything locked down. If you mention grabbing coffee with someone in a text, your Sentience checks your calendar, picks a time, and has the invite ready for you to send. If you're in a rough stretch and can't sleep, your Sentience surfaces what you said last time you were in the same spot, reminds you how it ended, and shows you the evidence that you've been here before and come out the other side. No other tool lives in lockstep with you like this. Your Sentience sees the full picture of your life and acts on your priorities before you can. ## What's New? - **Suggested Prompts**: your Sentience takes action on your behalf before you even ask. - **Routines**: automate the stuff you do every day but shouldn't have to think about. Your Sentience runs tasks on a schedule and delivers rich, context-aware output. - **Referrals**: invite friends and collaborators to Sentience for free and earn rewards along the way. AirPods Max, Apple Watch, Oura Ring, merch, and free Sentience for life. - **Library**: a wiki of your entire life that writes itself. Your Sentience maintains structured, up-to-date pages on the people and things that matter to you. - **Notion integration**: your Sentience reads, writes, and edits your Notion directly. Ask it to update a page, create a doc, or pull info from a database with its information and context. - **Pre-Meeting Brief**: your Sentience pulls from past calls, emails, texts, and notes to brief you on what you need to know before every meeting. - **Onboarding** (in progress): we're rebuilding the entire first experience. The goal is getting you to the magic of Sentience faster. ## Routines Your Sentience now runs tasks on a schedule and delivers useful, context-aware output without you lifting a finger. - "Every morning, check my calendar and email and tell me the three things I need to handle before noon." - "Every Monday, pull my PostHog metrics and draft a weekly update for the team in Notion." - "Every Friday at 5pm, look at all the threads I said I'd follow up on this week and draft the ones I haven't sent." - "After every meeting, write up the notes and next steps in Notion before I context-switch." Routines run with full context of your life and produce high-quality actionables: an email draft, a summary, a decision laid out with the info you'd need to make it. You wake up and your morning briefing is already sitting there. You start your Monday and last week's shipped work, open threads, and key numbers are already formatted into a team update. You get to Friday and every follow-up you promised this week is drafted and waiting for you to hit send. Every Sunday, it looks at your calendar for the week ahead and tells you where you're underprepared. ![Screenshot of a Sentience Routine](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/8493c2eb-a1c9-455d-a279-7f22b28c3c61/Screenshot_2026-07-09_at_10.54.21_AM.png?t=1783608865) Access **Routines** in your navigation bar on the left side of your desktop app. ## Referrals You can now invite friends and collaborators to use Sentience for free, and we're rewarding you for it. > **5 referrals**: 1 month free Sentience + Sentience socks > **15 referrals**: 6 months free + Sentience hat or hoodie > **30 referrals**: 1 year free + Apple Watch or Oura Ring > **50 referrals**: Lifetime free + AirPods Max + early access to new features + persona setup session with the team Rewards are cumulative, so 30 referrals gets you everything from every tier above it too. ![Screenshot of Sentience referral rewards](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/5c5b9b89-f00a-4343-beb0-955e80105843/Screenshot_2026-07-09_at_10.14.08_AM.png?t=1783606451) Find your referral link in the Desktop app (click your name → "Send to a friend" → enter emails). The product is still free, so there's no friction for the people you send it to. Your referrals will be automatically attributed once they sign up for the product. With gratitude, —[Sam](http://linkedin.com/in/samkececi) and [Teddy](https://www.linkedin.com/in/teddy-schoenfeld/) --- ## Recall #9: Top of Mind By Sam Kececi and Teddy Schoenfeld, 2026-07-29. Teaching your Sentience to 'manage up': a look inside the new Suggestion Engine, plus research on personal writing style. Canonical URL: https://sentience.com/company/recall-9-top-of-mind Visit [sentience.com/early-access](http://sentience.com/early-access) for free early access to Sentience and white-glove onboarding from our team. ## Suggestion Engine This week, we wanted to give you a peek behind the curtain at what we're working on. Our team has been heads down creating Sentience's new Suggestion Engine. The engine will be used to determine what's top-of-mind for you and get it off your plate. It will pre-draft messages for you based on your priorities, triage information and strategy into documents, suggest and implement routines based on your patterns, and much, much more. This is all focused on our core goal of modeling both your motivation and your knowledge. Sentience will learn how you prioritize and get better over time from watching you work. ![Planning the Suggestion Engine architecture](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/894a2223-6a5e-4f65-a1a1-d942ef81ab0d/IMG_1242.jpg?t=1785264329) ![Check out the Sentience sticker on Jules' Mac!](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/7ef99ed4-9b85-496f-b1a3-68c10b53adfe/IMG_1258.jpg?t=1785264336) Our engineers [Jules](https://www.linkedin.com/in/juleslabador/) and [Ben](https://www.linkedin.com/in/benjamin-carsley-89a4b2239) are spearheading this project, which is set to become the new core of our desktop app homepage. We're going to launch this in 2 weeks to an early cohort, and then broadly on August 25th. Right now, the Suggestion Engine searches through all incoming memories and identifies what you need to work on: email replies, calendar invites, research, and more gets kicked off to your agent from a centralized feed. Instead of staring at the dreaded empty prompt box, your Sentience is the one sending you the first message. At Sentience, we talk a lot about "managing up"—the idea that you should push rather than pull tasks and insights. Sentience will now start managing up to you instead of waiting for you to prompt it. ![An early version of the output of the Suggestion Engine (pure dev prototype).](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/d97d40ed-4d47-46c6-ad20-e245d5f00b12/Screenshot_2026-07-28_at_2.23.08_PM.png?t=1785264681) This is an early mock of how suggestions produced by the engine will look on the homepage. You'll be able to edit and send messages using hotkeys so that managing your life from your Sentience becomes effortless. ![Suggestion Engine homepage mockup](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/8a527ad5-479f-4c22-8bb3-a571dd3acea2/47.png?t=1785268493) These are preliminary designs for the new homepage! Our designer [Pedja](https://www.linkedin.com/in/pedjaristic) is bringing these to life in the desktop app very soon. ## One Person, Many Voices AI writing benchmarks normally measure two things: whether a sentence or passage is grammatically correct, and whether it's factually correct. But benchmarks don't measure whether writing is written in your style, because there's no test set to score against. This is why AI writing is still so recognizable even when you ask your agent to write for you. [Ben Carsley](http://linkedin.com/in/benjamin-carsley-89a4b2239), who leads our tone and style work, took his full writing corpus—2,406 texts, 409 emails, 406 Slack messages, 134 passages of academic writing—and analyzed it twice: once by topic, to see how his writing shifts with subject matter, and once by style, to see how his style shifts across channels. ![Ben's writing corpus, embedded on semantics](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/af6fa5cd-6494-4eed-a118-e2a8c3fc514a/Screenshot_2026-07-28_at_1.57.31_PM.png?t=1785264834) ![Ben's writing corpus, embedded on style](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/d3d0f21c-7dfd-42f9-93db-858fa41b7796/Screenshot_2026-07-28_at_1.59.16_PM.png?t=1785264842) [The numbers are revealing](http://sentience.com/voices). Ben starts 96% of his texts with lowercase but only 18% of emails. His median text is 18 words, his median email is 40, his median academic paragraph length is 120. His em dash rate quadruples from texts to academic writing: 3.3 per thousand words to 13.2. Corpus linguists established forty years ago that people shift their writing as much between registers as much as different people in the same register, and Ben's research confirms the results. Ben's work driven massive improvements in person-specific tone and style output. Our tone and style work is continually evolving, so stay tuned for more. Read the full writeup at [sentience.com/voices](http://sentience.com/voices). Kudos to Ben for all his work! ## User Spotlight: Orçun Dogmazer ![Orçun Dogmazer](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/131de7a7-83b0-4112-aed7-9103bc2583b7/image__2_.png?t=1785265467) Orçun is a VC at ScaleX Ventures in Istanbul, and he started using Sentience the way most people do: as a work tool. Sentience became the layer that pulled his deal flow, LP comms, portfolio updates, founder conversations into one place. Gradually, the ways he used Sentience grew. Orçun logs everything—coffee with his mom, a movie, photos with the people he loves. He puts it all in his calendar in full detail, and Sentience makes it searchable and alive. In late June, he got married (congratulations!) and he used Sentience to help pull together information to write his wedding vows. He had the story and the flow he wanted, but Sentience surfaced the specific memories he would have otherwise forgotten to include. In Orçun's words: "It resulted in something deeply personal and true." ## What's New? - **Slack message sending:** Your Sentience sends Slack messages, replies, and DMs on your behalf directly from chat - **iMessage sending:** Your Sentience sends iMessages directly from chat - **Notion inline edits**: edit Notion pages in-place from chat + new database entry checks - **Web links as memories**: add any web link as a searchable memory, or ask your Sentience to read a page and save it - **Edit audio transcripts**: fix/edit any recording transcript and its summary directly - **Search memories** from the Memories tab Until next time, —[Sam](http://linkedin.com/in/samkececi) and [Teddy](https://www.linkedin.com/in/teddy-schoenfeld/) --- ## Recall #10: Meet Your Digital Self By Teddy Schoenfeld and Sam Kececi, 2026-08-12. A new Profile, a deeper Sense of Self, and an avatar that makes your Sentience unmistakably yours. Canonical URL: https://sentience.com/company/recall-10-meet-your-digital-self We're preparing for an upcoming launch! Join us at [sentience.com/early-access](http://sentience.com/early-access) to be the first to hear about it and get an extended free trial when we go live. ## Building a Profile of You Every personal AI system starts from roughly the same place. Connectors can give it access to your context, but they often don't promote deep understanding. Your system can have access to all the messages and emails in the world without knowing how you think, decide, work, or relate to other people. ![Screenshot of the Sentience Profile screen showing archetype and trait results](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/5c40ce9f-6060-4335-97a6-bb20a590631a/image.png?t=1786546286) A true digital self should feel personal immediately. So we built a traits analysis that creates a profile of who you are in about five minutes. The test mixes rapid-fire decisions, real-world scenarios, and questions about how you work. Your results give you one of ten archetypes and a hyper-personalized trait map of where you fall on six different spectrums. ![Screenshot of the hyper-personalized trait map showing six spectrums](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/18399da7-df3d-4c36-bab3-e63c4d6203f3/image.png?t=1786546300) These results become the starting point for how your Sentience understands and supports you: they shape your Profile and help your Sentience recommend routines that fit how you work. From there, your model keeps evolving. Your Sentience learns from your email, calendar, messages, meetings, connected sources, and direct feedback. The personality test and Sense of Self interview give it an initial picture of who you are, and the context of your life makes that picture deeper and more accurate over time. ## Custom Avatar and App Icon ![Grid of custom Sentience avatars generated from a photo, from photorealistic to stylized](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/fa266075-b0d0-4880-a6c3-ed0d17b95da9/teddy-3.0-avatars.png?t=1786547978) Your Sentience now has a customizable, high-fidelity avatar generated from a photo that you upload. The base version will be a video-game style photorealistic avatar (see the leftmost image below), you have the freedom to customize it however you choose. Have fun with it and share your avatar in the Discord! ![Personalized Sentience Desktop app icon based on a custom avatar](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/37e7608f-0d84-4e1e-8146-f27fef1f5115/image.png?t=1786546605) Your avatar appears throughout the product and even becomes your personalized Sentience Desktop icon. There is no longer one universal icon—if your Sentience is a unique model of you, it should give you a unique app icon! ## Sense of Self ![Screenshot of the Sense of Self section inside the Sentience Profile](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/71089515-cdb3-4a99-a7e3-f2a3f34d1973/image.png?t=1786547564) Your Sentience now has a durable layer where your most important details, preferences, and principles live. Your Sentience's Sense of Self lives inside your Profile. These sections provide your Sentience durable context it can utilize when helping you make decisions or act on your behalf. ![Screenshot of the Sense of Self quiz interface](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/241d421b-d7ef-4224-b45f-f07421eaffcb/image.png?t=1786547601) Although these sections will generate automatically after your Sentience knows you well enough to fill them out, you can jump-start this process with a short voice chat. The new Sense of Self quiz gives you a direct way to teach your Sentience about your values and preferences. It is voice-first: you respond naturally to questions about your experiences, preferences, relationships, and decisions. Your Sense of Self will auto-populate with the answers your provide. We're speeding towards a future where your Sentience truly feels like a digital extension of you, and a personalized, interactive profile is the most recent step on that journey. ## User Spotlight: Anna Levitt ![Photo of Anna Levitt, founder of Bubble Boss Co.](https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/76337094-d62c-4719-8e54-92300bb33fc4/ALevitt_Image.jpeg?t=1786546534) Meet Anna—and Coach Anna. Anna Levitt is the founder of Bubble Boss Co., where she works as a fractional Head of People and coaches leaders to utilize AI effectively without losing the human judgment behind their work. She starts many mornings with Sentience, catching up on what she needs to know over her morning coffee. Her Sentience surfaces relevant context, helps her think through decisions, and drafts emails in her voice. It also captures ideas whenever they arrive—including the ones that Anna has in the middle of the night. Now, she's exploring Coach Anna, a client-facing Sentience grounded in her coaching methodology. Her vision is for Coach Anna to understand each client's goals, context, and working style and support their reflection between sessions. Anna doesn't want to automate the relationship aspect of coaching, but Coach Anna helps extend the parts of her work that don't require her direct presence, and preserve her judgment for the moments that do. ## What's New? - **Archetype and traits:** Take a three-minute test to discover your archetype and six core traits, then see your results in Profile. - **New Profile:** A redesigned home for your avatar, model version, archetype, Sense of Self, and Principles. - **Personalized icon:** Turn your generated avatar into your desktop app icon. - **Sense of Self:** Sentience learns your habits, constraints, and preferences and applies them when you put it to use. - **New onboarding:** Get from creating your Sentience to useful output faster. - **Home redesign:** Actions, reflections, and daily context now live in one cleaner feed. - **Suggested routines:** Get personalized recommendations for recurring work based on your personality and patterns. - **Reliability:** Better headlines, fewer duplicate drafts and messages, clearer completion states, and correct Google Messages attribution. Until next time, —[Teddy](https://www.linkedin.com/in/teddy-schoenfeld/) and [Sam](http://linkedin.com/in/samkececi)