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.

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 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.

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.

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.

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:

Sentience drafted a context-aware email from Slack messages in a casual, appropriate tone: