Pinned Tweet
Today we're introducing Slite as the first self-maintaining Knowledge Base
Your wiki docs go outdated everyday, and your agents depend on them for your most ambitious workflows.
Slite monitors your docs' accuracy from all other work tools (slack, jira, linear, codebase, etc) while you sleep and updates them.
It even directly talks to your AI agents to give them accurate context without burning their context window or tool calls.
You've been trying to build this 'company brain' for months now with hacky MVPs
This is the final version of what you need, already built to be collaborative, headless, and secure.
Check it out and HMU if you need this for your team, I'll be running personal onboardings for the next few days!
Christophe Pasquier °} retweeted
The scariest thing in your team's stack this Halloween?
An AI that answers from a two-year-old document, and sounds completely sure about it 👻
Slite Agent dressed our team up based on how we keep our knowledge.
Open Slite Agent to find yours (dark mode has an extra treat 🌙)
Christophe Pasquier °} retweeted
How much of your company's documentation would you trust an AI agent to act on?
That's one of the questions in our survey for our next playbook: how teams keep company knowledge accurate enough for people and AI to trust.
If you own documentation on your team, or you're rolling out AI on top of it, we'd like to hear how you do it. It takes about 10 minutes, and you'll see the findings before anyone else.
Take the survey: forms.gle/tTHkj8aGNNTfMTxT9
Prefer to talk it through? There's a link to book a 30-min call at the end, and everyone we interview gets a gift card. 🎁
Christophe Pasquier °} retweeted
Amazon’s site went down after an AI agent read an old wiki document.
But how many of those documents do we all have? 👀
In March, Amazon’s retail site had four high-severity incidents in one week. One traced back to an engineer following AI advice that came from an outdated internal wiki.
AI agents now read our documentation and act on it, but a lot of teams can’t say which pages are still up to date.
You’d expect AI to make this easier. In practice it makes it trickier: agents answer from an old page just as confidently as from a current one, and they write new pages faster than anyone can check them.
Usually someone on the team keeps updating the documentation, often without it being their actual job.
That’s what our next research piece at @slitehq is about: how teams keep their knowledge accurate enough to trust, for people and for AI.
The survey for our last ebook, on company brains, got so many great responses and interviews. If this topic speaks to you, I’d love your experience and opinions in this one too.
Here’s the 10-min survey: forms.gle/tTHkj8aGNNTfMTxT9
If you’d rather talk it through, there’s a link to book a call at the end, and everyone who does an interview gets a gift card 🎁 💸
Using Jev to classify an 8 yo workspace with ~20k docs cost 1$
I could get used to these kind of bills anymore 😅
Quality of life improvement for Slite
When you get notified of a change, you land on the history view, and see exactly who changed what, when, via which agent.
I've never seen any other doc tool do this, and I could not come back.
Christophe Pasquier °} retweeted
Using France's fiscal problems to argue against voting for Democrats feels off base. Just look at where American innovation thrives: California, Massachusetts, New York and Washington
We can protect innovation, reduce deficits by tackling corruption, tax breaks for the wealthy and costly wars, fight inflation & still build a compassionate society that protects the most vulnerable
(Oh and I love France. This isn't a dig at France. If it shifts hard right, I suspect things will get way worse. But that's a post for another day)
I’m French. I want to talk to Americans who are about to vote Democrat. Not to insult you. To warn you.
I come from your future.
In France we did everything your progressive politicians promise. Free healthcare, free college, generous welfare, strong unions, heavy regulation, high taxes on the rich, a state that takes care of everything. Public spending close to 57% of GDP, one of the highest on the planet. On paper, it’s the dream.
Here’s what it looks like from the inside. France hasn’t passed a balanced budget since 1974. Our debt is above 3,300 billion euros. Interest on that debt is becoming one of the biggest items in the national budget. Our hospitals are collapsing despite record funding. Our schools rank lower every year. Young people with degrees can’t afford an apartment in the city they were born in. Our best engineers leave for London, Zurich and San Francisco. And the rich you wanted to tax? They left too, and took the jobs with them.
The promise was protection. The result is stagnation.
The worst part is that nobody in France voted for decline. Every single step sounded generous, compassionate, reasonable. One more program. One more regulation. One more tax to fund it. Each step alone makes sense. Fifty years of them, and you wake up in a country that can no longer build a nuclear plant on time or keep its streets safe.
I love America because it’s the one place on earth where people still believe they can build something from nothing. I came to Silicon Valley as a self-taught kid and it changed my life. That spirit is the most precious thing your country has.
Before you vote, ask yourself one question: is the program you’re voting for making America more like America, or more like France?
Trust me. You don’t want to be France.
Christophe Pasquier °} retweeted
We hosted a company brain webinar to talk architecture.
But the questions that kept coming back were about maintenance:
1. Who reviews a change before it lands?
2. Which edit wins when two people disagree?
3. How do you know a gap the agent flagged is real?
Building a company brain is the part everyone plans for. Keeping it accurate is what they wanted to know about.
Five of their questions are in the image, and answered by Yochan Khoi from Gorgias, who built their brain in-house, and Christophe Pasquier (@Christophepas) who built Slite.
Missed the webinar?
Watch the full session: slite.com/webinars/company-b…
What's the maintenance question your team hasn't answered yet?
ALT What builders asked us about company brains: five questions from the Company Brain webinar on access, conflicts, trust, team size and integrations, each answered by Yochan Khoi (Gorgias) or Christophe Pasquier (Slite).
Christophe Pasquier °} retweeted
Your dev team is shipping faster than ever with AI.
Your help center hasn't kept up.
In this demo, a maintenance routine finds a merged PR that changes product behavior and suggests an update to the help center.
How it works:
1. Set which documents to check, how often to run the check, and who's responsible for reviewing them.
2. Choose the sources the routine should check against.
3. Review the suggested changes before accepting an update.
This clip comes from Company Brains in Action: Build vs. Buy, our 22 September webinar with Christophe Pasquier from Slite and Yochan Khoi from Gorgias. It shows the maintenance workflow being developed in Slite at the time.
Full session: slite.com/webinars/company-b…
Christophe Pasquier °} retweeted
We just solved attribution for AI Agents.
Introducing Journeys.
AI agents are visiting your product. Now you can see what they’re trying to do, what converts, and what’s making them churn.
With Journeys, you can:
- See the moment AI agents visit your product
- Follow the paths they take
- Track purchases, installs, and completed setup
- Pinpoint where agents get stuck and whats blocking them
- Review fixes prepared for you and publish them with a click
- Watch how those changes improve conversion
Turn agent traffic into revenue.
Try Journeys at tryscope.com
Christophe Pasquier °} retweeted
We're live on Product Hunt today ! An upvote takes five seconds and helps us a lot.
Tristan says he'll owe you something forever. I'll make sure he pays up 😅
xitter.cf/tristan_cte/status/211…
the best thing you can do to help me today
=> upvote here producthunt.com/products/pan…
I'll owe you something forever!
Christophe Pasquier °} retweeted
This is the Frame .io for the agentic video era
Introducing Flask: give feedback and collaborate on video with together with Claude, Codex, HyperFrames, Remotion or any agentic workflow
Try it free at flask.do or copy the prompt ↓
Christophe Pasquier °} retweeted
Meet Pancake, the Vercel for GTM.
Try it at pancake.ai
Your agent ships your product. Now it ships your go-to-market.
How? A GTM brain that knows your business, 50+ data providers to find the right customers and tools to reach them.
Your next customers are one prompt away.
(did I really have to jump off a plane to say that? questionable, but I survived and now you're reading my tweet)
Christophe Pasquier °} retweeted
What does an AI harness actually do?
These 6 terms explain how an agent goes from a request to a finished task.
Let's take this example: a support agent that checks an order and drafts a reply.
What happens at each step:
/1 Agent loop
The model chooses an action, a tool runs, and the result comes back. The cycle continues until the reply is ready, help is needed or a limit is reached.
/2 Tool calling
The model requests a tool by name, with arguments. The harness checks and executes that request, then returns the result. An order lookup gives the model a delivery status it can use.
/3 Context management
What the model sees at each step comes from your instructions, the conversation and tool results, like the order status. When the window fills up, older messages get compacted, and your prompts and hooks decide what's kept.
/4 Checkpointing
The workflow saves its state outside the model. After an interruption, it can reload the order lookup result and continue from a saved point.
/5 Permissions and sandboxing
The harness sets what the agent can touch: which tools, files and actions, and where code runs. The support agent can read the order but can't issue a refund.
/6 Guardrails
Checks inspect inputs, outputs or proposed actions. An output check can inspect the drafted reply; an approval gate can pause before sending it. Those are different controls, and neither catches every error.
The real payoff: you can switch between models from different labs and share the same skills and context across your team.
Which part is hardest to get right in your setup? 🤔
ALT AI Harnesses: six illustrated concepts. Agent loop repeats actions and results; tool calling retrieves order status; context management compacts older chat; checkpointing restores workflow state; permissions and sandboxing allow reading an order but block a refund; guardrails can require human approval before sending.
Christophe Pasquier °} retweeted
From our 22 September webinar, Company Brains in Action: Build vs. Buy, with @Christophepas (Slite) and Yochan Khoi (Gorgias).
Full session: slite.com/webinars/company-b…
Christophe Pasquier °} retweeted
Meet Mistral Large 4, aka Le Chonk.
• 1T parameters, natively multimodal. 49B active.
It is the best open weights model from US or Europe on aggregated benchmarks.
• State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding.
• Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure.
• Available to all via API today. Working with cybersecurity partners privately.
Open weights release end of October.
🤖 Made with AI
