Christophe Pasquier 🇺🇦

Genius feature @conductor_build

i have a lot of respect for @arthurmensch for trying to engage and educate the french institutions. This is un-ironically important work that you're doing mate 🙏 May it be fruitful

@pdotcv @mikejulian @linear @cursor_ai And why do you need to navigate to their website ? Is it just because it’s great inspiration ?

@Christophepas @mikejulian @linear @cursor_ai My URL bar autocompletes to a specific blog article now as my route to the Linear marketing site. Should probably just bookmark the homepage.

Major pet peeve: apps that deploy on their root domain instead of app.domain.tld or whatever. Makes it so annoying to look at the homepage. lookin at you @linear and @cursor_ai

Honestly, faster horses would've been way cooler.

There is massive value in purpose-built. I also have had the same for a year, with more comprehensive data than Granola could even grab, yet I'm in love with having no maintenance efforts and to delegate the taste and details to @meetgranola

@novikoff @rive_app Lovely file name too 🥰

oh man what a pleasure working in .@rive_app

@avstorm Finally 🔥

Slite logo was ready for this

@femke_plantinga @slitehq Perfect shape for this trend

late to the party? 🪩 @slitehq

Everyone's building a personal Knowledge Base. For one person. But what about teams? Obsidian. Notion. Claude. Readwise. It looks clean. It feels smart. It works great. Here's what nobody shows you when you try to do the same for your team ↓ Permissions & access control Verification & expiry cycles Owner accountability Staleness detection Multi-source ingestion (Slack, GitHub, Jira, Linear, Drive...) Conflict resolution (who's right when two docs contradict?) Onboarding flows Search at scale AI that knows what's trusted vs. someone's Slack opinion Guest management Audit logs SSO / SCIM provisioning Cross-tool search Content gap detection A personal KB needs one thing: you to keep feeding it. A team KB needs all of this, and it needs to run without anyone remembering to do anything. That's not a note-taking problem. That's an infrastructure problem. With @slitehq, we're building a knowledge base that maintains itself. More coming in June! 👀

@Griveau @linear so good

Recent Icons design work for @linear

Your codebase is your best knowledge base. You just can't search it in plain English. (Until now) Most AI tools search the docs your team wrote. But docs go stale. Code doesn't lie. Last week, a support agent asked Super: "What happens when a blocked user tries to sign up?", something no one had documented. 𝗠𝗲𝗲𝘁 𝗦𝘂𝗽𝗲𝗿, 𝗼𝘂𝗿 𝗔𝗜 𝗸𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 𝗮𝘀𝘀𝗶𝘀𝘁𝗮𝗻𝘁: → browsed the codebase → walked the relevant code paths → returned the exact behavior No ticket. No engineer pulled away from their work. No two-day wait. This is what @Christophepas, our CEO, shared for @Newsweek's AI impact newsletter last month: "The code has always been the real source of truth." Super connects to Slack, Intercom, your help center, and your codebase. Ask anything in plain English. Get a cited answer from wherever the truth really lives. Read the full post: newsweek.com/ai-impact-comp…

Your AI agent is only as smart as your worst doc. And your worst doc is probably 18 months old. Everyone's deploying AI agents right now. Cursor. Claude. Internal copilots. Support bots crawling your company wiki. But almost nobody is asking the obvious question: 𝗪𝗵𝗮𝘁 𝗵𝗮𝗽𝗽𝗲𝗻𝘀 𝘄𝗵𝗲𝗻 𝘆𝗼𝘂𝗿 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁 𝗿𝗲𝗮𝗱𝘀 𝗮 𝘀𝘁𝗮𝗹𝗲 𝗱𝗼𝗰? It acts. Confidently. At scale. One wrong answer to one customer becomes one wrong answer to five thousand before anyone notices. A stale doc used to be a human inconvenience. Now it's an infrastructure risk. So what does a team KB actually need to support AI agents? Four things: 1️⃣ Continuous ingestion: Your knowledge doesn't live in one place. It lives in the Slack thread where a decision got made, the support ticket that revealed a product gap, the meeting where the policy changed. A real team KB pulls from all of it — automatically, continuously. 2️⃣ A verification layer: A verified policy doc and a half-baked Slack thread shouldn't carry the same weight when your AI is answering questions at scale. The system needs to know what's been reviewed, approved, and trusted, and treat sources accordingly. 3️⃣ Freshness monitoring: A human skimming a doc might sense something feels off. An AI agent won't. Freshness monitoring flags content that hasn't been reviewed in months and surfaces docs that contradict newer information before they quietly become the source of truth. 4️⃣ Agentic maintenance:  The goal is to make human review scalable. Instead of waiting for someone to notice a doc is wrong, the system proactively identifies what needs updating, drafts a suggested fix, and puts it in front of the right person for a quick approve or edit. Karpathy said there's room for "an incredible new product" for personal knowledge bases. The same is true 10x over for team knowledge.

@felixhhaas This one hits hard 🔥

Today is a big day! We're launching Lovable Aesthetics 🔥 We just supercharged Lovable's design output. You can now ask for typography, layout, and color preferences, get various design concepts while building, and create much bolder landing pages, apps, and blogs. It's been my favorite thing to play with for the last few weeks. Go check it out!

Internal tracking for EGC 🔥

@langfuse @altalogy gorgeous isometric views!

new langfuse.com, new brand. same mission: open source LLM engineering platform. s/o to @altalogy for the great work.

@ayushsoni_io Great work

love where we landed w/ conduit

Startup School is coming to Paris! 🇫🇷 Hear from founders like @lxbrun of @amilabs, @oliveur of @datadoghq, @kiwicopple of @supabase, @james406 of @posthog, and more. And join the best builders and hackers from across France and Europe for a day of talks and sessions with YC partners.

@cynthiamcgillis Preparing @slitehq for this. Imo your skills should be in a human-agent format (docs) + constantly reviewed against team activity Skills are the new SOPs

How are y'all handling company-wide skills? Putting them in a repo? Does that work for Cowork and less technical teams? I feel like there has to be a better way to organize these.