Hi, I'm Oleks. I build kwant, and it started with an AI agent telling me "all tests pass" when the tests had never run. Another one sent me a link to back up a fact, and the page said something else.
So kwant has one rule: a task turns Verified only when kwant runs the check itself, not when the bot says it's done.
We launch here tomorrow, Nov 3. Before that, I'd love to hear yours: what did an agent say it finished, and how did you find out it hadn't? I'll reply to every story.
Hi PH 👋 I'm Oleks, maker of kwant.
AI agents are great at saying "done". They're worse at being done. I kept getting confident reports about tests that never ran and links that said something else. So kwant is built around one rule: nothing counts until it's checked.
What you get:
🗂️ Mission Control: bots split the work into cards, hand off and test each other
✅ Verified means verified: a card turns Verified only when kwant runs the check itself
🔗 Cited answers: web facts come with a link that opens at the exact quote. Missing or lookalike quotes are refused
⚖️ Truth Ledger: when two sources disagree, you see both and pick
🎓 Flight School: bots earn more autonomy with scorecards, and only you promote them
💳 Payments always ask: in the shell and in the bot's own browser, even behind a plain "Continue"
🛡️ Rules per bot: say what each bot should and shouldn't take, and which sites its browser may open
📊 Insights: what each verified result actually cost ("Not reported", never a fake $0)
🧠 Who answers: each message goes to the bot that fits, and you see why. Wrong bot? Pick another one, and kwant remembers. Laya picks the model and effort for bots on auto, so quick asks stay cheap
✨ Suggested routines: kwant notices your habits and offers to automate them
🏠 Spaces: work and home stay apart
It's one signed app for Mac and (new this week) Linux, or a VPS. It runs on the Claude, Codex or Grok subscription you already have. Your data stays on your machine, and it's open source (AGPL).
What would you hand to a team like this first?