Cleo
The AI PM that runs your team
573 followers
The AI PM that runs your team
573 followers
Cleo is the AI product manager for founders and lean teams. It lives in Telegram and Slack - learns your tone, knows your team, and runs the PM work (standups, follow-ups, decisions) while you ship the product. What's different: every fact Cleo learns is transparent - you see the source, the confidence, and can confirm or correct it. No black-box memory. Five trust levels, from observer to operator. Free in Telegram. 1 min setup
The AI PM angle is interesting because product work is not just task creation. The hard part is explaining why a priority changed. Can Cleo show the evidence trail behind a roadmap decision, such as customer feedback, current sprint load, and launch risk?
Cleo
@cyrus_elmtalab Exactly!!! The "why" is the part that matters. When Cleo shifts a priority it shows what moved it: which client/feedback triggered it, what's already on the team's plate, and what's at risk if you don't. So it's not "trust me," it's "here's the trail, you decide." That evidence layer is honestly the harder thing to build than the task creation itself.
Second Brain for AI
The transparent memory angle is really interesting. Showing the source and confidence level behind every fact the AI learns is something I haven't seen done this clearly. How are you handling cases where two teammates give Cleo conflicting information about the same decision?
Cleo
@rahilpirani When two teammates disagree, we don't pick a winner - we keep both claims, tag each with who said it and when, and flag the decision as contested instead of silently overwriting one with the other. Cleo then surfaces the conflict to you ("Sarah says the 15th, Marcus says the 22nd - which is right?"), and your answer becomes the source of truth, with the full history of who said what still visible.
The transparent memory model is what caught me — showing the source and confidence level for every fact it learns is genuinely different from how most AI tools handle context. Curious: when Cleo gets corrected, does it update globally or per-context? As a solo founder managing multiple workstreams, the "operator" trust level sounds useful but I'd want to know exactly what it can act on autonomously before handing over decisions.
Cleo
@hirogure Per-context by default - correct it on one client and it won't wrongly apply that everywhere, but you can push a fix global when it's a universal fact. On autonomy: out of the box Cleo drafts and suggests, doesn't act alone. You explicitly grant what it can do solo (send, schedule, update), per workstream. Nothing happens behind your back until you say so.
Powabase
Cleo
@michael_t_chang Hey, try to book on trycleo.ai
Is the free Telegram tier enough for a 5-person team to test properly?
Cleo
@jk_jensen Free tier's enough to get a feel for it with your team, but for a proper 5-person test you'll want Pro. Use code FOUNDER50 and Pro's on us. No time pressure, kick the tires properly. Happy to help you get set up if you hit anything.
The "agents that act like employees" framing is what most AI products fail at because they conflate orchestration with prompting. From the demo it looks like Cleo actually maintains state between agent turns - not just stuffing context back into prompts. are you using LangGraph's checkpointing for cross-session state, or did you build your own?
Cleo
@louislecat The endgame is bigger than a PM tool.
We're building toward agents that operate as employees - not assistants. They sit in your meetings. Execute across every integration your team uses (50 native, 500+ through Composio). Run entire functions of the company under your judgment.
Cleo today is the operational layer. The architecture (memory + provenance + learned rules + integrations) generalizes - same primitives that draft a client follow-up today will run the entire client-success function tomorrow.
An AI workforce that operates under human judgment, with auditable memory and trust gates. Not "AI that helps you." AI that does the work.