Ayven
Carries and drives your team's agenda
117 followers
Carries and drives your team's agenda
117 followers
Ayven drives your agenda. It means observing, cutting the work into pieces your team can take one at a time, putting an owner and a date on each, and filing them in Jira or YouTrack. Then it runs, tracks and talks about the work for weeks: asking whoever knows, waiting, chasing silence, moving work when someone is away. Your team answers in Slack and the board moves. Planning stops being the barrier and you ship your agenda like crazy.
Howard here, founder of Alknoma.
We didn't start with a product. We started with an ANNOYANCE. Agents were impressive while you were talking to them, and then, as soon as you stopped typing, they effectively disappeared.
You'd put one in Slack and end up with another bot sitting in a channel waiting for someone to tell it what to do.
You don't prompt your teammates.
So the real problem was never, "How do we make the model smarter?" It was: how do you give a language model a spine? Something that lets it chain call after call, across days and months, reaching out to different people, all without a human babysitting it.
Sounds impossible if you know from experience just how complex chaining LLM calls can be. Three things turned out to matter, and we learned each one the painful way.
1. What a piece of work actually is.
Small enough that it can be validated, iterated, executed and closed 99.9% of the time.
Too big and the agent starts hallucinating. Too small and it loses all semantic meaning.
2. Resolving time should be first-class.
A lot of work in a team is essentially waiting.
Waiting isn't failure. It's the norm. And that happens to be one of the things LLM agents are worst at. Ayven reasons about when it should wake up next, EVERY SINGLE TIME, across thousands of runs a week.
It is about recognising a deadline, annual leave, or when a teammate has gone quiet. The async gap is hard to nail down. Ayven does that.
3. What is the base unit of a fact.
In a team, things change constantly. Someone changes their mind, a deadline moves, a customer replies, a meeting gets cancelled. An agent would treat information that was true two days ago as gospel. Change is the critical signal, and that was difficult to implement when teamwork is so unpredictable. Ayven makes sure the right things change with it.
The magic moment that wowed us, and made us decide to launch Ayven: we gave Ayven the agenda for September. Nothing else. The next thing we knew, the board was full, and accurate to our plans. It put together the pieces of what execution would look like.
Later, I asked: "What's stopping us from launching on Product Hunt?" Ayven then told me about every dependencies that I did not previously know. Nobody wrote that answer. It was just the work being captured in its truest, current state.
There is a lot more to Ayven that we haven't covered here.
Talk to us if you want this deployed in your own environment. Tell us what you want it connected to.
Ask me anything :)
@howard_chen10 "The magic moment that wowed us, and made us decide to launch Ayven": proving your tool works by actually putting it to work for you is always a best-case scenario!
This sounds like an interesting one.
"resolving time should be first-class" is the sharpest line in that post. waiting being the norm rather than a failure state is exactly the thing most task tools get wrong, they treat an open ticket as something going wrong instead of something just not due yet. the rerouting-when-someone's-away answer below is the part I'd want more detail on though - does the reassigned person get a say before the work lands on them, or does Ayven just move it and tell them after? autonomous reassignment without a check-in is the kind of thing that works great until it hands someone a deadline they didn't know was coming.
@galdayan That is a great question. The way we go about it is to make Ayven dynamically react to an incoming deadline, and provide the "best result I can ship" instead of it being hard blocked by people and fail the deadline.
We also put a lot of effort going into the message delivery system, to make sure that users are aware about the situation.
Together with mcp, people can quickly go through the to-dos and all the requests and respond to unrealistic deadlines. Ayven will actually adjust the case accordingly!
@howard_chen10 the "best result I can ship" part answers the deadline side well, but I'm still stuck on the reassignment side specifically. when Ayven moves a task to someone else on the team, does that person get a heads up before it lands on their board, or do they just find it there next time they check? you mention the message delivery system is built for exactly this kind of situational awareness, just want to know if the notice arrives before the task does or after.
@galdayan
If the question is if Ayven would just go ahead and reassign any delegated task without notice. The answer is no, never. All actions done by Ayven can be gated. So would the person get a heads up? Yes, always. The assignment state would not change unless one clicked "approved"
Unless users decide to allow that action class to be enabled with no human-in-the-loop gate blocking it.
Another relatively new feature Ayven now has is to provision a slot within the reasonable timeframe between now and the future deadline on the user's calendar, so user gain visibility on the task and the best path to resolve all collaborative requests almost immediately AFTER the reassignment happened.
Thanks for the deep question! As I said, there are a lot of things that Ayven can do that we have yet covered. This kind of question give us the excellent chance to describe a lot of the product building decision we went through!