The proactive agent stack.
Alknoma builds and secures proactive AI agents, online, for teams anywhere. Ayven is the agent we built: you give it the outcome, and it plans the work, hands it out and sees it through. Our services build and secure one for your team. Minutehand, free, tests the one you built.
The stack
A product, a service and a free tool
Use the agent we built, have us build and secure one for your team, or test the one you are building yourself.
For business owners
The built product
Coordinates your team in Slack and Microsoft Teams. Give it the outcome: it plans the steps, asks each person for the part only they hold, files what it cannot do as a ticket for the right owner, and watches every part until it is done.
For teams
Agent services
We build and secure your agents
We build proactive agents for your team, inside the tools it already uses, online, wherever you are. Securing one means validating it: checking that it does not hallucinate across a high volume of agent turns before it reaches your people.
Ayven codifies a team’s chatter. It reads the conversations in Slack and Microsoft Teams, keeps structured records of who asked what, who owes an answer and what was decided, and coordinates the team to the outcome you give it: it plans the steps, hands each part to the right person and watches it through to done. [How Ayven works, in full](/blogs/meet-ayven-ai-automation-busy-work-outcomes).
- Who asked what
- Who owes an answer
- What was decided
- Every part handed out and seen through to done
Free tool · for engineers
Run your agent through a week in seconds
Minutehand runs the proactive agent you built through simulated days of work in seconds, against fake Slack, Teams, Asana, Jira, YouTrack, Notion, GitHub, Google Drive and others, with people who answer late or not at all, and reports every message it got wrong.
Too early, too late
A follow-up sent before anyone could have answered, or after the moment it was due.
Again, with nothing new
The same message sent again when nothing had changed in between.
A move the service refuses
An action the real service would not have allowed.
A fact the agent made up
With --judge, a reviewer model flags it for you to review.
One import in your agent’s code, inert in production.
pip install minutehandFree to use and source-available under FSL-1.1-ALv2: each release becomes Apache 2.0 two years after it ships.
Insights
From our blog
When should an AI agent interrupt a human?
A proactive agent should interrupt a person for two reasons only: a decision it may not make, or news the person does not have. Here is how to tell, and how to test the timing before go-live.
How do you know an AI agent won't hallucinate before it goes live?
Buyers now treat hallucination as a security question. Here is how Alknoma tests an agent for it before it reaches a real person.
What are reactive, proactive and durable agents?
Reactive, proactive and durable are not three levels of one thing. They answer different questions about an AI agent: what starts it, and how long it lives.
Let's talk
Want Ayven for your team, or a proactive agent built and secured for it? Book a Google Meet and let’s talk it through, online, wherever you are.