Guided onboarding
We set kanman up with your team.
Most teams start on their own with the 14-day trial. If you would rather have us there, we connect your tracker and repo with you, check that your CI judges kanman's changes like your own and tune the rules until kanman fits how your team works.
Price on request, with any paid plan
The onboarding
What happens, step by step
-
Step 1
Setup
We connect your tracker and repo together, pick the Trial preset and watch kanman's first pull request go through your CI.
-
Step 2
First stories
kanman takes real stories from your backlog. Every pull request says what the reviewer proved. You review as usual.
-
Step 3
Your rules
We tune the policy with you. What kanman may touch, the budgets, which calls come to you. Most teams move to Balanced here.
-
Step 4
Results
A written summary of what shipped, what needed rework, what it cost and what we would change. You keep all of it.
What your team brings
- A repo on GitHub or GitLab, with GitHub Issues, Jira or GitLab as the tracker
- One tech lead who reviews kanman's pull requests, about two hours a week
- A CI pipeline that runs your tests. If it is thin, we help.
- Model access, either your own keys or usage through kanman at provider cost plus 15%
What we bring
- Setup in a joint session with your team
- A look at your CI together, so it judges kanman's changes like your own
- Regular reviews of runs, decisions and cost with you
- The written summary at the end
What you get on every pull request
What the reviewer proved
The bug or acceptance check before and after the change, the tests it ran and its findings, each on its line. In the pull request's description and in the story's log.
The flow
What every story goes through
-
1. Tell kanman
Describe the work in the app, in Slack or in Microsoft Teams. kanman asks what is unclear and drafts stories with acceptance criteria and a way to demonstrate each one.
-
2. Rules
Your policy decides what kanman may touch, spend and merge. Big calls come to you with a recommendation.
-
3. Work
Claude Code or Codex does the coding in a sandbox. kanman picks the model by complexity, so trivial fixes stay cheap.
-
4. Proof
Your CI runs first. Then a reviewer that did not write the change reruns the bug or the acceptance check before and after, and runs the tests. No green CI and no approval, no merge.
-
5. Hear back
kanman tells you what changed and what the reviewer proved. Your code host's rules decide whether a person approves before the merge.
Ask about onboarding
Tell us about your team
We reply within two working days and suggest a 30-minute call. No slides, just your backlog and our questions. You get an offer for your setup. Onboarding runs on a short order form under our Terms of Service, with our data processing agreement signed before any code is touched.
Your mail app should open now.
Send the prefilled email and we reply within two working days. If nothing opened, write to [email protected].
FAQ
Questions about getting started
- What does it cost to run, and how do budgets work?
- Every plan is a flat price per AI team, never per seat, listed in the pricing section. Local is free, Starter and Team are billed monthly, Enterprise annually. From 5 Team teams in one workspace, every Team team costs less (volume pricing). Model usage comes on top, on your own keys or at provider cost plus 15%. You set budgets per run, per day and per month with hard stops. Incident work is never blocked by a budget. Read the docs (opens in a new tab)
- Is kanman only for engineering teams?
- It does its deepest work where code is involved: stories, reviews, pipelines and incidents. The same kanman also serves the teams around the code: it reviews ServiceNow incidents, goes on call from your alerting, reads your monitoring and wikis, builds team apps and runs routines. Every team has its own members, rights and budget, and one kanman knows which team owns what. Read the docs (opens in a new tab)
- Where is our code processed and stored? What do model providers see?
- kanman runs in the EU. Coding happens in sandboxes in Frankfurt, and every run gets a fresh sandbox that is thrown away afterwards. Model calls go to the provider you choose when you bring your own keys, or through kanman to Anthropic or OpenAI in the US. Either way, the provider sees only the prompts and code context a run needs. With the self-hosted runner on Enterprise, code execution stays in your network. Read the docs (opens in a new tab)
- What are team apps?
- Internal tools kanman builds and keeps for a team, such as a dashboard, a queue view or a page with a button that reruns a job. Ask for one in the chat, or ship one you built in Claude Code and kanman checks it before anyone opens it: keys in the code, calls to hosts nobody approved, accessibility gaps. Apps run only on your own runners, show data with each viewer's rights, and every change is a version you can roll back. Team apps are part of Enterprise. Read the docs (opens in a new tab)