# kanman > Tell kanman what you need, in the app, in Slack or in Microsoft Teams. It drafts the stories, ships them through Claude Code or Codex under your rules, proves every change against your acceptance criteria and tells you how it went. Hosted in the EU or on your own servers. Everyone on your team has an AI coding tool. Nobody has an AI teammate. Copilot and Claude Code licenses make each developer faster. They don't decide what gets built, what the agent may touch, or whether the result works. ## A walk through kanman [A walk through kanman](https://kanman.ai/video/kanman-demo-en.mp4): Describe the work, continue in the team's chat, approve the drafted stories, hand one to kanman, answer a decision in the conversation and watch the run collect its evidence. Recorded in the real app, at a calm pace. A requirement from finance for the Sandbox Team is typed into the general conversation. kanman offers to continue in the team's chat, the conversation moves there beside the team's board, and kanman drafts three stories with acceptance criteria, which are approved and written to the tracker. The first story is moved to Ready on the board and kanman starts planning. kanman asks to approve the plan, the plan is approved in the conversation, and the run passes every check on a clean checkout. The pull request is merged, the story moves to Done with its criteria, tests and cost, and the weekly report sums up the week. ## From a conversation to a reviewed pull request - 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. - Rules: Your policy decides what kanman may touch, spend and merge. Big calls come to you with a recommendation. - Work: Claude Code or Codex does the coding in a sandbox. kanman picks the model by complexity, so trivial fixes stay cheap. - Proof: Before anything reaches review, an acceptance spec runs against a fresh environment. No spec, no Ready. No green run, no review. - Hear back: kanman tells you the pull request is ready, with the evidence attached. Your people review and merge, or your policy does. ## It tells you what happened. It asks only when it needs you. No dashboard to check, no status to chase. kanman writes to you in the app, in Slack or in Microsoft Teams, in one voice and in a few sentences. - Updates when something happened: A run finished, a failure it handled, a convention it learned. Each update links to the run or the evidence pack. When nothing happened, it stays quiet. - Decisions where you read them: When your policy says a call needs you, kanman asks one question with its recommendation and the options. You answer right there, in the app or in your channel. - A weekly report you can forward: Stories merged, rework and time to review, with the reason behind each change. Ask a follow-up in the same conversation. ## Priced per AI team. Not per seat. - Local (free): The kanman board and the kanman MCP in your own Claude Code or Codex. Your machine does the work. - Starter (€99 per AI team per month): kanman works your stories under your rules and proves every change. - Team (€249 per AI team per month): kanman as a full teammate, in your channels and on call. - Enterprise (from €1,000 per month): For several teams and stricter requirements. Contracted for the number of teams you need. Every new team gets the Team plan for 14 days, without a card. When the trial ends, cloud runs pause until you pick a plan. Your board and the Local plan keep working. Want us to set kanman up with your team? Guided onboarding is available on request, with any paid plan, priced for your setup. Model usage runs on your own keys (Anthropic, OpenAI, Azure OpenAI or Amazon Bedrock), or is passed through at provider cost plus 15%. No per-seat pricing. Prices are net. No VAT is added, as kanman is a small business under section 19 UStG. ## Pages - [Guided onboarding](https://kanman.ai/en/onboarding/): We set kanman up with your engineering team, in your tracker and your repo, and stay with you for the first stories. Available on request with any paid plan. - [How it works](https://kanman.ai/en/how-it-works/): Follow one story from a conversation with kanman to a reviewed pull request with an evidence pack. Five stages, inside your tracker or on the kanman board, under your rules. - [Security and data](https://kanman.ai/en/security/): Where kanman runs, what it can touch, what model providers see and how long data is kept. Every claim links to the document behind it. - [Pricing](https://kanman.ai/en/pricing) - [Docs](https://docs.kanman.ai/en/) - [llms-full.txt](https://kanman.ai/en/llms-full.txt) ## Blog - [Agents Need a Policy, Not a Better Prompt](https://kanman.ai/en/posts/agents-need-a-policy/): "Please don't touch the billing module" in a system prompt is not a rule. It's a wish. kanman replaces wishes with a policy: authority levels, presets, budgets with hard stops, decisions that come with a recommendation, and an audit log you can export. - [Don't Trust an Agent That Says Done](https://kanman.ai/en/posts/dont-trust-an-agent-that-says-done/): Coding agents grade their own homework. kanman doesn't let them: an acceptance spec is written before the code, must fail before work starts, can't be edited by the agent, and has to pass on a clean checkout before anyone is asked to review. - [Issue to PR Is a Commodity. Here's What Isn't.](https://kanman.ai/en/posts/issue-to-pr-is-a-commodity/): GitHub, Linear, Jira and OpenAI all turn issues into pull requests now. The loop is free. What your team still doesn't have is the operating model around it: who writes the work, who sets the rules, and who proves the result. - [The Post-AI-Hype Era Starts Now](https://kanman.ai/en/posts/post-ai-hype-era/): Every industrial revolution has a hype cycle. We're in one now. But while everyone debates AI, some of us are ready to skip ahead and just build things together. - [An AI Teammate, Not Just an AI Assistant](https://kanman.ai/en/posts/virtual-teammates-not-assistants/): Assistants answer when you ask. A teammate owns work: it takes requirements, follows the team's rules, shows its evidence and is accountable for the result. Your team doesn't need more assistants. It needs one teammate it can trust. - [Why Your Manager's Favorite Tool Hates Your Focus](https://kanman.ai/en/posts/managers-favorite-tool-hates-focus/): B2B planning suites optimize for reporting, not doing. Here's why tools built for oversight sabotage the people doing the actual work. - [When Minimalism Is a Feature, Not a Missing Feature](https://kanman.ai/en/posts/minimalism-is-a-feature/): Every feature is a potential distraction. kanman's deliberate omissions - no second tracker, no calendar, no dashboards - aren't gaps in a roadmap. They're the point. - [Autonomy vs. Oversight: Choosing Tools That Side with the Doers](https://kanman.ai/en/posts/autonomy-vs-oversight/): Most B2B planning tools serve managers at the expense of makers. Here's how to evaluate tools through the lens of worker agency - and why it matters. - [How to Sell a 'Do Less' Tool to a 'Do More' Manager](https://kanman.ai/en/posts/selling-do-less-to-do-more-manager/): Your manager wants dashboards and velocity charts. You want focus. Here's how to bridge the gap and advocate for calm productivity tools in a metrics-obsessed workplace. - [Designing for the After-Hours Brain](https://kanman.ai/en/posts/designing-after-hours-brain/): At 11pm after a long day, you don't need a complex interface. You need a tool that stays usable when your brain is tired. Here's how low cognitive load makes software better. - [How to De-Weaponize OKRs](https://kanman.ai/en/posts/de-weaponize-okrs/): OKRs were meant to align teams. Instead, they often become performance weapons. Here's how to use goal frameworks without letting them suffocate your actual work. - [The Manager's Report vs. The Maker's Reality](https://kanman.ai/en/posts/managers-report-vs-makers-reality/): What managers see in dashboards rarely matches what workers experience. Here's why reporting abstractions fail makers - and what to do about it. - [Getting Desktop Notifications From Codex on Linux, Windows, and WSL](https://kanman.ai/en/posts/codex-desktop-notifications/): Wire Codex into native desktop notifications on Linux, Windows, and WSL with lightweight scripts. - [Breaking the Burnout Loop](https://kanman.ai/en/posts/breaking-the-burnout-loop/): The grind-evaluate-punish cycle of modern work tools creates burnout by design. Here's how to escape and build sustainable work habits instead. - [Hustle Culture's Hidden Costs](https://kanman.ai/en/posts/hustle-cultures-hidden-costs/): Context switching, rework, and lost focus are the real price of always-on work. Here's what hustle culture actually costs - and how calm tools help you reclaim it. - [The Weekly Reset: A Five-Minute Ritual](https://kanman.ai/en/posts/the-weekly-reset/): Replace Sunday night planning dread with a simple five-minute ritual. Open your projects, drag to reprioritize, close and move on. No frameworks required. - [Screw Plans, Ship Work: Why Perfect Roadmaps Stall Real Progress](https://kanman.ai/en/posts/screw-plans-ship-work/): Plans are guesses dressed in confidence. While you perfect your roadmap, someone else is shipping. Here's how to prioritize action over planning theater. - [The Myth of the Perfect Workflow](https://kanman.ai/en/posts/myth-of-perfect-workflow/): The search for the perfect productivity system is itself a form of procrastination. Your workflow doesn't need to be perfect - it needs to be used. - [When Metrics Gaslight Makers](https://kanman.ai/en/posts/when-metrics-gaslight-makers/): Velocity charts and burndown graphs can make you feel behind even when you're shipping. Here's how vanity metrics distort priorities - and how evidence instead of metrics lets outcomes speak for themselves.