The plan your AI agents work from.
Direction for your agents and projects, grounded in your customers and your goals. Give Claude Code, Cursor, Codex and Grok one shared plan, and see what shipped.
claude mcp add --transport http annsa https://app.annsa.ai/mcp> take the top priority from Annsa ⏺ annsa.work claim Add dark mode ⎿ Claimed. 4 customers asked. ⏺ Reading direction ⎿ Principle: keep the app calm and familiar ⏺ Writing the spec and Done when
Your agents are doing more. You're still carrying the plan between them.
Plan and track work Add a customer email, a Slack thread or your own idea. Annsa finds who else asked, ranks it against your business goals and puts it on the list.
Learn about planning and tracking workGive your AI agents context Write your goals and rules once. Your goals, rules and past decisions are there for every agent before it starts. Save an answer as a rule for future work.
Learn about giving agents contextThis quarter
- Drive trials
- Improve retention
How we decide
- Keep the app calm and familiar
- Focus on the biggest bottleneck first
⏺ Reading direction ⎿ Principle: keep the app calm and familiar ⏺ Default theme: waiting on you
Run multiple AI agents Connect Claude Code, Cursor or Codex. Each agent claims a job from the list and writes the spec. One agent holds each job, and a note keeps the next one informed. When a decision needs you, the agent brings the question and its recommendation. You decide; it carries on.
Learn about running multiple agentsTrack what's done and live Write what "done" means before the work starts. The agent proves each line with a test or a link. You see when the change reached your codebase and when it went live for customers.
Learn about tracking what's done- Dark mode follows the system settingVerified on staging
- Every screen passes contrast checksVerified by a test
- Charts stay readable in dark modeVerified on staging
Keep customers in the loop
What they asked for, what shipped, and who heard back.
Collect and prioritize customer feedback
Connect Slack, Intercom, calls and surveys. Requests land in one list, with who asked.
Insights and reporting
Open Home each morning. See what's stuck on you, and whether your agents' work matches your goals.
Release notes that close the feedback loop
When a change ships, Annsa drafts a note to each customer who asked. You send it.
Everything you'd expect
And it works with the agents and tools you already use.
Planning
Priorities and roadmapOne ranked list. Share it as a roadmap.Goals, themes and saved viewsRank work against what you're aiming for.Data exportYour data, yours to take any time.Agents
Specs and PRDsAgents write the spec. You decide what done means.DocsThe context every agent reads before it starts.Integrations and APIConnect the tools you use, or build on the API.Annsa is built with Annsa
priorities shipped or shared in Annsa’s own workspace, as of 2 Nov 2026.
The tipping point to leading a company of agents is when AI is across your product, marketing, sales, customer support and it’s not possible to steer it all. AI and your agents are only as good as the direction you give them.
I built Annsa to help me build Annsa. Now much of it runs on self-drive.
Cat Williams-Treloar, founder of Annsa
Learn the way founders run agents
- Follows the system settingVerified on staging
- Passes contrast checksVerified by a test
The source of direction for agent teams.
Begin with one agent and the work that matters next.