FAQ
Frequently asked questions
The short version of how mowa works, who it's for, and how to reach someone when you need help.
What is mowa?
mowa is the AI governance layer for teams shipping with AI: the system of record for your AI’s behavior. Every change to a prompt is reviewed, eval-tested before it ships, and written to a tamper-evident audit log, so you always know who changed your AI’s behavior, when, and why.
Do I need to move my prompts into mowa first?
No. The point is to meet prompts where they already live. Connect a GitHub repo and we scan automatically, or add prompts manually through the dashboard.
Who can edit prompts?
Product, support, operations, and engineers can all collaborate. Roles include owner, editor, PM, and viewer, with full audit attribution on every change.
How does versioning work?
Every change creates a new version. You see diffs against any prior version, run side-by-side eval comparisons, and roll back with one click if a regression slips through.
How does MCP fit in?
Every workspace ships with an MCP server. Connect it to Cursor, Claude Desktop, or any MCP-compatible client. Your AI agent can read prompts and propose changes through the same review flow as your team.
Is the audit log exportable?
Yes. Every edit, test run, and promotion is captured with author, timestamp, reason, and diff. The log is queryable and exportable for compliance.
How do I get help?
Email hello@mowa.dev or use the contact form on the site.
Still need help?
Book a 30-minute call and we'll walk through it with you.