Hushwire

compliance

Keeping client code confidential with AI agents

Practical steps for agencies whose clients own the code they write.

Agencies are often bound by clauses that the client owns the work product and that it must not be shared. Big-lab AI subscriptions often keep prompts for abuse monitoring, which many clients consider sharing.

A private backend that keeps nothing, plus a per-client key, lets you show a client exactly what is processed for their project and that nothing is stored.

Checklist

  • □One API key per client project, named after the client.
  • □Spend caps per key so one project cannot use the whole budget.
  • □Show the client the “what we store” page for their key.
  • □Revoke the key when the engagement ends.

This is practical guidance, not legal advice. Check your contracts with the client or a lawyer.

What Hushwire gives you

A backend for coding agents that stores no prompts, code or completions, never routes to OpenAI or Anthropic, and gives you a downloadable security summary to attach to the client’s questionnaire.

Try it before you configure anything

The playground runs the same open coding models. No sign-up, 20 messages a day, and nothing you type is stored.