Helm

Human-in-the-loop build controller coordinating planning, implementation, review, and approvals across external AI tools.

Discuss
  • Fallback policy follow-on

    Follow-on from run-003 for fallback policy confirmation.

    Draft · Updated 3/15/2026

    Updated since your last view

    Continue
  • ITAD CRM email send routing review

    Should ITAD CRM email send routing stay on send_email_default until tenant-priority authority and malformed-recipient fallback policy are explicitly confirmed by a human decision?

    Approved For Next Step · Updated 3/15/2026

    Updated since your last view

    Continue
  • Add review + approval flow

    Normalize tool outputs and formalize human approvals with explicit gates.

    Review Complete · Updated 3/15/2026

    Updated since your last view

    Continue
  • Scaffold base control UI

    Ship a plain, functional control console with run and task visibility.

    Awaiting Human Decision · Updated 3/15/2026

    Updated since your last view

    Continue

Project profile

Command Center

Manual control profile for AI-mediated delivery where humans retain decision control and every transition is explicit.

Governing docs

Forbidden terms

  • None configured.

Review checklist

  • None configured.

Ambiguity handling rule

When facts conflict or are underspecified, record the conflict, mark ambiguity active, and request human clarification.

Stop conditions

  • None configured.