Bug Triage Assistant
Convert scattered bug notes, Slack messages, or user complaints into structured engineering tasks with reproduction steps, severity, and root cause hypothesis.
Extract decisions, action items, and open questions from raw meeting notes — the three things that need to survive the meeting.
Raw meeting notes are chronological. What needs to persist after a meeting is a completely different structure: what was decided, who owns what by when, and what's still unresolved. This workflow takes notes in any format — transcript fragments, bullet points, a stream-of-consciousness dump — and produces the three outputs that actually matter for follow-through.
Paste the raw notes
Copy your notes as-is — bullet points, transcript fragments, or freeform text. Include attendees and date if you have them.
Review decisions and owners
Decisions without clear owners and action items without due dates are the two most common gaps. Fix them before sending.
Verify open questions
The open questions list should name who needs to answer each one. An unassigned question is unlikely to get resolved.
Distribute
Send the structured output to all attendees and relevant stakeholders. The context section gives absent stakeholders what they need.
It's not treated as an action item: the rules say only include items with a clear owner, so unowned tasks are flagged instead. Action Items follow the format [Task] — Owner: [Name or role] — Due: [Date or TBD], and a missing date is flagged "Due: TBD — needs date". The system-prompt-generator builds this; you fill the real owners and dates before distributing.
Outcomes only: a rule states do not include the discussion that led to decisions, record outcomes only, which is why the notFor calls it wrong for verbatim transcripts or compliance recordings. It extracts Decisions Made, Action Items, and Open Questions, plus a Context for Absent Stakeholders recap. The system-prompt-generator produces the system prompt; you paste raw notes into your assistant and verify the extracted items.
Convert scattered bug notes, Slack messages, or user complaints into structured engineering tasks with reproduction steps, severity, and root cause hypothesis.
Turn AI into a structured pull request reviewer that catches risky changes, flags maintainability issues, and suggests missing test coverage.
Configure AI to answer support questions within your actual policy boundaries — not generic best-guess answers.
A complete 'act as a product manager' role prompt — the perspective, responsibilities, and decision criteria a real PM brings, not just the job title.
A reusable AI agent task template with variables for objective, context, available tools, constraints, success criteria, failure handling, and output format.
Formats fuzzy agent instructions into a structured prompt with objective, available tools, constraints, success criteria, and failure handling.
Build structured system prompts from role, tone, constraints, and model target.