{ }
A Devin-style engineering workflow that turns a scoped ticket into a branch, implementation plan, code changes, test run, and pull request draft with review evidence.
Designed for
AI product teams that want a coding agent with visible scope, tests, and review gates before a PR reaches humans
Operating goal
Convert well-scoped issues into reviewable pull requests while preserving ownership, tests, and rollback context.
4 steps from trigger to verified handoff, with success and failure paths.
1 MCP layer and 4 connected tools with explicit auth and risk levels.
3 guardrails, 3 evals, and 1 harnesses before production use.
Decides whether a ticket is small and safe enough for autonomous implementation.
Reasoning model
Plans and applies the implementation on a dedicated branch.
Code-specialist model
Runs checks and turns failures into fix attempts or handoff notes.
Code reasoning model
Loads the workflow goal, allowed actions, escalation policy, and output contract before the agent plans work.
A coding skill for turning a small ticket into a branch, patch, tests, and PR notes without scope creep.
Centralizes high-risk action checks for writes, secrets, customer data, billing, deploys, and public communications.
Exposes repository roots, file reads, diff summaries, test commands, and PR draft operations.
Validate ticket clarity, ownership, and blast radius.
Identify files, tests, and rollback notes before editing.
Make minimal code changes on a dedicated branch.
Run lint, typecheck, and targeted tests.
Open it in Codelit, refine it with the agent chat, then generate the architecture or product board from the same workflow spec.
Open in Agent WorkflowA Slack-native engineering agent that receives operational requests, gathers context from tickets and repos, routes work to specialist agents, and drafts auditable responses before anything risky happens.
A code review workflow that watches pull requests, assigns specialist reviewers, checks implementation risk, and posts concise review notes with links to evidence.
A security workflow that watches alerts, gathers evidence from code and runtime systems, ranks blast radius, and prepares a human-approved remediation plan before any production action.