{ }
A 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.
Designed for
Small engineering teams that live in Slack and need one reliable front door for support, incidents, and internal platform requests
Operating goal
Resolve or route 80% of routine engineering requests without losing auditability or human approval.
5 steps from trigger to verified handoff, with success and failure paths.
1 MCP layer and 5 connected tools with explicit auth and risk levels.
3 guardrails, 3 evals, and 1 harnesses before production use.
Classifies the Slack request and decides the next workflow path.
Fast classification model
Collects evidence before the reasoning agent responds.
Tool-use model with strong retrieval discipline
Turns gathered evidence into a concrete response or action plan.
Deep reasoning model
Checks whether the proposed action is safe and allowed.
Reliable policy model
Loads the workflow goal, allowed actions, escalation policy, and output contract before the agent plans work.
A Slack-first engineering triage skill for incidents, platform requests, runbook lookups, and owner routing.
Centralizes high-risk action checks for writes, secrets, customer data, billing, deploys, and public communications.
Exposes Slack thread context, channel history, message drafts, and approval prompts.
Read the Slack thread and classify urgency, domain, and action type.
Pull runbooks, issues, repo references, recent deploys, and relevant telemetry.
Create a concise recommendation, owner, next action, and Slack response.
Check the proposed action against permissions, data sensitivity, and mutation risk.
Post the approved response or create a Linear follow-up with the evidence pack.
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 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.
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.
A launch workflow that coordinates release notes, docs, changelog updates, social copy, customer comms, and post-launch monitoring from one evidence-backed plan.