{ }
A data-quality workflow that watches analytics schema changes, validates event health, explains metric drift, and opens owner-ready fixes when instrumentation breaks.
Designed for
Product and growth teams that rely on analytics but do not want broken events silently corrupting decisions
Operating goal
Keep analytics events trustworthy by catching schema drift, missing properties, and metric anomalies before teams make decisions from bad data.
3 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.
Detects event schema changes and instrumentation drift.
Structured analysis model
Explains how data issues affect product metrics.
Reasoning model
Prepares owner-ready tickets or PR notes.
Code-aware model
Loads the workflow goal, allowed actions, escalation policy, and output contract before the agent plans work.
A workflow skill that captures the operating contract, tool boundaries, and escalation rules for DataSmith — Analytics QA Agent.
Centralizes high-risk action checks for writes, secrets, customer data, billing, deploys, and public communications.
Exposes task resources, prompt templates, connector tools, and audit records behind a permission-aware boundary.
Compare schema, freshness, and event samples against expectations.
Measure affected dashboards, metrics, and confidence.
Create GitHub issue or Slack handoff with code pointers and test suggestions.
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 meta-agent workflow that generates red-team cases, runs regression suites, scores agent behavior, and blocks production rollout when a workflow violates its safety contract.
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 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.