Automation library · Chat assistants

Guard releases and investigate regressions with Browserbase

Started by another system calling it, and works across Email, GitHub, Slack and Supabase. It hands the judgement calls to OpenAI. 34 steps, 6 branches, 1 loop or waits: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAI

Download free
34 stepsLarge: read it before trusting it with anything live
6Branches: places the flow splits
1Loop or waits
4Services it connects to

The flow

Starts it 2Model 4Logic 18Service 10

The steps in the order they run, from what starts it.

  1. 101, Deployment WebhookWebhookStarts it
  2. 201, Manual Test RunManual triggerStarts it
  3. 3AI Model (swap for Anthropic/Gemini/Groq)Lm Chat Open AiModel
  4. 407, Structured Diagnosis ParserOutput Parser StructuredModel
  5. 507, MCP Tools (optional advanced)Mcp Client ToolModel
  6. 602, Load ConfigurationSetLogic
  7. 707, Investigate Regression (AI Agent)AgentModel
  8. 802, Normalize Deployment PayloadSetLogic
  9. 909, Fingerprint + Dedup CheckCodeLogic
  10. 1008, AI Fallback ReportSetLogic
  11. 1103, Generate Test PlanSplit In BatchesLogic
  12. 1209, Check Existing GitHub IssueHttp RequestService
  13. 1305, Aggregate ResultsAggregateLogic
  14. 1403, Demo or Live?IfLogic
  15. 1509, New Issue Needed?IfLogic
  16. 1606, Detect FailuresIfLogic
  17. 1704, Demo Smoke Test (synthetic)CodeLogic
  18. 1804, Browserbase: Create SessionHttp RequestService
  19. 1910, Build GitHub Issue BodyCodeLogic
  20. 2010, Capture Issue URLSetLogic
  21. 2106, Classify FailuresCodeLogic
  22. 2214, Success Notify On?IfLogic
  23. 2305, Merge Test ResultsMergeLogic
  24. 2404, Browserbase: Stagehand Run TestHttp RequestService
  25. 2508, QA Infra Failure (no false regression)SlackService
  26. 2610, Create GitHub IssueGithubService
  27. 2711, Slack Enabled?IfLogic
  28. 2813, Email Enabled?IfLogic
  29. 2907, Supabase: Recent Errors (optional)SupabaseService
  30. 3014, Success NotificationSlackService
  31. 3104, Browserbase: Fetch LogsHttp RequestService
  32. 3211, Notify SlackSlackService
  33. 3313, Send Email ReportEmail SendService
  34. 3405, Normalize Live ResultCodeLogic

How it's built

Starts on
Another system calling it
Steps
34, with 6 branches, 1 loop or waits
Size
Large: read it before trusting it with anything live
Connects to
Email, GitHub, Slack, Supabase
Model
OpenAI

Questions

What does it need to run?

An n8n account, plus your own Email, GitHub, Slack and Supabase accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling it.

Does it use AI?

Yes. It calls OpenAI. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 34 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

Before you run it

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 34 steps before you point it at anything that matters.