# Guard releases and investigate regressions with Browserbase: n8n workflow

> Started by another system calling it, and works across Email, GitHub, Slack and Supabase. It hands the judgement calls to OpenAI.

Source: https://millionrounds.com/workflow/guard-releases-and-investigate-regressions-with-browserbase (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Chat assistants](https://millionrounds.com/workflows?category=Chat+assistants#library)

# 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.

Large Calls a model: OpenAI

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fguard-releases-and-investigate-regressions-with-browserbase)

**34 steps** Large: read it before trusting it with anything live

**6** Branches: places the flow splits

**1** Loop or waits

**4** Services it connects to

## The flow

Starts it 2 Model 4 Logic 18 Service 10

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

- 1 **01, Deployment Webhook** Webhook *Starts it*
- 2 **01, Manual Test Run** Manual trigger *Starts it*
- 3 **AI Model (swap for Anthropic/Gemini/Groq)** Lm Chat Open Ai *Model*
- 4 **07, Structured Diagnosis Parser** Output Parser Structured *Model*
- 5 **07, MCP Tools (optional advanced)** Mcp Client Tool *Model*
- 6 **02, Load Configuration** Set *Logic*
- 7 **07, Investigate Regression (AI Agent)** Agent *Model*
- 8 **02, Normalize Deployment Payload** Set *Logic*
- 9 **09, Fingerprint + Dedup Check** Code *Logic*
- 10 **08, AI Fallback Report** Set *Logic*
- 11 **03, Generate Test Plan** Split In Batches *Logic*
- 12 **09, Check Existing GitHub Issue** Http Request *Service*
- 13 **05, Aggregate Results** Aggregate *Logic*
- 14 **03, Demo or Live?** If *Logic*
- 15 **09, New Issue Needed?** If *Logic*
- 16 **06, Detect Failures** If *Logic*
- 17 **04, Demo Smoke Test (synthetic)** Code *Logic*
- 18 **04, Browserbase: Create Session** Http Request *Service*
- 19 **10, Build GitHub Issue Body** Code *Logic*
- 20 **10, Capture Issue URL** Set *Logic*
- 21 **06, Classify Failures** Code *Logic*
- 22 **14, Success Notify On?** If *Logic*
- 23 **05, Merge Test Results** Merge *Logic*
- 24 **04, Browserbase: Stagehand Run Test** Http Request *Service*
- 25 **08, QA Infra Failure (no false regression)** Slack *Service*
- 26 **10, Create GitHub Issue** Github *Service*
- 27 **11, Slack Enabled?** If *Logic*
- 28 **13, Email Enabled?** If *Logic*
- 29 **07, Supabase: Recent Errors (optional)** Supabase *Service*
- 30 **14, Success Notification** Slack *Service*
- 31 **04, Browserbase: Fetch Logs** Http Request *Service*
- 32 **11, Notify Slack** Slack *Service*
- 33 **13, Send Email Report** Email Send *Service*
- 34 **05, Normalize Live Result** Code *Logic*

## 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.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fguard-releases-and-investigate-regressions-with-browserbase)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Email](https://millionrounds.com/workflows?service=Email#library)[GitHub](https://millionrounds.com/workflows?service=GitHub#library)[Slack](https://millionrounds.com/workflows?service=Slack#library)[Supabase](https://millionrounds.com/workflows?service=Supabase#library)

## Workflows like it

Also chat assistants, with the same services where possible, closest in size first.

- [**Assist hospital doctors with Telegram and OpenAI** 34 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/assist-hospital-doctors-with-telegram-and-openai)
- [**Manage rent, maintenance and tenant messages with OpenAI** 34 steps · calls a model · Google Sheets, Slack](https://millionrounds.com/workflow/manage-rent-maintenance-and-tenant-messages-with-openai)
- [**Pyragogy AI Village - Orchestration Master with OpenAI** 35 steps · calls a model · Email, GitHub](https://millionrounds.com/workflow/pyragogy-ai-village-orchestrazione-master-with-openai)
- [**Pyragogy AI-driven handbook generator with OpenAI and GitHub** 35 steps · calls a model · Email, GitHub](https://millionrounds.com/workflow/pyragogy-ai-driven-handbook-generator-with-openai-and-github)
- [**Triage project and UAT feedback with OpenAI and Jira** 32 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/triage-project-and-uat-feedback-with-openai-and-jira)
- [**Company knowledge base agent (RAG) with OpenAI** 31 steps · calls a model · Google Drive, Supabase](https://millionrounds.com/workflow/company-knowledge-base-agent-rag-with-openai)