Skip to main content
Unlock automated bug investigation from user-recorded repros. When a Jam bug recording is shared in Slack, Devin uses the Jam MCP to pull the session — including the repro steps, console logs, network requests, and user actions — then traces each signal back to the codebase and posts a root-cause summary in-thread.

Use this template

Open Jam Bug Report Investigation in Devin and create the automation with the default configuration. You can customize it before saving.

​
What this automation does

Jam recordings are gold for debugging — they’re a time-machine view of what the user did and what the app did. The Jam MCP makes that data programmatic: Devin can read the recorded console stack trace, see the failed network request, match timestamps to code paths, and give your team a fix-ready diagnosis without anyone re-reproducing the bug.

​
How it works

Trigger: Slack event — message
  • Event: slack:message
    • Conditions:
      • channel eq #bugs
What Devin does: Starts a session with full event context, executes the prompt below, and (optionally) notifies you on failure.

​
Prerequisites

  • Integrations:
  • MCP servers:
    • Jam MCP — connects Devin to Jam

​
Example prompt

The template ships with this prompt. You can edit it after clicking Use template, or leave it as-is.

​
Setting it up

  1. Open Automations → Templates in Devin.
  2. Click Jam Bug Report Investigation. The create page opens with this template pre-filled.
  3. Connect any required integrations and install MCP servers if you haven’t already.
  4. Replace any placeholder values in the trigger conditions (for example, swap your-org/your-repo for your actual repo).
  5. Review the prompt and adjust it for your team’s language, conventions, and guardrails.
  6. Click Create automation.
Most automation templates include suggested ACU and invocation limits to bound cost during early rollout. Keep them as-is until you’re confident in the automation’s behavior, then raise them to fit your workload.

​
When to use this template

  • Product teams running Jam for bug capture
  • Support handoffs where “it doesn’t repro for me” is a blocker
  • Customer-reported bugs with intermittent symptoms
  • Reducing the time-to-diagnosis for user-facing issues

​
Customization ideas

  • Scope to specific Slack channels or user groups
  • Combine with Sentry MCP for automatic Sentry cross-reference
  • Route different bug categories to different playbooks
  • Auto-create a Linear ticket with the investigation summary

​
See also