AI AGENTS
Shell-Gated Monorepo Batch Upgrade Agent
Walks each package in a monorepo, bumps shared dependencies one at a time, runs that package's tests in a sandboxed shell.
How it runs
The automated pipeline, trigger to output.
- TriggerScheduled workspace scan
- ActionEnumerate packages depending on target version
- ActionBump and test each package in sandboxed shellShell
- LogicKeep passing bumps, discard failures
- ActionStage surviving changes and open grouped GitLab MRGitLab
- OutputReturn MR with upgraded vs skipped package listGitLab
What it does
This agent handles the messy reality of monorepos. It iterates package by package, attempts a pinned bump in each, validates it in isolation, and assembles one consolidated GitLab MR that includes only the upgrades that survived their tests.
When to use it
Use it in a Turborepo or pnpm workspace where a shared dependency spans many packages and a single all-or-nothing bump is too risky. You get partial progress instead of a stalled upgrade.
How it works
- 1A schedule starts the workspace scan.
- 2The agent enumerates workspace packages that depend on the target version.
- 3For each package it applies the pinned bump and runs that package's test command in a sandboxed shell.
- 4A logic gate keeps passing bumps and discards failing ones, recording which packages were skipped and why.
- 5The agent stages the surviving changes onto one branch and opens a grouped GitLab MR.
- 6The MR body lists upgraded versus skipped packages as the final output.
Set it up
What you configure once, before turning it on.
- 1Connect ShellRun sandboxed commands inside the workspace.
- 2Connect GitLabRepos, MRs, pipelines, registry.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More AI Agents workflows
Custom Metrics Cardinality Spike Pager
A webhook from a Datadog monitor fires when custom-metric cardinality jumps; an agent pinpoints the offending metric and tag, estimates the added cost.
Sentry-to-Confluence Runbook Updater
When a Sentry issue is resolved, the agent finds the matching Confluence runbook page and proposes an inline update with the verified fix.
Stale Doc-PR Chaser for Runbook Gaps
On a daily schedule the agent finds runbook doc PRs that were opened from resolved incidents but never reviewed, summarizes what each one fixes.
Resolved Incident to Public Troubleshooting Doc
For customer-facing errors resolved in Sentry, the agent drafts a sanitized troubleshooting entry and opens a PR to your ReadMe documentation.
On-Call Runbook Gap Closer: Resolved Sentry Issues to Doc PRs
An agent reads each newly resolved Sentry issue, compares the actual fix against your existing runbook, and opens a GitHub PR adding the missing remediation steps.
Weekly On-Call Doc-Gap Digest
Each week the agent reviews every Sentry issue resolved in the last 7 days, ranks the ones whose runbook coverage is missing or thin.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.