AI AGENTS
Replicate Successor Auto-Bump Merge Request with Eval Gate
When a pinned Replicate version is deprecated and its successor passes the golden-prompt eval clean, the agent opens a GitLab merge request that bumps the pinned hash…
How it runs
The automated pipeline, trigger to output.
- TriggerSchedule detects a deprecated pinned version
- ActionDry-run successor version on golden promptsReplicate
- LogicGate on whether all prompts pass drift tolerance
- ActionEdit pinned hash and open GitLab merge request on passGitLab
- ActionOpen GitLab review issue with failing diffs on failGitLab
- OutputNotify Slack with link and eval verdictSlack
What it does
This agent closes the loop from detection to code change. On a deprecation, it dry-runs the successor version against your golden prompts; if every prompt passes the drift gate, it edits the config file to bump the pinned version hash and opens a ready-to-merge GitLab merge request. If any prompt regresses, it instead opens a human-review ticket rather than shipping a risky bump.
When to use it
Use it when you trust a clean eval to auto-prepare the code change, so trivial successor bumps merge in minutes while only genuine regressions reach a human.
How it works
- 1A schedule detects a deprecated pinned version.
- 2The agent dry-runs the successor against the golden prompt set.
- 3A logic gate checks whether all prompts pass within drift tolerance.
- 4On pass, the agent edits the pinned hash in the repo file and opens a GitLab merge request.
- 5On fail, it opens a GitLab review issue with the failing diffs instead.
- 6It notifies Slack with the MR or issue link and the eval verdict.
Set it up
What you configure once, before turning it on.
- 1Connect ReplicateImage, video, and model inference.
- 2Connect GitLabRepos, MRs, pipelines, registry.
- 3Connect SlackChannels, DMs, threads, mentions.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, 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.