ENGINEERING
BigQuery regression to Linear ticket with AI root-cause hypothesis
Detects BigQuery query regressions on a schedule, asks an LLM to read the query plan and propose a likely root cause and fix.
How it runs
The automated pipeline, trigger to output.
- TriggerScheduled regression hunt
- ActionCompare BigQuery jobs to baselineBigQuery
- LogicFilter to material regressions
- ActionLLM analyzes plan, returns root-cause hypothesisOpenAI
- OutputCreate Linear issue with hypothesis and cost deltaLinear
What it does
This goes a step beyond detection: when a query regresses, it sends the plan and stats to an LLM that names the likely culprit (missing partition filter, broadcast join blowup, spilled shuffle) and drafts a suggested fix. The result lands in Linear as a ready-to-pick-up ticket, so triage is mostly done before a human opens it.
When to use it
Ideal for analytics-engineering teams who live in Linear and want regressions to arrive with a starting hypothesis instead of just a number. Useful when the people fixing queries aren't always the people who wrote them.
How it works
- 1A schedule triggers the hunt at a set hour.
- 2BigQuery job history is queried and compared to a baseline to find regressed queries.
- 3A logic step filters to material regressions worth a ticket.
- 4The query text, execution plan, and cost delta are passed to an LLM that returns a root-cause hypothesis and suggested fix.
- 5A Linear issue is created with the hypothesis, plan, delta, and a priority derived from the cost increase.
Set it up
What you configure once, before turning it on.
- 1Connect BigQueryDatasets, queries, schemas.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect LinearIssues, projects, cycles, triage.
- 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 Engineering workflows
Gate breaking API PRs behind downstream consumer acknowledgement
When a PR introduces a breaking contract change, comments the impact summary back on the PR, applies a blocking label.
Publish a versioned API changelog to Confluence on each release tag
On a new semver release tag, gathers the contract changes since the last release and writes a clean.
Agent reviews model-license fit and suggests compliant swaps on the PR
When a PR adds a Hugging Face model, an agent reads the model card and license, judges fit against your commercial-use policy.
Upgrade Impact Router to Module Code Owners
Maps a dependency-bump PR's affected modules to their CODEOWNERS, then DMs each owner on Slack with only the changelog slice that touches code they own.
Re-Voice IVR Prompts on Phone-Tree Config Merge
When a phone-tree config change merges in GitHub, regenerates the ElevenLabs audio for any prompt whose script changed in the diff and opens a follow-up PR adding the new audio…
Upstream Release to Notion Upgrade Brief
When a watched package publishes a new release, fetches the release notes, maps them to the internal modules that depend on it.
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.