DATA OPS
Agent-Driven dbt Freshness Incident Investigator
On a freshness alert, an agent investigates across BigQuery, Honeycomb, and dbt logs, writes a plain-English root-cause hypothesis, and posts a summarized incident brief to Slack.
How it runs
The automated pipeline, trigger to output.
- TriggerFreshness-breach webhook receivedHTTP webhook
- ActionPull model build cadence and gap from BigQueryBigQuery
- ActionPull upstream latency, errors, deploys from HoneycombHoneycomb
- LogicAgent reasons over signals, ranks root-cause hypothesesOpenAI
- OutputPost structured incident brief to on-call SlackSlack
What it does
Runs an autonomous investigation when a model breaches freshness SLA. An agent pulls the model's recent build history from BigQuery, correlates the gap with Honeycomb upstream traces, reasons over the evidence, and writes a human-readable incident brief with a ranked root-cause hypothesis and a recommended next action — then posts it to Slack for the on-call engineer.
When to use it
Use this for ambiguous freshness incidents where the cause isn't a simple lookup — when you want a first-pass diagnosis written up before a human even starts, instead of a raw metrics dump.
How it works
- 1A freshness-breach webhook starts the agent with the affected model.
- 2The agent queries BigQuery for the model's build cadence and the size of the current gap.
- 3It queries Honeycomb for upstream service latency, errors, and recent deploys in the window.
- 4The agent reasons over the signals and drafts a ranked root-cause hypothesis with a recommended action.
- 5It posts the structured incident brief to the on-call Slack channel.
Set it up
What you configure once, before turning it on.
- 1Connect HTTP webhookTrigger any URL on agent actions.
- 2Connect BigQueryDatasets, queries, schemas.
- 3Connect HoneycombDistributed traces and queries.
- 4Connect OpenAIModels, embeddings, files.
- 5Connect SlackChannels, DMs, threads, mentions.
- 6Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 7Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 8Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Data Ops workflows
Snowflake column type-drift sentinel with Linear fix ticket
Snapshots the data types of every column in your tracked Snowflake schemas on a schedule, diffs against the last snapshot.
Daily BigQuery Scheduled-Query Cost Attribution to Owners
Each morning, totals the prior day's on-demand bytes-billed per scheduled query, maps each query to its owner from a label, and posts a per-owner cost leaderboard to Slack.
BigQuery dropped/renamed column sentinel with PagerDuty incident
Detects when a column is dropped or renamed in your governed BigQuery datasets and, because that breaks downstream queries hard, pages the on-call via PagerDuty and posts…
PR-time Snowflake schema contract check on dbt model changes
When a pull request changes a dbt model, it compares the model's declared output columns against the live Snowflake table it will replace and blocks the merge with a GitHub check…
Agent-triaged warehouse drift with impact analysis and runbook update
On a webhook from your warehouse audit log, an agent investigates the changed column, traces which downstream models and dashboards depend on it.
Cross-warehouse replication schema mismatch reconciler
Compares the column shape of mirrored tables between BigQuery and Snowflake and, when a replicated table has drifted out of sync between the two, opens an Asana task for the data…
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.