AI & RAG
Slack /why-spiked Command Backed by Runbook RAG
Lets engineers type a Slack slash command naming a metric or dashboard and get an instant retrieval-augmented answer about likely causes and fixes, cited from indexed runbooks.
How it runs
The automated pipeline, trigger to output.
- TriggerEngineer runs /why-spiked slash command in SlackSlack
- ActionQuery Datadog for metric values and anomaliesDatadog
- ActionVector-search runbook chunks for relevant stepsPostgres
- ActionCompose cited diagnosis from retrieved textOpenAI
- OutputReply in Slack thread with answer and citationsSlack
What it does
Gives anyone in Slack a self-serve way to ask why a metric is misbehaving. An engineer runs the command with a metric name or dashboard link; the flow gathers current Datadog readings, retrieves matching runbook guidance, and replies in-thread with a cited diagnosis — no alert required.
When to use it
Use it for the constant stream of 'is this normal?' questions in team channels, or when someone is investigating a slow dashboard outside of a formal incident. It puts the runbook knowledge base one command away instead of behind a wiki search.
How it works
- 1An engineer invokes the Slack slash command with a metric, monitor, or dashboard reference.
- 2The flow queries Datadog for that metric's recent values, anomalies, and related tags.
- 3It runs a vector search over runbook chunks in Postgres to find relevant troubleshooting steps.
- 4An LLM composes an answer that explains probable causes and quotes only the retrieved runbook text.
- 5The reply is posted back into the same Slack thread with citation links and the live metric snapshot.
Set it up
What you configure once, before turning it on.
- 1Connect SlackChannels, DMs, threads, mentions.
- 2Connect DatadogMetrics, traces, log search.
- 3Connect PostgresAny Postgres URL — query, write, migrate.
- 4Connect OpenAIModels, embeddings, files.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More AI & RAG workflows
Coda-grounded sales answer bot with citations in Slack
Reps ask product, pricing, or competitive questions in Slack and get an answer drawn only from your Coda knowledge hub, with links to the exact docs and rows it pulled from.
Weekly knowledge-gap digest from unanswered rep questions
Each week, scans rep questions the answer bot couldn't ground in Coda, clusters the recurring gaps.
Pre-meeting prep brief grounded in Coda and CRM
Before each booked sales meeting, builds a one-page prep brief by combining the account's HubSpot context with grounded talking points and objection responses pulled from your…
Publish a Grounded API FAQ Page to Confluence Weekly
Each week, clusters the top unanswered or repeated API questions, generates spec-grounded answers with citations.
Detect Breaking API Changes from Spec Diffs and Alert Owners
Compares the new OpenAPI spec against the previous version on each GitLab merge, uses retrieval over the changelog to classify whether changes are breaking.
Re-Index API Specs on GitLab Merge to Keep the Answer Bot Fresh
Watches GitLab merges to your API repo, detects changed OpenAPI specs and changelog files, re-chunks and re-embeds only what changed.
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.