AI & RAG
Runbook Gap Detector from Unanswered On-Call Questions
When the answer bot can't ground a metric question in any existing Confluence runbook, it files a Linear ticket capturing the question, the Datadog evidence it found.
How it runs
The automated pipeline, trigger to output.
- TriggerEngineer asks the bot a metric question in SlackSlack
- ActionSearch Confluence for a runbook covering the metricConfluence
- LogicBranch: exit if a runbook exists, continue if the metric is undocumented
- ActionQuery Datadog for the metric's value and baseline as evidenceDatadog
- ActionDraft a runbook stub from the question and baseline data (OpenAI)OpenAI
- OutputFile a Linear ticket with the stub and evidence for documentation triageLinear
What it does
This workflow catches the moments when on-call knowledge is missing. When an engineer asks the bot about a metric and no Confluence runbook covers it, instead of guessing, the bot files a Linear ticket. The ticket includes the original question, the Datadog baseline it was able to compute on its own, and an OpenAI-drafted runbook stub the team can review and publish. Over time it turns every unanswered question into documented knowledge.
When to use it
Use it to close the long tail of undocumented metrics. It's ideal for teams whose runbooks lag behind their dashboards and who want every "we should write that down" moment captured automatically.
How it works
- 1A Slack question to the bot triggers the flow.
- 2Confluence is searched for a runbook covering the referenced metric.
- 3A logic branch checks whether a relevant runbook was found; if yes, the flow exits (the answer bot handles it).
- 4When no runbook exists, Datadog is queried for the metric's value and baseline as supporting evidence.
- 5OpenAI drafts a runbook stub with the question, the baseline data, and suggested healthy ranges.
- 6A Linear ticket is created with the stub and evidence, tagged for documentation triage.
Set it up
What you configure once, before turning it on.
- 1Connect SlackChannels, DMs, threads, mentions.
- 2Connect ConfluenceSpaces, pages, blueprints.
- 3Connect DatadogMetrics, traces, log search.
- 4Connect OpenAIModels, embeddings, files.
- 5Connect LinearIssues, projects, cycles, triage.
- 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 AI & RAG workflows
RFP and security questionnaire drafter grounded in Coda
Drafts answers to inbound RFP and security questionnaire questions by retrieving approved language from your Coda hub, then files the cited draft for review before a rep sends it.
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.
Grounded reply suggestions for inbound sales email
Reads inbound prospect emails, retrieves the matching answers from your Coda hub.
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.
On-Call Spec Answerer from Dropbox Engineering Corpus
Answers on-call questions posted in a Slack channel by retrieving the most relevant Dropbox engineering specs and replying with a grounded, source-cited answer in the thread.
Agentic Deep-Dive API Researcher for Hard Spec Questions
An agent fielded via webhook that answers multi-part API questions by iteratively searching OpenAPI specs, changelogs, and Confluence runbooks.
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.