AI & RAG
Policy conflict and contradiction detector
On a schedule, scans your Confluence and Drive policy library for statements that contradict each other (e.g. two different PTO rules) and posts a triage report to Slack so doc…
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly schedule fires
- ActionCluster related policy chunks from SupabaseSupabase
- ActionJudge contradictions across passages (OpenAI)OpenAI
- LogicKeep only confirmed, high-severity conflicts
- OutputPost triage report with source links to SlackSlack
What it does
Finds where your own policies disagree. It clusters semantically related passages across Confluence and Drive, asks the model to judge whether any pair genuinely conflicts, and reports the contradictions with both source links so an owner can fix the canonical version.
When to use it
Use it when policy lives in many places and has drifted over time, before an audit, or after a big reorg. It is the cleanup companion to a Q&A bot: a bot can only be trustworthy if the underlying docs do not contradict each other.
How it works
- 1A scheduled trigger starts the scan (e.g. weekly).
- 2The workflow pulls policy chunks from the Supabase vector store and clusters near-duplicate topics.
- 3OpenAI evaluates each candidate cluster and labels real contradictions, ignoring harmless restatements.
- 4A filter keeps only confirmed conflicts above a severity bar.
- 5A formatted triage report with both conflicting passages and links is posted to a Slack channel for doc owners.
Set it up
What you configure once, before turning it on.
- 1Connect SupabaseTables, auth, storage, edge functions.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect ConfluenceSpaces, pages, blueprints.
- 4Connect Google DriveDocs, sheets, slides, 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 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.