AI & RAG
Quarantine low-trust answer-bank entries by age and usage signals
Scores every answer-bank entry on recency, how often it was edited by agents after retrieval, and citation health.
How it runs
The automated pipeline, trigger to output.
- TriggerSchedule: weekly
- ActionLoad entries with freshness + usage signalsPostgres
- LogicCompute composite trust score per entry
- ActionFlag below-threshold entries as quarantinedPostgres
- ActionSummarize lost coverage with LLMOpenAI
- OutputSend trust scorecard to SlackSlack
What it does
Manages the lifecycle of your RAG corpus so quality never silently erodes. Each entry gets a composite trust score from its age, how recently its source conversation occurred, whether agents frequently rewrote the suggested draft, and whether its citation passed the last freshness audit. Low-scoring entries are quarantined so retrieval only surfaces answers you still trust.
When to use it
When your answer bank has grown large and you need an automatic way to retire aging or low-quality entries instead of manual spring cleaning. Run weekly to keep retrieval precision high.
How it works
- 1A weekly schedule starts the decay scan.
- 2The workflow loads all entries plus their freshness flags and usage counters from Postgres.
- 3A logic step computes a trust score per entry from age, agent-edit rate, and last citation-audit result.
- 4Entries below the quarantine threshold are flagged inactive so vector search excludes them.
- 5An LLM summarizes which topics lost the most coverage from quarantining.
- 6The trust scorecard and a list of quarantined entries are delivered to a Slack channel for owners to review or refresh.
Set it up
What you configure once, before turning it on.
- 1Connect PostgresAny Postgres URL — query, write, migrate.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect SlackChannels, DMs, threads, mentions.
- 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 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.