AI & RAG
Answer field-tech manual questions in Slack with page-cited sources
Lets field technicians ask equipment questions in Slack and replies with a grounded answer plus deep links to the exact manual page each fact came.
How it runs
The automated pipeline, trigger to output.
- TriggerTechnician asks a question in Slack channelSlack
- ActionEmbed query and retrieve manual chunks from Supabase pgvectorSupabase
- ActionGenerate grounded answer constrained to retrieved passagesOpenAI
- LogicIf no passage clears the relevance threshold, return 'not in manuals'
- ActionBuild citation deep links to source pages in Google DriveGoogle Drive
- OutputPost cited answer back in the Slack threadSlack
What it does
Gives field technicians a Slack channel where they can ask plain-language questions about any piece of equipment and get an answer drawn only from the official manuals, with a citation link to the precise page behind every claim.
When to use it
When techs are on-site without time to dig through hundreds of PDF pages, and you need answers that are traceable to an approved source instead of a hallucinated guess. Ideal for service orgs that must defend every spec they quote.
How it works
- 1A technician posts a question in the support Slack channel, which fires the trigger.
- 2The question is embedded and matched against the manual chunks stored in Supabase pgvector, returning the most relevant passages and their page numbers.
- 3OpenAI composes an answer constrained to the retrieved passages and refuses if the manuals do not cover it.
- 4The flow assembles per-fact citations into Google Drive deep links pointing at the source page.
- 5The reply is posted back in the Slack thread with the answer and clickable page links.
Set it up
What you configure once, before turning it on.
- 1Connect SlackChannels, DMs, threads, mentions.
- 2Connect SupabaseTables, auth, storage, edge functions.
- 3Connect OpenAIModels, embeddings, files.
- 4Connect Google DriveDocs, sheets, slides, 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
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.
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…
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.
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.
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.