AI & RAG
Index Loom SOP recordings into a searchable knowledge base
When a new Loom walkthrough is published, transcribe it, split the transcript into timestamped chunks, embed them, and store them in a vector index so 'how do I' questions can be…
How it runs
The automated pipeline, trigger to output.
- TriggerLoom recording finished processingLoom
- ActionFetch transcript + metadata from LoomLoom
- LogicChunk transcript with timestamp offsets
- ActionEmbed chunks with OpenAIOpenAI
- OutputUpsert chunks + vectors into pgvectorPostgres
What it does
Turns your growing pile of Loom screen recordings into a queryable RAG knowledge base. Every new walkthrough is automatically transcribed, broken into time-aligned passages, embedded, and written to a Postgres pgvector table alongside the Loom share URL and a per-chunk timestamp offset. This is the ingestion half of a Loom SOP assistant — run it once and every later question can cite the precise second in the right video.
When to use it
Use it when your team records standard operating procedures in Loom but nobody can find the right clip later. Ideal for ops, support, and enablement teams who want answers that link straight to the relevant 20-second segment instead of forcing people to scrub a 15-minute video.
How it works
- 1A Loom webhook fires when a recording finishes processing.
- 2The flow pulls the video's transcript and metadata (title, duration, share URL) from Loom.
- 3It splits the transcript into overlapping chunks, each tagged with its start-time offset.
- 4OpenAI embeds each chunk into a vector.
- 5The chunks, vectors, Loom URL, and timestamps are upserted into a Postgres pgvector table, ready for retrieval.
Set it up
What you configure once, before turning it on.
- 1Connect LoomVideo transcripts, libraries.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect PostgresAny Postgres URL — query, write, migrate.
- 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
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.