CONTENT CREATION
Answer a support ticket with a Loom-sourced article when one matches
When a Zendesk ticket arrives, match its question against your library of Loom-derived help articles and, if there's a strong match, draft a reply embedding the relevant article…
How it runs
The automated pipeline, trigger to output.
- TriggerNew Zendesk ticket createdZendesk
- ActionLLM ranks help articles by relevanceOpenAI
- LogicProceed only if match confidence is high
- ActionFetch matched Loom chapter timestampsLoom
- OutputDraft Zendesk reply with article and Loom clipZendesk
What it does
Intercepts incoming Zendesk tickets and compares the customer's question to your existing Loom-based help articles. When the LLM finds a confident match, it drafts a support reply that links the article and embeds the most relevant Loom chapter. Weak or no match leaves the ticket untouched for a human.
When to use it
For support teams that have built a library of recorded walkthroughs and want to deflect repeat "how do I" questions with the exact video segment that answers them, without auto-sending anything risky.
How it works
- 1A new Zendesk ticket is created and triggers the workflow.
- 2An LLM reads the ticket and ranks candidate help articles by relevance to the question.
- 3A confidence check decides whether the top match is strong enough to act on; low confidence ends the run.
- 4Fetch the matched recording's chapter timestamps from Loom to deep-link to the right moment.
- 5Draft an internal Zendesk reply with the article link and the timestamped Loom embed for an agent to approve.
Set it up
What you configure once, before turning it on.
- 1Connect ZendeskTickets, queues, knowledge base.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect LoomVideo transcripts, libraries.
- 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 Content Creation workflows
On-demand: turn a blog URL into narrated B-roll clips
Accepts a blog URL via webhook, scrapes the article, generates a B-roll clip per paragraph with Replicate and a voiceover with ElevenLabs.
Sync a Figma master frame into localized hero renders
Pulls the current master hero frame and its text layers from Figma, generates a localized image variant for each locale defined in Airtable.
Build a Dropbox B-roll library from exported blog drafts
Triggers when a new blog draft file lands in a Dropbox folder, generates a Replicate B-roll clip for each paragraph.
Generate B-roll clips when a blog post is marked Ready in Notion
Watches a Notion blog database for posts flipped to 'Ready', splits the body into paragraphs, and generates a short B-roll video clip for each paragraph with Replicate.
Weekly: clip last week's top blog paragraph and post to socials
Runs on a weekly schedule, picks the highest-traffic paragraph from the past week's posts, generates one polished B-roll clip with Replicate.
On-Demand Screenshot Freshness Report from a Slack Command
A writer requests a freshness check in Slack for a specific docs page; the workflow inspects every screenshot on that page, scores each by age and version gap.
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.