CONTENT CREATION
Route low-confidence Hugging Face captions to Slack for human review
Generates captions for media records with Hugging Face and auto-applies high-confidence results.
How it runs
The automated pipeline, trigger to output.
- TriggerScheduled batch of uncaptioned recordsAirtable
- ActionGenerate caption + confidence via Hugging FaceHugging Face
- LogicBranch on confidence threshold
- ActionPost low-confidence drafts to Slack for reviewSlack
- OutputWrite approved caption to AirtableAirtable
What it does
This is a human-in-the-loop captioning gate. Each image gets a Hugging Face caption plus a confidence signal. Confident captions are written straight to Airtable. Anything below the bar is posted to a Slack channel with the image preview and the draft caption, so a reviewer can confirm or correct it before it becomes canonical.
When to use it
You want the speed of automated captioning but can't ship customer-facing alt-text blindly. This routes only the uncertain cases to people, keeping reviewer load low while protecting quality.
How it works
- 1A schedule pulls a batch of uncaptioned Airtable image records.
- 2Send each image to the Hugging Face model and capture the caption and confidence.
- 3Branch on confidence: high-confidence captions write directly to Airtable and mark the record done.
- 4Low-confidence captions post to Slack with the image, the draft text, and approve/edit actions.
- 5The reviewer's confirmed or edited caption is written back to the Airtable record.
Set it up
What you configure once, before turning it on.
- 1Connect AirtableBases, tables, views, automations.
- 2Connect Hugging FaceModels, datasets, spaces — the open-source hub.
- 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 Content Creation workflows
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.
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.
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.
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.
Research-driven localized hero banners tuned per market
An agent researches cultural and seasonal cues for each target market, adapts the master hero concept to fit local context, generates a tailored image per locale.
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.