MARKET RESEARCH
Daily HuggingFace license-change scan for vendored models
Each morning, checks the model cards of every HuggingFace model your team has vendored and flags any whose license metadata changed since the last run, writing a risk note to Coda.
How it runs
The automated pipeline, trigger to output.
- TriggerDaily schedule (morning run)
- ActionRead vendored-model list from Coda tableCoda
- ActionFetch current model card + license for each modelHugging Face
- LogicKeep only models whose license string changed
- OutputWrite dated risk note to Coda License Risk LogCoda
What it does
Keeps a running inventory of the HuggingFace models your product depends on and watches each one's license for silent changes. When a model card's license tag flips (for example Apache-2.0 to a custom "research-only" license, or a switch to a gated/OpenRAIL term), it logs a dated risk note in a Coda table so legal and engineering see it the same day instead of at audit time.
When to use it
Use it when you ship inference on third-party open weights and a license downgrade could create real exposure. Ideal for a model-governance or platform team that has 10-100 vendored models and no automated way to know when upstream changes the terms.
How it works
A daily schedule reads your vendored-model list from a Coda table. For each model ID it fetches the current model card and license metadata from HuggingFace, then compares the license string against the last value stored in Coda. A logic step keeps only the models whose license actually changed. For each change, it writes a new row to a Coda "License Risk Log" table with the model ID, old license, new license, and timestamp, then updates the stored license so the next run compares against the new baseline.
Set it up
What you configure once, before turning it on.
- 1Connect CodaDocs, packs, automations.
- 2Connect Hugging FaceModels, datasets, spaces — the open-source hub.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Market Research workflows
Enrich Inbound Accounts with BigQuery Firmographics and Score Fit
When a new account row lands in Airtable, joins it against BigQuery public business datasets to attach firmographic attributes.
Blend BigQuery TAM with Live Competitor Signals into a Notion Brief
On demand, sizes a chosen segment from BigQuery public data, gathers current competitor signals via Brave Search, and synthesizes a one-page market brief into Notion.
Allocate Sales Territory TAM from BigQuery Geo Data to HubSpot
When triggered by a webhook, queries BigQuery public ZIP-level business data to compute TAM per sales territory.
Hiring Surge Detector with Slack Alert
Detects when a target account's open-role count jumps above its recent baseline and posts a ranked Slack alert to the GTM channel so reps can act on a company that is clearly…
Tech-Stack Shift Inference from Job Descriptions
Reads new job descriptions for target accounts, uses an LLM to extract named technologies and infer stack changes.
Weekly Hiring-Intel Briefing for GTM
An agent reviews the week's accumulated hiring signals across all target accounts, writes a narrative briefing that infers each account's likely initiatives.
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.