ENGINEERING
Weekly HuggingFace model-drift digest to Notion
Once a week, summarizes all card, license, and revision changes across your watched HuggingFace models into a single readable digest page in Notion and posts the link to Slack.
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly schedule fires
- ActionLoad past week's drift events from PostgresPostgres
- ActionSummarize and group events with LLMOpenAI
- ActionCreate dated Notion digest pageNotion
- OutputPost digest link to SlackSlack
What it does
Rolls up a week of upstream activity into one place. Rather than a stream of per-change alerts, it aggregates every detected card edit, license change, and new revision across your watchlist over the past seven days, has an LLM write a concise plain-English summary grouped by model and severity, and publishes it as a dated Notion page. The team gets a single Monday-morning read on what moved upstream.
When to use it
Use it as the calm companion to the real-time alarms: leadership and the broader team want a periodic overview, not pages. Good for status syncs and keeping a durable change log of your model supply chain.
How it works
- 1A weekly schedule triggers the digest.
- 2It loads the past week's recorded drift events from Postgres.
- 3An LLM step groups and summarizes the events by model and severity.
- 4It creates a dated Notion page containing the digest.
- 5It posts the Notion link to Slack so the team can open it.
Set it up
What you configure once, before turning it on.
- 1Connect PostgresAny Postgres URL — query, write, migrate.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect NotionPages, databases, comments.
- 4Connect SlackChannels, DMs, threads, mentions.
- 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 Engineering workflows
Agent reviews model-license fit and suggests compliant swaps on the PR
When a PR adds a Hugging Face model, an agent reads the model card and license, judges fit against your commercial-use policy.
Block PRs that add incompatible Hugging Face model licenses
When a pull request adds or bumps a Hugging Face model dependency, it fetches the model card license, checks it against your org's allowed-license policy.
Quarterly Logging Hygiene Audit Agent
An agent-driven quarterly sweep that surveys all Axiom datasets, builds a logging-hygiene scorecard per service.
Post-Merge Log Volume Recheck After Downsampling PR
After a log-level PR merges, waits a day then re-queries Axiom to confirm the targeted stream's volume actually dropped.
Axiom Ingest Cost Spike to Linear Triage Ticket
When Axiom ingest volume spikes beyond its baseline, identifies which service caused it and files a Linear ticket with the offending log stream, sample lines, and a downsampling…
File a Linear license-review ticket for risky model adds
When a PR introduces a Hugging Face model with a non-permissive or unknown license, it opens a Linear issue assigned to the legal-review team with the model, license.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.