AI AGENTS
New Release Eval -> Snowflake Scorecard History
On each new HuggingFace release in the tracked family, runs your fixed eval against the incumbent and writes a structured scorecard row to Snowflake.
How it runs
The automated pipeline, trigger to output.
- TriggerSchedule polls for new releases
- ActionList new HuggingFace revisionsHugging Face
- LogicKeep revisions not yet in Snowflake
- ActionRun fixed eval, normalize scorecardShell
- ActionWrite scorecard row to SnowflakeSnowflake
- OutputSlack note when swap threshold crossedSlack
What it does
Builds the long-term record behind your model decisions. Every time a new model appears in the family you watch, the workflow benchmarks it against the current incumbent on a frozen eval and appends a fully structured scorecard to a Snowflake table — model id, revision, every metric, cost, and the swap verdict — so you can audit and trend model quality over time.
When to use it
Use it when you need a defensible, queryable history of model evaluations for dashboards, audits, or trend analysis, rather than one-off swap decisions. Pairs well with a BI layer reading from the same table.
How it works
- 1A schedule polls HuggingFace for new releases in the tracked org or collection.
- 2A filter keeps only genuinely new revisions not yet recorded in Snowflake.
- 3The agent runs the fixed eval on the new model and the incumbent.
- 4It normalizes results into a flat scorecard with metrics, cost, latency, and a swap-recommended flag.
- 5It writes the row to the Snowflake scorecard table for history and BI.
- 6It posts a short Slack note linking the new row when a challenger crosses the swap threshold.
Set it up
What you configure once, before turning it on.
- 1Connect Hugging FaceModels, datasets, spaces — the open-source hub.
- 2Connect ShellRun sandboxed commands inside the workspace.
- 3Connect SnowflakeWarehouses, queries, shares.
- 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 AI Agents workflows
Custom Metrics Cardinality Spike Pager
A webhook from a Datadog monitor fires when custom-metric cardinality jumps; an agent pinpoints the offending metric and tag, estimates the added cost.
Sentry-to-Confluence Runbook Updater
When a Sentry issue is resolved, the agent finds the matching Confluence runbook page and proposes an inline update with the verified fix.
Stale Doc-PR Chaser for Runbook Gaps
On a daily schedule the agent finds runbook doc PRs that were opened from resolved incidents but never reviewed, summarizes what each one fixes.
Resolved Incident to Public Troubleshooting Doc
For customer-facing errors resolved in Sentry, the agent drafts a sanitized troubleshooting entry and opens a PR to your ReadMe documentation.
On-Call Runbook Gap Closer: Resolved Sentry Issues to Doc PRs
An agent reads each newly resolved Sentry issue, compares the actual fix against your existing runbook, and opens a GitHub PR adding the missing remediation steps.
Weekly On-Call Doc-Gap Digest
Each week the agent reviews every Sentry issue resolved in the last 7 days, ranks the ones whose runbook coverage is missing or thin.
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.