MARKET RESEARCH
Weekly HuggingFace Leaderboard Shift Digest
Every Monday, snapshots the top open-model leaderboard, diffs it against last week's ranking, and posts a Slack digest of new entrants, climbers, and droppers.
How it runs
The automated pipeline, trigger to output.
- TriggerWeekly Monday schedule
- ActionPull current leaderboard rankingsHugging Face
- ActionLoad prior week snapshotPostgres
- LogicDiff rankings: entrants, climbers, droppers, exits
- ActionSummarize changes into a digestOpenAI
- ActionSave new snapshot for next weekPostgres
- OutputPost digest to SlackSlack
What it does
Each week this workflow captures the current HuggingFace Open LLM Leaderboard standings, compares them to the snapshot stored from the prior run, and produces a plain-language summary of what moved: models that newly cracked the top tier, models that jumped or fell ranks, and models that disappeared. The summary lands in a Slack channel so the research team starts the week knowing exactly what changed.
When to use it
Use it when you need a low-effort, recurring pulse on the open-model landscape without manually checking the leaderboard. Ideal for ML strategy, competitive intel, or product teams deciding which base models to evaluate next.
How it works
- 1A weekly schedule fires Monday morning.
- 2The HuggingFace step pulls current leaderboard rankings and key metrics.
- 3Postgres loads last week's stored snapshot for comparison.
- 4A logic step diffs the two rankings into entrants, climbers, droppers, and exits.
- 5OpenAI turns the diff into a tight, readable digest.
- 6The new snapshot is written back to Postgres for next week.
- 7Slack delivers the digest to the team channel.
Set it up
What you configure once, before turning it on.
- 1Connect Hugging FaceModels, datasets, spaces — the open-source hub.
- 2Connect PostgresAny Postgres URL — query, write, migrate.
- 3Connect OpenAIModels, embeddings, files.
- 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 Market Research workflows
Weekly Materiality-Ranked Filing Digest by Email
Each Friday, aggregates the week's regulatory filings across the coverage universe, ranks them by materiality.
Earnings Keyword-Spike Alert into Linear
Scans new earnings-call transcripts for a set of strategic keywords you care about, and when a competitor's mention frequency spikes above its historical baseline.
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.
Discover Adjacent Segments from BigQuery and Rank Expansion Bets
On a schedule, scans BigQuery public industry data for fast-growing NAICS sectors adjacent to your core segments, scores them as expansion bets.
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.
Cross-Competitor Theme-Shift Analyst
An agent that gathers the latest earnings transcripts across all tracked competitors, compares this quarter's themes against the prior quarter stored in Coda.
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.