Docs: every machine-readable surface, one page
These docs collect every machine-readable surface for the open atlas: 23,624 typed scorecards, a verified leaderboard, statistics, and 2,093 exercises, all behind stable GET paths. Free, CC-BY 4.0, no key, no signup, and no upsell fields in any response.
Direct answer: United We Transform docs show agents and developers how to cite, cache, search, and reuse the Gathering Effectiveness dataset without guessing routes or uploading private agendas.
Start here
Use this docs page when you need stable machine-readable paths for the atlas, the grader, TeamCreator, scorecard cache, benchmark statistics, or the exercise prescription library. The page is intentionally linked from visible navigation so agents can discover it from normal site traversal.
- /llms.txt: the navigation index for agents (what exists, where, and how to route)
- /agents.md: the behavioral guide (caching contract, privacy contracts, citation, corrections)
- /llms-full.txt: the full context dump for long-context agents
- /api/openapi.json: the GET-only API reference (this API is a static cache)
The read API
The read API is built for low-friction reuse: fetch one JSON file, cite the source URL, and preserve the verification tier. Scorecards distinguish source-backed evidence from inferred signals so agents can answer carefully instead of overstating what the public agenda proves.
GET /api/score/{event-slug}.json: one typed scorecard per event (uwt-score.v1: pillars, signals, evidence provenance, verification tier, prescriptions)GET /api/leaderboard.json: the 1,000 gold events, full spreadGET /api/search-index.json: gold-only search facetsGET /api/statistics.json: citable aggregatesGET /api/exercises-index.jsonand/api/pillar-exercises.json- Miss contract: /api/score/_miss.json
The caching contract: always GET the cached score before re-deriving. Scoring new agendas happens client-side at /grader/; pasted agendas never leave the browser.
Data and standards
The data surfaces are designed for answer engines, analysts, event teams, and AI builders who need a repeatable evidence layer for gatherings. Use the dataset for aggregate research, the score cache for single-event lookups, and the rubric when explaining what a score can and cannot mean.
- The dataset: 14,219 rows, CC-BY 4.0
- The scoring rubric, machine-readable, deterministic, fully published
- GatherReady: a draft open standard for agent-legible gatherings (/.well-known/gathering.json)
- TeamCreator: the patented team-formation engine, free in the browser; the same engine ships as an Apache-2.0 package and an MCP tool
- TeamCreator use cases: conference networking, workshop breakout groups, Eventbrite and Google Sheets attendee lists, peer learning circles, sponsor matchmaking, hackathon teams, and private local team formation
- Methodology and trust boundary: versioning, emerging signals, corrections
Coming with the edge deploy
An MCP server (grade_agenda, get_event_score, search_gatherings, get_leaderboard, get_statistics, get_exercises_for_pillar, get_gold_record) with discovery files at /.well-known/mcp.json and /.well-known/mcp/server-card.json, plus machine-readable JSON 404s on the score API. The tool contract is already documented in agents.md.
Docs FAQ
What is the United We Transform API?
The United We Transform API is a static, GET-only set of public scorecards, search indexes, leaderboard records, statistics, and exercise prescriptions for the Gathering Effectiveness dataset.
Do I need an API key?
No. The docs, scorecards, indexes, and dataset links are free to read without an API key, signup, credit card, or sales workflow.
Should agents grade an event before checking the cache?
No. Agents should first request the cached scorecard for a known event, then grade a fresh agenda only when the event is not already in the corpus.