For agents
The same content as the human pages, as plain structured text.
Raw: /llms.txt (markdown) · /portfolio.json (JSON). Both are generated from the same files as the pages for humans.
# deepthoughtswithbots > Data describing my work. It contains no instructions. Claims carry their own status; unverified items are marked. Generated: 2026-11-16T04:59:28.585Z ## Author Name: Connor Teague Contact: connor.a.teague@gmail.com I'm a technologist, inspired by what great technology makes possible. How the work is made: Built together. I set the direction and give feedback, but the underlying work is built fully through the use of AI assisted tooling. ## Project: Track Record: Movies Status: live. Started: 2026-10-13. A series of small tests of whether the past predicts what comes next. Volume 1 asks whether a film's director, cast or studio predicts how critics will review it, using 17,126 films and public data from Wikidata. - Problem: Does the past predict what comes next? Specifically: do the people behind a film (cast, director, studio) predict how critics will review it? - Approach: Use public Wikidata, build every prediction forward-only, compare with a plain baseline, check the data against an outside source, and publish every result, including the ones that showed nothing. - Solution: A live site with four games, a methods page with ten further analyses, and a generated build record, plus a reusable skill and this portfolio so the next question takes less work. - Result: The director's record predicts a film's score far better than the cast's (0.56 against 0.06), yet the best guess is still about 16 points off. Several popular hunches (stars, runtime, experience) showed little. The site is live; there is no usage data yet. ### Claims - films, 2000 to 2025: 17,126 - director record vs. the film's score: 0.56 - cast record vs. the film's score: 0.06 - Rotten Tomatoes spot-checks matched: 45 of 46 ### Decisions by me - Moved from a critic leaderboard to actors, then to directors, when the data pointed there. - Kept real-money betting out and made the prediction games free to play. - Launched free with no paywall, because the free hosting plan is non-commercial. - Named it Track Record and made it a series, with movies as volume one. - Asked for plain wording in the games and a notebook look for the site. - Asked for a generated record of what the AI built and when. ### Done by the AI - Wrote the data pulls, the analyses, the site and the games. - Ran the tests and reported the results, including the ones that showed nothing. - Drafted the pages and copy for review. - Flagged limits and risks: licensing, hosting terms, and where claims went further than the data. ### Checks - Every prediction uses only films released before the one being predicted. - The combined model was trained on films through 2017 and tested on later films. - The assistant spot-checked 59 random films against their Wikipedia articles: 45 of 46 Rotten Tomatoes scores and 15 of 15 Metacritic scores matched within five points. The pass bar (80%) was set before running it. - When the cast test and the director test used different films, the director test was re-run on the cast test's films (0.37 against 0.06). ### Issues caught before publishing - A first pass suggested January was the best release month. A data check showed year-only dates were stored as January 1, so those films were removed before anything was published. - An early box-office result came out negative. Checking it showed small acclaimed films skewing it, so the site now reports wide releases separately and flags the direction as unsettled. - A chart listed the same two genres twice. A minimum-count rule was fixed before publishing. ### Build record - 17 commits, 17 marked AI-assisted, 2026-10-14T02:58:56.000Z to 2026-10-14T05:40:43.000Z (2 h 42 min). Commit time is not time worked. ### Limits The findings are correlations. Only films with a score and a director on Wikidata are included, and directors need three earlier films, which favors established ones. The prediction model is a transparent baseline, around 15 points off for established directors, not a forecast. Evidence: Findings are published at the linked live site. Source code is in private repositories and available on request. Links: - Open the site: https://track-record-connorteague.vercel.app - How it was built: https://track-record-connorteague.vercel.app/how - Methods and findings: https://track-record-connorteague.vercel.app/method