Codex Automations for Baseball Research #Shorts

Codex Automations can prepare recurring research context before you start working. In this Marvin Builds Short, baseball research is the example: public Major League and Minor League sources, candidate flags, source notes, and human review questions. This is not a professional scouting tutorial. The point is the automation pattern: let Codex scan public sources, prepare a first-pass brief, and keep the final judgment human. The exact prompt used for the demo is below. Copy it, adapt it, and use it for your own recurring research task. PROMPT Create a recurring Codex Automation that prepares a concise morning baseball scout-style research brief. This is a Codex Automations demo, not a professional scouting workflow. Use baseball scouting only as the example domain. Your job is to prepare context for human review, not to make final player decisions. Run context: - Use the current run date, the user's timezone, and the latest verifiable public information available at run time. - Start the report with a short data cutoff line. - If live data is unavailable or a page cannot be verified, state the limitation clearly. Task: Scan public baseball sources and prepare a short brief that helps a human decide where to look first. Source priorities: 1. MLB official stats and player pages: - mlb.com/stats - mlb.com/player 2. Baseball Savant / Statcast: - baseballsavant.mlb.com - focus on contact quality, exit velocity, hard-hit rate, barrels, expected stats, pitch profile, or similar public metrics when available 3. MiLB public stats: - milb.com/stats - focus on age versus level, production, plate discipline, strikeout/walk pattern, role, and recent changes 4. MLB Pipeline / prospect context: - mlb.com/milb/pipeline - mlb.com/prospects 5. Transactions and roster movement: - mlb.com/transactions - official team or league transaction pages when relevant Optional watchlist: [Paste your own player watchlist here. Suggested columns: Player, Organization, Level, Position, Age, Scout Focus.] Watchlist rules: - If a watchlist is provided, use it as the main tracking list. - If no watchlist is provided, do not invent one. - If no watchlist is provided, identify up to five real candidate leads only when each lead can be verified from reliable public sources. - Do not invent players, stats, injuries, transaction details, prospect status, or source claims. Output format: Keep the report under 700 words. Use compact bullets and small tables where useful. 1. Data Cutoff State the run date, timezone assumption, and what data window was checked. 2. Candidate Leads List up to five source-backed players worth a human first look. For each lead, include: - Lead: player, team/organization, level or league - Reason: why the player surfaced - Uncertainty: what the public data does not prove - Next human check: one concrete follow-up question 3. Source Notes Summarize which public sources were checked and which source gaps matter. 4. Human Review Questions End with three questions a human should answer before making any scouting or roster judgment. Rules: - Do not provide signing recommendations. - Do not rank players as final targets. - Separate verified facts from interpretation. - Prefer clear English over scouting jargon. - If the evidence is weak, say so directly. - End with "Confidence Level: high / medium / low" plus one short reason. Marvin Builds: real AI-agent workflows, shown end to end. #Shorts #Codex #AIAgents #OpenAI #Baseball #MarvinBuilds