# AI Field Guide — project starters Fill in the bracketed fields, then attach the relevant brief alongside the guide's copied prompt in ChatGPT/Codex or Claude. These files do not create scheduled tasks or connect accounts. Start with everyday/ for event plans, sample email, weekly updates, and a small winery journal. No GitHub or AWS setup is needed for these examples. - pricing-watch-brief.md: inputs for the baseline and recurring dumpster competitor check. - daily-routine-config.md: shared source roster for Good Morning and Good Evening. - long-run-brief.md: scope, example limits, and outputs for the BullyBearAI AFK cycle. - afk/openai/ and afk/claude/: epic planning, implementation launch, and fresh-agent review prompts. - afk/feature-template.md and afk/run-ledger.csv: a bounded child issue and a progress record. - instructions/openai/AGENTS.md and instructions/claude/CLAUDE.md: adaptable project working agreements. - game/openai/first-build.md and game/claude/first-build.md: platform-specific prompts for the first playable escape-room loop. - game/playtest-followup.md: turn control, puzzle, and audio feedback into a bounded implementation pass. - lms/interview-first.md: ask the agent to help define the deliverable, guardrails, and authorized actions before coding. - lms/full-build-prompt.txt: the complete Izzy's Virtual Classroom example, for use after the interview and review. Adapt personal details and permissions for your own project; it works as a brief for either coding agent. - dots/openai/launch-helper.md: give a ChatGPT dot a bounded responsibility through launch day. Requires Dots access; copying the file does not create a dot. - space/openai/field-notes.md: draft a private collection of editable observing Pages. Requires Space access; sharing and recurring updates are separate steps. Use sources you have access to. Keep secrets out of briefs. The AFK example assumes access to BullyBearAI; adapt the repository, epic, PRs, and deployment target for your project. The historical case used Codex; the Claude briefs adapt the method. The review prompt authorizes a separate deployment phase in the named development environment when you run it.