The AI Field Guide
Which AI do you use?
Choose your edition

One useful task at a time

Go beyond
asking questions.

Start with a job you wish someone would take off your plate. Explain the result, give it the information, and check the work.

Follow along, copy a prompt, and try it with sample information. Replace anything in [brackets].

01

Choose work AI can do while you’re away

Asynchronous means you start a job now and come back later to review it. The AI may pause when it needs you.

Good fits include research and comparisons, summaries, organizing information, drafts, and small prototypes. These produce something you can check before using it: a supplier comparison, a service FAQ from public information, or a draft reply list.

Use this six-question check

  1. Is the finish line clear? Ask for a one-page comparison or five draft replies, rather than “improve my business.”
  2. Are the inputs ready? Provide the facts, files, and approved tools. Check they remain accessible while you are away.
  3. Is the job bounded? Set the scope, time limit, and spending limit. Start small; do not authorize open-ended work.
  4. Are the steps low-risk and reversible? Prefer drafts and copies over changes to live records or customer accounts.
  5. Can you check the result? Ask for sources, calculations, tests, and any uncertainty. Inspect the output yourself.
  6. Does it know when to stop? Require a pause for missing facts, unavailable access, a new decision, or a reached limit.

Keep a person involved

AI can prepare options and drafts. Keep spending, consequential messages, publishing, deletion, and security or access changes behind explicit approval. You can approve specific, bounded actions; some sensitive steps require you to act yourself. Medical and financial decisions need human judgment and qualified review.

Try a bounded handoff

Using [approved information], prepare [specific result] for my review. Work only within [scope, time limit, and spending limit]. Include sources and unresolved questions.

Do not send, publish, delete, or change access. Stop and ask if information is missing or a decision would change the plan. Finish with the result and what you checked.

Before stepping away, confirm background execution is available. Any steps using your own computer still need it awake and connected.

02

Describe what you want built

A long-running job needs a clear finish line. Work with AI to write the brief before asking it to build.

“Build me a virtual classroom” leaves too much to guess. Who will use it? What should happen when they click? What should it look like? An interview turns a rough idea into decisions the AI can follow while you are away.

  1. Let AI ask questions about the people, goals, features, style, and limits.
  2. Have it turn your answers into a detailed build brief, including what success looks like.
  3. Review the brief. Correct assumptions and approve the first version before implementation.

Start with an interview

Help me design a virtual classroom for a fictional three-year-old who is beginning to read. Interview me first. Do not build anything yet.

Ask a few plain-language questions at a time about:
- Learning goals, child and parent users, and activities.
- Features, how they should work, parent progress tracking, and rewards.
- Colors, visual style, devices, and ease of use.
- Privacy, budget, time, other constraints, and what a successful first version must do.

Ask follow-up questions when choices are unclear. Do not invent my preferences.

Then turn my answers into a detailed, self-contained build prompt for a coding agent. Include the agreed behavior, design, limits, and checks for success. Separate the first version from future ideas and flag unresolved choices. Let me review it before implementation.

You do not need to know the technical terms. Explain the experience you want, then check that the brief describes it accurately.

03

Organize your work

Save details you will use again so you do not repeat yourself.

For a returning job, a Project can hold related chats, files, and instructions. Add the Seestar script brief and approved notes, then continue the work there.

Start a Seestar image project

I need a script to check my mounted Seestar S50 storage and external storage for newly captured images. Find the JPEG with the most stacked frames and copy it to a local folder.

First confirm the storage locations and destination; do not invent paths. Ask what counts as new and whether I want one JPEG overall or one per observation. If frame counts are unclear, ask rather than guess.

Copy selected images without changing or deleting the originals.

Set up an ongoing Project to track the brief, decisions, script, and work completed. Help me version the script with GitHub. Confirm the repository before pushing code, and do not upload images unless I approve.

A Page is an editable document. ChatGPT Space holds saved work; a space groups related Pages. Ask for your approved plan as a private Page, or save a document instead.

Space is available on eligible Pro, Business, and Enterprise accounts. Create and edit on desktop or web; mobile editing is coming soon.

Check sharing first: a shared space includes its Pages, and a shared Page includes child Pages. Linked files keep their permissions; copied private details become visible to the Page’s readers.

Optional examples · field notes and project rules

Try it with your project

Using the observing notes and equipment list in this project, suggest three targets for my next clear night. Ask for my location and date if they are missing. Explain why each target suits my equipment.

Build a home for your field notes

Create a private Space for Deep Space Field Notes, with an equipment page, an observing log, and a next-session plan.

Use only the notes and files I provide. Keep source links and mark missing details as questions. Do not invent observations or change the original files.

Draft the next-session plan as a Page I can edit. Ask for my location and date if they are missing. Keep everything private for my review; do not invite anyone or schedule updates.

AGENTS.md starter

# Working rules
- Explain changes in plain language.
- Label sample data and uncertain claims.
- Never invent customer feedback or test results.
- Test changed behavior and report what was not checked.
- Finish with what changed, the evidence, and the next step.
04

Connect your apps

A plugin connects AI to an app you use. Each connection gives it specific tools and permissions.

One project can use several connections. For Deep Space, each has a different job:

  • GitHub keeps the Seestar script and its change history.
  • AWS Core helps inspect approved hosting and plan how to put changes online.
  • Fourthwall could connect a storefront for selling selected images, where the required tools and permissions are available.

Connect Deep Space to its apps

Help me plan the next step for Deep Space using the connections I approve.

GitHub: inspect the Seestar script and its version history in [repository].
AWS Core: inspect the approved hosting setup and prepare a deployment plan.
Fourthwall: check the available tools, shop permissions, and product catalog. Draft options for offering selected images for sale, if supported.

Confirm the accounts, repository, AWS environment, and shop first. Say which connections are available or missing. Keep the existing Deep Space gallery and domain unchanged.

Read and prepare drafts only. Ask before deploying, uploading images, publishing listings, changing prices or domain records, or spending. Report what you verified and what remains proposed.

Connecting an account is different from approving a change. Start with reading and a plan; review before anything is deployed, published, or offered for sale. Available plugins and actions vary by account.

Connect one app at a time

Choose the account and access this project needs. A connection can be installed but still need sign-in or permission.

  1. Open the Plugins directory. Find the service, select + to add it, and sign in when prompted.
  2. Read the permission screen. If it shows checkboxes, tick the access you want to grant, then approve.
  3. In Settings → Plugins (called Apps in some versions), open the connection’s Permissions. Keep Always ask for actions you want to review. Start a new chat to use the plugin.

Confirm the selected repository, hosting account, or shop. Reading information and changing it are separate permissions. Do not use a write action just to test the connection.

05

Save a routine as a skill

A Skill saves a method you want AI to follow again.

Reuse a weekly update

Save a Weekly Update skill. Ask which approved notes to use. Summarize completed work, blockers, decisions, and next actions.

Include sources. Flag missing facts; do not invent progress, owners, or dates. Keep it as a draft. Do not send, change shared files, or schedule anything.

Test once with sample notes. If saved skills are unavailable, give me a reusable prompt.

A Skill remembers how; a schedule decides when. Saving a Skill does not grant access or start future work.

Optional routine · Good Morning and Good Evening

Create your daily skills

Help me create two reusable skills: Good Morning and Good Evening.

Ask which calendar, email, chat, and document connections to check, and where to save my daily note.

Good Morning: check those sources and give me three priorities, today's meetings, and blockers.

Good Evening: compare the morning plan with actual progress. Save completed work, open commitments, and tomorrow's first step.

Include source links and say when a connection could not be checked. Do not send messages or change my calendar. Test both skills once.

In ChatGPT, choose @skill-creator where available. In Codex CLI or the IDE, use $skill-creator. Claude has its own skill settings and Claude Code uses SKILL.md files.

06

Make something you can use

A Site turns your work into a website or interactive tool people can open and use.

Deep Space turns selected telescope images and capture details into a gallery. Its existing project keeps image preparation, review, and publication separate. Build on that work rather than start over. See the example project.

Build on the Deep Space gallery

Help me build on my Deep Space gallery to share selected Seestar images and their capture details.

First inspect [confirmed GitHub repository] to understand the existing script and gallery. Confirm the image folders, selected images, available metadata, preview location, and publication destination. Do not invent paths or missing facts.

Use approved image copies. Preserve the originals, existing gallery and domain, and private working files. Show verified capture details beside each image; mark unknown details clearly.

Prepare a reviewable preview for phone and desktop. Test image loading, navigation, and captions. Explain the changes and publication plan.

Wait for my approval before uploading images, deploying, publishing, changing the domain, or adding sales links.

Open the preview and try it. Check the images, captions, phone layout, and who can access it. A working preview is a review point; publishing is a separate decision.

Optional Site capability · approved visitor data

Where enabled, a workspace-private Site can use supported plugins to show each signed-in visitor data from their own approved accounts. Sharing the Site does not share your account connections. Sharing, plugin access, and scheduled updates have separate settings.

Sites with plugins

Optional creative example · Before the Morning Bell

Build a small first version

@Sites Create a short, spooky browser escape game called Before the Morning Bell.

Start with one room, one hidden key, and one locked exit. Add a clear goal, readable controls for mouse and touch, and an ending when I escape. Include an optional sound toggle; keep sound off until I turn it on.

Save a first version for me to review before publishing. Include brief instructions for trying it.
07

Put a task on a schedule

A scheduled task repeats a job at a saved time. Test the job once before scheduling it.

A daily fantasy review can turn fresh league information into decisions for you to make. What matters changes during the week: completed games, waivers, injuries, or the next lineup deadline.

Review both fantasy teams daily

Use my approved fantasy connection to review both of my Sleeper teams. Confirm the teams and current season/week. Keep each league’s rules and recommendations separate.

Check recent results, upcoming matchups, rosters, injuries, available waiver options, and lineup suggestions. Focus on today’s useful decisions and verified deadlines. Include current sources, an as-of time, and missing data. Do not invent results or availability.

Recommendations only: do not change lineups, add or drop players, submit claims or bids, or make trades.

Run once for my review. Then help me schedule this every day at [time] in [time zone], delivered privately to [destination]. Confirm both teams, source access, and the saved task. If scheduling is unavailable, give me the prompt to run manually.

Check the actual saved schedule, time zone, destination, and first result. A written promise is not a created task. Writing a cadence on a Page does not schedule it. The task must be able to reach both teams’ data when it runs.

Optional public-web example · weekly pricing check

Start a weekly pricing check

Check these dumpster rental companies in [city]: [official website URLs]. Compare [dumpster size], rental days, included weight, base price, and extra fees. Link each source and date the result. Mark unpublished prices “quote required.” Do not contact the companies.

Run this once now and save the comparison in [destination]. After I check it, schedule the same task for Mondays at 8 AM in [timezone]. Compare with the last successful result and report changes or failed checks. Confirm the task exists and where I can see its results.
08

Hand off a longer job

Give one outcome, a checkpoint, and a clear finish line.

Prepare an event packet

Use [approved brief and files] to prepare an event plan, invitation draft, reply queue, and weekly update. Reuse the same verified facts; label unknowns.

Show the plan and wait for approval. Then save each finished draft. Pause when a missing decision blocks progress. Do not send, book, buy, publish, or change sharing.

Finish with the four drafts, sources, checks, and unresolved questions. Tell me where to reopen this task.

At a checkpoint, ask: “Compare this with my brief. What passed, failed, or still needs review?” Correct the scope, then resume the same task.

Cloud work runs on a remote computer. Eligible new Work tasks can continue across devices with sync enabled. Check that the task can reach its files and tools; cloud access does not include your local files or sign-ins automatically.

Steps using your computer need it awake, online, and connected. Any job can pause for missing inputs, permission, or limits.

Optional software case study · an overnight Codex job

Example · BullyBearAI An overnight Codex session worked through epic #1090 and produced eight draft pull requests—proposed code changes ready for review.

The run reported 11h 25m of session elapsed time and a separate 2h 46m goal timer. It did not deploy to AWS. The Claude edition adapts the workflow; the original run used Codex.

  1. Create an epic. This is the overall outcome, such as “Make our weekly customer report trustworthy.” Add small feature issues underneath, each with a clear completion check.
  2. Label the features. AFK means “away from keyboard”: the AI has enough information and permission to finish. HITL means “human in the loop”: it needs a person’s decision, access, or real customer feedback.
  3. Launch the ready work. Set the scope, time limit, and allowed actions. Subagents are extra AI workers; give each a separate task and have the lead agent track progress.
  4. Review in a new chat. Give another agent the code changes and test evidence. Ask it to inspect and check the work before you use it.

Prepare once, return from anywhere

  1. Prepare the environment on web or desktop. Add the repository, describe the tools and setup you need, and let Codex test it. Review the access and publish the environment when it is ready.
  2. Start a cloud task. Choose Work in → Cloud and the published environment. On mobile, open Codex and choose an available environment.
  3. Return to the same task. Reopen it to continue with its saved files and progress. A new task starts separate work from the published setup.

Codex Cloud currently does not support browser or computer use. Work and your dot’s cloud computer have different capabilities. Save important output and commit code changes; saved task state is not a replacement for source control. Cloud task guide · Environment setup

Start in Codex with the project and required access ready. For a job that should run while your laptop is closed, use a prepared Codex Cloud environment. You can check its progress from another device. Local or Remote work still needs its host computer available.

Use /goal where supported, including the desktop app, interactive Codex CLI, or IDE extension. In Work on the web, paste the brief directly. Give either tool the same clear outcome, boundaries, and completion checks.

Launch a bounded job

In Codex, work through the AFK-ready features under [repository and epic]. Refresh the issues and project rules first; skip blocked or human-dependent work.

Use up to two subagents on independent tasks, with separate branches. For each feature, implement it, run the relevant tests, update documentation, and open a draft pull request. Save progress after each feature.

Stop after [time limit], at [usage limit], or when no ready work remains. Report any limit you cannot measure. Do not merge or deploy. Finish with PR links, test evidence, dependencies, and what needs a person.

Hand the result to a fresh reviewer

A second chat gets a clean look at the work. Include the epic, pull requests, and the original completion checks. If deployment is part of the review, name the exact test environment.

Review and validate the work

Review BullyBearAI epic #1090 and PRs #1128, #1129, #1130, #1134, #1135, #1136, #1139, and #1140. Fetch current changes and dependencies; do not rely only on the author's summary.

Check the code and rerun tests. Fix problems on the affected PR branch and push the updates. Recheck after every fix.

Deploy and test sequentially only in [authorized AWS test account, region, and environment]. Stop if that target is unspecified. Record the deployed commit and results for each PR. Do not merge or touch production, broker access, or trading controls. Finish with the review order and remaining blockers.

Before you leave: check that the agent can reach the files and tools, knows when to stop, and has somewhere to save progress. Long jobs can still stop for limits, questions, or missing access.

09

Give your dot an ongoing role

A dot is an ongoing assistant that can coordinate work and bring back decisions.

Create your dot on desktop or web, then use the supporting mobile app update. Review its plugin permissions and use Custom Rules to set approval boundaries.

Keep a launch on track

Help me prepare [product] for launch on [date]. First ask about the customer, readiness, and sources you may use.

Draft a launch checklist, five customer answers, and three blockers. Link evidence and flag missing facts. After I approve the plan, keep these drafts current through launch day and tell me what changed.

Do not send, publish, spend, or change code. Report access problems or limits. Stop on launch day unless I extend the work.

Its cloud work can continue between conversations. Local-computer steps still need that computer available. Background research is read-only; actions follow your permissions and safety rules.

Rolling out to eligible Pro and Business Premium accounts. Enterprise, Edu, and Healthcare need admin-enabled beta access. If unavailable, try a one-off Work task or Chat. Dot availability and setup

Before you call it done

Open it. Try it. Check the evidence.

Open the result. Try it. Check facts and missing work. Save the instructions that helped.

Read the examples first

Editable prompts and templates for ChatGPT/Codex or Claude. Read one here, replace the sample details, then copy the instructions you want to use.

The optional ZIP contains 29 text files: 19 Markdown (.md), 9 plain text (.txt), and 1 CSV tracking sheet. There are no installers, executable scripts, or macro-enabled documents. Some advanced prompts ask AI to change code or deploy it; review those permissions before using them.

Browse all 29 files

Choose a filename to read its complete contents here. The preview and individual download use the same bytes as the ZIP entry.

README.md

Download this file

# 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.

Start here and everyday work

Plans and reusable routines

Websites and games

Advanced software work

Download all examples as a ZIP · 32,872 bytes (32.9 KB)

To use the ZIP, extract it and start with README.md. Open the files in a text editor, or the CSV in a spreadsheet. Downloading them does not connect accounts or create tasks.

September 29 OpenAI announcements, setup, Space, file workflows, cloud continuity, and dots checked September 30, 2026. Other examples retain their September 25 review. Features vary by account and app version.

Video credit: How to Use ChatGPT Work Better Than 99% of People.

An independent guide. Not affiliated with OpenAI or Anthropic.

Optional · which tool does what?

Start with the AI you already use. Chat handles questions and drafts. Work handles jobs with files and tools. Codex is a dedicated workspace for building and testing software. A dot can coordinate ongoing work; it still needs the right access and permissions.

Features vary by plan, app, region, and workspace settings. If a feature is unavailable, practice the same brief in Chat. You can ask for a website without learning to read code.

GitHub stores software projects. AWS provides cloud computing services. Neither is required for these everyday exercises.

September 29 updates · optional reference

DevDay 2026. Checked September 30. Beta, preview, and coming-soon features are labeled; account and rollout limits apply.

Everyday work and collaboration
  • dots: Give an always-on assistant a continuing responsibility, with clear permissions and review points. Rolling out to eligible accounts. Official details
  • ChatGPT Space and Pages: Keep editable documents and saved work together. Space is available on eligible Pro, Business, and Enterprise accounts. Mobile can find, read, and share Pages; creation and editing are coming soon. Official details
  • Work across devices: Continue eligible new synced tasks on desktop, web, or mobile. Local steps still need the connected computer online; old tasks retain their original mode. Official details
  • Meetings plugin · beta: Turn meetings into private notes and suggested actions in Space. Available on macOS for Pro and Business; Enterprise is in limited alpha. Obtain everyone’s consent before taking notes. Official details
  • Collaborative slides · coming weeks: Announced for Pro, Business, and Enterprise, with multi-person editing and presentation/export options. Do not plan a live demonstration until it appears in your account. Official details
  • Shareable profiles: Showcase selected Sites and plugins. Personal profiles start private; public viewers must sign in. Review the audience and visible information before sharing. Official details
Apps, plugins, and websites
  • Plugin Creator and discovery: Build reusable plugins with help, submit them through the updated flow, and find relevant tools through improved recommendations. Users still choose connections and permissions. Official details
  • Plugin Extensions: Developers can add sidebar apps, panels, file editors, and forms. Free/Go web extensions are coming soon; composer mentions are desktop-only. Official details
  • Sites with connected plugins: Build workspace-private apps that use each signed-in visitor’s own approved connections. Sharing the Site does not share your accounts. Official details
  • MCP Events: Supported plugins can trigger agreed work when an event arrives. This requires event support from the plugin; ChatGPT’s integration uses webhooks and MCP 2.0. Official details
  • Sign in with ChatGPT: Use your ChatGPT identity in participating apps. Eligible Plus/Pro users can also authorize plan usage; this draws on their allowance and has separate permissions. Official details
  • Website annotations: Developers can add more precise selection, context, and preview controls for feedback in supported desktop browsers. Official details
Software work with Codex
  • Reusable Codex Cloud environments: Prepare and publish a project setup once. Each new task gets its own workspace; reopen the same task to continue its saved work. Official details
  • Refreshed Codex CLI: Voice, an /agents view, and improved session and worktree controls make longer terminal workflows easier to manage. Official details
  • Code Review: Review code changes in the desktop app, inspect diffs, and ask Codex questions. Automatic cloud reviews can take a first pass while you are away. Official details
  • Codex Security Cloud · research preview: Scan connected GitHub repositories and monitor commits. Inspect validation evidence and proposed patches before creating a draft PR; a scan is not a security certification. Official details
Models, plans, and organizational controls
  • GPT-6.1 Sol: Available in Work, Codex, and the API; not yet in ordinary Chat. Check your account’s models and evaluate results against your own completion checks. Official details
  • Astra Ultrafast: A premium speed tier in Work/Codex for Pro $500 and eligible Enterprise/Edu plans. Workspace controls and usage limits apply. Sol Ultrafast was announced as coming soon. Official details
  • Pro $500/month: A new optional higher-usage tier with Ultrafast access. The workshop’s basic exercises do not require this tier. Official details
  • Teams and Team Tasks: Business/Enterprise teams can share work and run scheduled or event-triggered tasks using approved service-account connections. Admin permissions determine what is available. Official details
  • @ChatGPT in Slack and Microsoft Teams: Ask for help in approved team conversations. Deployment access, connected tools, and channel permissions are configured by the workspace. Official details
  • Private Intelligence: Business privacy announcements include Private Safety Processing and a Private Inference preview planned for fall. Eligibility and deployment requirements apply. Official details
  • Agent Security: Organizations can set tool, file, and network policies for local and Codex Cloud work. Work Cloud has separate controls. Official details
  • OpenAI Marketplace: Eligible enterprises can express interest in using part of their OpenAI commitment for approved partner software. Official details
For developers building their own agents
  • Decisions API · limited preview: Classify or route inputs using predefined questions and answer choices. A broader release was planned for the following days. Official details
  • Agents API with computer use: Build hosted agents that operate software and use tools, including multi-agent capabilities. This is application infrastructure with its own access and usage requirements. Official details
  • Bedrock Managed Agents: The OpenAI and Amazon integration brings managed-agent capabilities into AWS environments. Review AWS setup, availability, and pricing before use. Official details

Sources: September 29 DevDay recap, DevDay product guide, and the feature documentation linked above. Current docs supply the practical restrictions where announcement summaries are broader.