# ChatGPT playbooks OpenAI's AI assistant for the web, desktop and phone. It has a Chat mode for questions and drafts, and a Work mode for longer tasks that end in a file, analysis or report. People use it to research, write, analyze files and connect to tools such as Google Drive and Slack. - Vendor: OpenAI - Kind: assistant - Surfaces: web, desktop, mobile, browser, voice - Connects: Plugins bundle skills and MCP servers, and you add them from the Plugins tab. Type @ to call a plugin or skill. The desktop app can add custom MCP servers in settings. A built-in browser and a browser extension run in the desktop app, and a cloud browser runs on web. - Docs: https://learn.chatgpt.com/codex/use-chatgpt ## Good at - Answering questions and drafting text in a back-and-forth chat - Creating documents, spreadsheets, slides and PDFs you can download - Pulling context from connected tools through plugins - Keeping related chats, files and instructions together in projects ## Limits - The web app does not read local Codex config, so local MCP servers only work in the desktop app - Local files, apps and Computer Use need the desktop app - Some features depend on plan, region, workspace settings and rollout ## Playbooks (22) - [Build a keyword map that gives every page on your site one search query to own](https://agentshandbook.com/p/build-a-keyword-map-with-one-page-per-query.md): One table that maps each query to one page, with intent and status, plus a backlog of gaps sorted by value. (trust: corroborated, risk: low) - [Build a private spending dashboard from your bank and card CSV exports](https://agentshandbook.com/p/build-a-spending-dashboard-from-bank-csv-exports.md): You get a local dashboard of spending by month and category that you can rebuild each month, with totals that match your statements. (trust: corroborated, risk: medium) - [Build a weekly KPI report from your spreadsheets and send the draft for approval](https://agentshandbook.com/p/build-a-weekly-kpi-report-for-approval.md): Every Monday you get a draft report with this week's KPIs, the change from last week, a data check section and three lines of commentary, ready for one person to approve and send. (trust: corroborated, risk: medium) - [Claim compensation for a delayed or cancelled flight under EU261, UK261 or US refund rules](https://agentshandbook.com/p/claim-flight-delay-compensation.md): You know which rule applies and what you can claim, and you have sent a claim with your evidence attached and a plan for the next step if the airline refuses. (trust: corroborated, risk: medium) - [Clean and deduplicate a messy CRM or CSV export without losing real records](https://agentshandbook.com/p/clean-and-deduplicate-a-crm-or-csv-export.md): You get a clean file, a change log that explains every merge, and a short review sheet of possible duplicates for you to decide, with every original row accounted for. (trust: corroborated, risk: medium) - [Do a literature review with an agent that finds, screens and summarises real papers](https://agentshandbook.com/p/do-a-literature-review-of-papers-on-a-topic.md): You get a screening log, an evidence table with one row per included paper, a synthesis that cites only papers you hold, and a reference list where every entry resolves to a real record. (trust: corroborated, risk: medium) - [Draft your weekly newsletter from the links you saved, in your own voice](https://agentshandbook.com/p/draft-weekly-newsletter-from-reading-list.md): You get a draft issue with a short, sourced summary of each link you saved, grouped by theme, plus a list of links the agent could not read. (trust: corroborated, risk: medium) - [Find and book a restaurant table or local appointment with a shortlist you approve](https://agentshandbook.com/p/find-and-book-a-restaurant-or-appointment.md): You have a confirmed booking at a place you chose, at the right date, time and party size, with the cancellation terms known. (trust: corroborated, risk: medium) - [Find the questions AI assistants answer without naming your brand, and plan content to fix it](https://agentshandbook.com/p/find-questions-ai-answers-without-citing-you.md): You get a table of buyer questions with your mention rate, competitors' mention rates and cited sources per assistant, plus a short content plan for the biggest gaps that you approve. (trust: corroborated, risk: low) - [Gather your tax documents into one folder and write a checked summary for your accountant](https://agentshandbook.com/p/prepare-tax-documents-and-a-summary-for-your-accountant.md): Your accountant gets one tidy folder, a list of every form with its key figures and source, a list of missing documents, and your open questions. (trust: corroborated, risk: high) - [Get a refund from a merchant, then dispute the card charge if they refuse](https://agentshandbook.com/p/dispute-a-purchase-with-a-merchant-or-chargeback.md): You send the seller a clear refund request with evidence, and if that fails you file a card dispute on time with the same evidence. (trust: corroborated, risk: medium) - [Match receipts to bank transactions and flag VAT or sales tax questions for your accountant](https://agentshandbook.com/p/match-receipts-to-bank-transactions-for-your-accountant.md): You get a workbook with every bank line matched to a receipt or marked missing, a proposed category for each, and a short list of VAT or sales tax questions for your accountant. (trust: corroborated, risk: high) - [Negotiate a lower internet or phone bill with an agent-prepared script or chat](https://agentshandbook.com/p/negotiate-a-lower-internet-or-phone-bill.md): You lower your bill, or get a firm answer from retention, without agreeing to a plan change or contract you did not approve. (trust: corroborated, risk: medium) - [Plan a week of dinners and fill a grocery cart that you check and pay for](https://agentshandbook.com/p/plan-weekly-meals-and-fill-a-grocery-cart.md): You have a week of dinner recipes, one shopping list grouped by aisle, and a reviewed cart at your store that you paid for yourself. (trust: corroborated, risk: medium) - [Prepare for a doctor's appointment with a one-page summary and question list](https://agentshandbook.com/p/prepare-for-a-doctor-appointment-with-an-organized-summary.md): You bring a one-page summary of your symptoms, timeline and medicines, plus three to five questions, and your doctor makes every medical judgment. (trust: corroborated, risk: high) - [Refresh a blog post that lost traffic with a gap analysis of the pages that outrank it](https://agentshandbook.com/p/refresh-a-blog-post-that-lost-traffic.md): A refreshed post that covers what the top results cover and more, with the same URL and voice, and a plan you approved. (trust: corroborated, risk: low) - [Run a deep research report and check that every citation supports its claim](https://agentshandbook.com/p/run-a-deep-research-report-and-verify-its-citations.md): You get a report where every factual claim links to a source that loads and says what the report claims, plus a table of the claims you cut or changed. (trust: corroborated, risk: medium) - [Sort support tickets or survey answers into themes with counts you can check](https://agentshandbook.com/p/code-support-tickets-or-survey-answers-into-themes.md): You get a spreadsheet with every ticket or answer labelled, a theme table with counts and example quotes, and an agreement check that shows how far to trust it. (trust: corroborated, risk: low) - [Track a product's price and buy when it drops below your target, with you approving the purchase](https://agentshandbook.com/p/track-a-price-and-buy-when-it-drops.md): You buy the exact product you chose at or below your target price, and you pay for it yourself after checking the final total. (trust: corroborated, risk: medium) - [Turn a long podcast or video into a blog post, a timestamped clips list and social posts](https://agentshandbook.com/p/turn-podcast-or-video-into-blog-clips-and-posts.md): You get a blog draft, a list of clip candidates with start and end times, and a set of social posts, all checked against a timestamped transcript. (trust: corroborated, risk: low) - [Turn scattered travel records into an interactive mapped diary](https://agentshandbook.com/p/turn-scattered-travel-records-into-a-mapped-diary.md): You get a single HTML file that maps your destinations, totals your nights and mileage, and splits personal from business travel, covering as much of your history as your records allow. (trust: reported, risk: low) - [Write landing page copy variants with an agent and A/B test them properly](https://agentshandbook.com/p/write-and-ab-test-landing-page-copy.md): You get 3-5 copy variants tied to a written hypothesis, one live A/B test with a fixed sample size, and a result you can trust or a clear "no difference". (trust: corroborated, risk: low) ## Lessons - [Chat assistants apply the wrong consumer rule with confidence](https://agentshandbook.com/lessons/agents-misapply-consumer-rules.md) - [Agents miscount and drop rows unless every number comes from code](https://agentshandbook.com/lessons/agents-miscount-and-drop-rows-unless-they-use-code.md) - [AI-personalised cold emails read as generic or pitch the wrong thing](https://agentshandbook.com/lessons/ai-outreach-personalisation-reads-generic.md) - [AI research tools cite sources that are broken, made up, or do not say what is claimed](https://agentshandbook.com/lessons/ai-research-citations-fail-to-support-claims.md) - [AI summaries change quotes, numbers and timestamps, or describe pages they never read](https://agentshandbook.com/lessons/ai-summaries-alter-quotes-numbers-and-timestamps.md) - [A calendar invite from a stranger can hijack the assistant that reads your calendar](https://agentshandbook.com/lessons/calendar-invites-can-hijack-your-assistant.md)