Search across educators, skills, and resources.

Learn first

• How to structure instructions, memories, and skills
• When to use MCP servers versus retrieval or file search
• Subagents, hooks, and tool boundaries
• How to keep agent context small, relevant, and testable

Good matches

Simon Willison Matt Pocock Matthew Berman Mervin Praison

Open next

• OpenAI Cookbook
• AI Skills for Real Engineers
• AI SDK v6 Crash Course
• LLM Fundamentals

Learn first

• When to use Claude or GPT-class reasoning models for complex coding, analysis, and long-horizon agent work
• How Gemini, Llama, Mistral, Cohere, DeepSeek, Qwen, Grok, and Perplexity differ by modality, openness, retrieval, coding, and price
• Context windows, output limits, latency, pricing, tool support, and eval-based routing
• How to migrate safely when frontier model versions change

Good matches

Simon Willison Elvis Saravia AI Operators Club Jam Anderson

Open next

• OpenAI Cookbook
• Prompt Engineering Guide
• Perplexity Deep Research and Search API docs
• Perplexity Deep Research Workflows

OpenAI Cookbook

GitHub repo · OpenAI · Beginner to advanced

You need implementation examples rather than theory.

api, examples, rag, agents

Promptfoo

Open-source eval and red-team framework · OpenAI / Promptfoo · Intermediate to advanced

Declarative regression tests and side-by-side comparisons of prompts, models, RAG systems, and agent configurations, especially when red teaming is also required.

evals, llm evaluation, ai quality, open-source frameworks

OpenAI Evals

Hosted LLM and agent evaluation API · OpenAI · Intermediate to advanced

Existing OpenAI API teams maintaining dataset-based prompt or model regression tests during the remaining service window.

evals, llm evaluation, ai quality, cloud and provider evals

ChatGPT Finances privacy and accuracy guide

Connected-finance safety guide · OpenAI · Beginner

OpenAI announced on October 2, 2026 that ChatGPT Finances is rolling out to Free and Go users in the United States. Use this guide to understand the connected-account workflow, check the source data behind answers, and review privacy controls before linking an account.

chatgpt, personal finance, connected accounts, plaid, privacy

Introducing the Agents API

Managed agent API launch and guide · OpenAI · Intermediate to advanced

You want OpenAI's September 10, 2026 launch guide for building long-running cloud agents with the managed Codex harness, context compaction, tool search, multi-agent delegation, and your choice of hosted or self-managed sandbox.

openai, agents, codex, context compaction, multi-agent

GPT-Live-1 in the API

Voice agent model launch · OpenAI · Intermediate

You want OpenAI's September 10, 2026 launch of GPT-Live-1 in the API for full-duplex voice agents, including its $0.05-per-minute front-end pricing and guidance on pairing it with a backend model and agent harness.

openai, voice agents, realtime, api, model selection

OpenAI Data agent in ChatGPT Work

Data agent product guide · OpenAI · Intermediate

You want OpenAI's September 10, 2026 overview of the Data agent in ChatGPT Work, which connects company data, investigates changes, and produces interactive dashboards through a conversational workflow.

openai, data agents, analytics, enterprise, agent workflows

The AI policy window is open. We need to act.

Frontier AI safety policy guide · OpenAI · Advanced

You want OpenAI's September 9, 2026 policy proposal on frontier AI standards, independent assessments, incident reporting, and preserving human control as capabilities advance.

openai, ai safety, frontier models, evaluations, governance

Research acceleration: The view inside OpenAI

Research report · OpenAI · Intermediate

You want OpenAI's September 6, 2026 evidence and measurement framework for how coding agents are changing research workflows, including task delegation, parallel agent use, capability tracking, and the limits of interpreting productivity signals.

openai, codex, research agents, automated research, agent adoption

OpenAI mid-turn steering

API guide · OpenAI · Intermediate to advanced

You are building a GPT-6 Astra workflow where users need to add requirements or redirect a running response over the Responses API without waiting for the current turn to finish.

openai, gpt-6 astra, responses api, mid-turn steering, websocket

OpenAI Codex Record & Replay

Workflow guide · OpenAI · Beginner to intermediate

You want to demonstrate a stable workflow once on macOS and have ChatGPT or Codex turn it into a reusable skill for computer use, browser actions, plugins, and repeated operational work.

openai, codex, record and replay, skills, computer use

OpenAI Codex hooks

Coding agent guide · OpenAI · Intermediate to advanced

You need lifecycle hooks that run scripts or MCP tools around Codex sessions, prompts, tool calls, compaction, subagents, permissions, validation, logging, or persistent-memory workflows.

openai, codex, hooks, mcp, automation

OpenAI Site tools with WebMCP

Web agent guide · OpenAI · Intermediate

You want a website to expose predefined actions directly to ChatGPT Work or Codex in the built-in browser, using the same live page and signed-in session as the user.

openai, webmcp, site tools, browser agents, codex

GPT-6 Astra launch overview

Model launch · OpenAI · Intermediate to advanced

You want OpenAI's September 3, 2026 launch overview for GPT-6 Astra, including its rollout, computer-use and coding focus, long-context behavior, benchmark disclosures, pricing, and new Codex context-retrieval workflow.

openai, gpt-6 astra, frontier models, coding, computer use

GPT-6 Astra model guide

Model guide · OpenAI · Intermediate to advanced

You are evaluating or migrating to GPT-6 Astra and need implementation guidance for async tool calls, mid-turn steering, reasoning updates, Responses API tool use, unsupported parameters, and prompt changes.

openai, gpt-6 astra, responses api, async tool calling, mid-turn steering

OpenAI Sandbox Agents

Guide · OpenAI · Intermediate to advanced

You need the official beta guide to giving Python or TypeScript Agents SDK workflows isolated files, commands, packages, ports, snapshots, and resumable state while keeping the agent harness and sensitive control-plane work outside the execution container.

openai, agents sdk, sandbox, coding agents, containers

OpenAI Tool search

Guide · OpenAI · Intermediate to advanced

Your agent has a large function, namespace, or MCP catalog and you want GPT-5.4 or later models to load only the tool definitions needed at runtime, reducing context use while preserving prompt-cache efficiency.

openai, agents, tool search, deferred tools, mcp

Automating repetitive work at OpenAI with Codex

Practical guide · OpenAI · Intermediate

You want an August 25, 2026 field guide to capturing recurring engineering and evaluation work in reviewable notebooks, keeping approval boundaries explicit, and feeding lessons from earlier agent runs into the next run.

openai, codex, automation, evals, runbooks

OpenAI background mode

Guide · OpenAI · Intermediate

You need the current OpenAI path for long-running jobs, asynchronous tool workflows, or agent tasks that should continue outside a foreground request.

openai, background mode, long-running jobs, agents, automation

OpenAI Fast mode

Guide · OpenAI · Intermediate

You need the current OpenAI guidance for trading higher spend for lower latency in interactive or tool-heavy workflows instead of assuming standard processing is the only mode.

openai, fast mode, latency, gpt-5.6, interactive workflows

OpenAI Ultrafast mode announcement

Release notes · OpenAI · Intermediate

You want the primary-source August 13, 2026 OpenAI changelog entry for Ultrafast mode before teaching or adopting the new GPT-5.6 Sol latency tradeoff.

openai, ultrafast mode, gpt-5.6 sol, latency, release notes

OpenAI Batch API guide

Guide · OpenAI · Intermediate

You want the official OpenAI pattern for queueing large asynchronous jobs such as eval runs, backfills, classification batches, or dataset generation.

openai, batch api, async workflows, cost optimization, offline processing

Migrate to the Responses API

Migration guide · OpenAI · Intermediate

You are starting a new OpenAI integration or upgrading an older chat-completions flow and want the current API surface with built-in agent primitives.

openai, responses api, migration, agents, tool use

OpenAI conversation state

Guide · OpenAI · Intermediate

You need the official OpenAI pattern for preserving conversation state, reasoning items, and multi-turn context across longer-lived agent workflows.

openai, conversation state, responses api, reasoning, agents

OpenAI Flex processing guide

Guide · OpenAI · Intermediate

You need the current OpenAI guidance for trading latency for lower cost on non-urgent workloads instead of pushing everything through the default realtime path.

openai, flex processing, cost optimization, latency tradeoffs, batch workloads

OpenAI Prompt caching guide

Guide · OpenAI · Intermediate

You are sending repeated long context and need the official OpenAI guidance for lowering cost and latency with cache-friendly prompt structure.

openai, prompt caching, latency, cost, long context

OpenAI production best practices

Guide · OpenAI · Intermediate

You are moving from experiments to production and need the official OpenAI guidance on latency, retries, rate limits, safety, monitoring, and operational rollout.

openai, production, reliability, latency, cost

OpenAI eval design guide

Guide · OpenAI · Intermediate

You need practical guidance for designing representative eval datasets, choosing graders, and turning model testing into an engineering loop instead of ad hoc spot checks, especially while OpenAI's older Evals platform is winding down toward read-only status on October 31, 2026.

openai, evals, quality, datasets, regression testing

OpenAI evals quickstart and datasets

Guide · OpenAI · Intermediate

You want OpenAI's current quickstart for turning examples into dataset-backed evals and improvement loops instead of relying on a deprecated docs path.

openai, datasets, evals, fine-tuning, quality

OpenAI external models

Guide · OpenAI · Intermediate

You want to learn how OpenAI handles access to non-OpenAI model families before designing a mixed-provider or routed workflow.

openai, external models, model routing, open models, model selection

OpenAI model guide

Model docs · OpenAI · Beginner to advanced

You need to choose between current GPT-5.6 variants, smaller GPT-5.4 variants, reasoning levels, tool support, and cost-sensitive API paths, including the current default starting points of GPT-5.6 Sol, Terra, and Luna.

openai, gpt, gpt-5, reasoning models, model selection

OpenAI model selection

Guide · OpenAI · Intermediate

You want OpenAI's official framework for balancing accuracy, latency, and cost instead of choosing a model family by brand familiarity alone.

openai, model selection, gpt-5.6, latency, cost

OpenAI API changelog

Release notes · OpenAI · Intermediate

You want the official running log of OpenAI API launches, pricing shifts, renamed features, and model changes before updating a workflow or teaching page.

openai, release notes, gpt-5.6, pricing, migrations

OpenAI deprecations

Migration guide · OpenAI · Intermediate

You need OpenAI's current retirement schedule and recommended replacements before pinning model IDs in evals, coding agents, or user-facing features.

openai, deprecations, migrations, model selection, release notes

Assistants migration guide

Migration guide · OpenAI · Intermediate

You still have Assistants API code or course material and need the exact OpenAI migration path before the Assistants API shutdown on August 26, 2026.

openai, assistants api, responses api, migration, agents

OpenAI Academy

Official learning hub · OpenAI · Beginner to advanced

You want OpenAI's public course hub and guided learning material rather than piecing together model docs, blog posts, and third-party tutorials.

openai, academy, courses, developers, business