Members only
A member article for teams that need reviewable and consistent AI output in recurring daily work.
Practical guidance for AI tools, agents, and APIs.
Guides, prompt templates, workflow files, policies, reference pages, and technical articles for working with AI assistants, agentic systems, and API-integrated tools.
Choose the right path
Start with one clear next step instead of browsing the whole site at once.
Choose which sources AI may use for factual answers
Start with the evidence boundary first: files only, cited public sources, or an academic-style review.
Prompt Engineering Guide for Daily Work
A strong public entry point for evidence boundaries, verification, and fail-closed prompting.
Compare free access and member access
See what stays public, what the US$19/month member plan unlocks, and how member access works.
Explore guides, prompts, policies, reference, and articles
Use the public library that matches the kind of asset you need.
Guides
Step-by-step procedures, runnable checklists, and task-based decision paths.
Prompts
Workflow templates, reusable prompt components, and ready-made stacks.
Policies
Evidence rules, review constraints, and response requirements.
Reference
Stable definitions, diagrams, verification methods, and content maps.
Articles
Long-form analysis, system models, trade-offs, and research-oriented explanations.
Ways to work with AI
Browse the site by how you're working with AI: prompt engineering, AI assistants, agents and workflows, or API integrations and tools.
Prompt engineering
How to write prompts, choose sources, and check answers before you send them.
AI assistants
How assistant products handle sources, memory, and web browsing.
Agents and workflows
How agent systems are orchestrated, how they use tools and memory, and how to review multi-step behavior.
API integrations and tools
Connecting the model to tools, APIs, web browsing, and other systems.
Articles previews
Members only
A member article for reviewers who need a structured way to assess where untrusted content can influence chained LLM systems.
Members only
A member article for reviewers who need a structured way to examine how context, authorization, tools, and state interact across request assembly.
Members only
A member article for reviewers who need a structured way to assess how control-plane weaknesses can let untrusted state influence tool-using LLM systems across steps.
Latest articles
View all articlesRecent public articles from across the playbook.
Latest updates
View all updatesRecent additions across public content, member content, prompts, guides, policies, and navigation.