Use cited public sources
Rules for factual answers backed by cited public sources such as standards, papers, and official documentation.
Updates and release notes
Release notes for new guides, prompt files, policies, reference pages, and technical articles published on Andy's AI Playbook.
RTL/LTR BiDi-Safe Hebrew Output
Use this prompt component to keep Hebrew responses readable when they mix RTL Hebrew with LTR English, code, URLs, paths, filenames, commands, numbers, or identifiers.
How AI Tools Read Emotional Signals in Text
Explains how AI assistants interpret emotional signals in text, why that is not emotional understanding, and why affective inference must not control authorization, truth, or tool use.
Answer with cited public sources — procedure
Procedure for answering factual public-world questions with cited authoritative sources, stable locators, and fail-closed behavior when evidence is missing.
Run Chain-of-Verification before final output — procedure
Step-by-step guide for running Chain-of-Verification inside a selected evidence boundary before accepting a final answer.
Prompt Components for AI Workflow Controls
Reusable prompt components for adding evidence boundaries, verification checks, deep search, artifact reading, confidence scoring, and no-fabrication controls to AI workflows.
Use Web Search When Current Facts Matter
Use this prompt to request web search for current, changing, or hard-to-verify public information, with cited sources and fail-closed behavior when evidence is insufficient.
Evidence-Gated Academic Mode
Use this evidence mode to require authoritative citations, academic register, structured evidence labels, fail-closed behavior, and confidence scoring.
Check Implementation Against Official Documentation
Use this prompt to review supplied code, configuration, or design materials against official documentation, standards, or primary vendor guidance.
Use Provided Material Only
Use this prompt component when answers must rely only on files, logs, screenshots, excerpts, repository snapshots, ZIPs, or other material supplied in the current request.
Gmail and WhatsApp Agents as Private-Message Execution Surfaces
Security analysis of Gmail and WhatsApp agents as private-message execution surfaces, covering prompt injection, sensitive data exposure, sender ambiguity, tool misuse, memory contamination, and safer workflow controls.
Review Architecture and Boundaries
Use this prompt to review system architecture, layering, dependency direction, interface boundaries, state ownership, and minimal structural remediation from supplied code or design materials.
Run the architecture boundary review — procedure
Procedure for architecture classification, layering and boundary analysis, and minimal structural remediation from inspected materials.
GA4 and Funnel Visibility Audit
Use this prompt to review whether GA4 events and conversion-funnel tracking make important user actions, subscription paths, checkout steps, and conversion outcomes visible.
SEO Discoverability Audit
Use this prompt to review whether a page or site can be discovered, crawled, indexed, understood, and internally connected before or after publishing.
Review SEO and conversion visibility before publishing — procedure
Use this guide to review whether a page or site is discoverable in search and measurable through GA4 events, subscription tracking, checkout tracking, and conversion-funnel visibility.
Confidence Score
Use this prompt component to add an evidence-based confidence score to standard AI responses.
Add an evidence-based confidence score — procedure
Procedure for adding an evidence-based confidence score to non-sentinel answers while preserving fail-closed evidence behavior.
File Upload Is Not Full-File Review
A technical explainer on why file upload is not proof of full-file review in AI workflows, how file content may be extracted, split, retrieved, and selected, and how professional workflows check source coverage before trusting the output.
Review test coverage and regression risk — procedure
Use this guide to review whether code, configuration, API, fixture, mock, or test changes are adequately covered by tests and protected against regression.
ChatGPT workflow placement
Map AI workflow layers to ChatGPT Projects, project files, Project Sources, Project Memory, Custom GPTs, GPT Knowledge, capabilities, apps, actions, Skills, Custom Instructions, Library, Agent mode, and runtime chat prompts.
Claude workflow placement
Map AI workflow layers to Claude Projects, Project Instructions, Project Knowledge, RAG, Claude Skills, Claude Code, CLAUDE.md, settings, permissions, hooks, MCP, subagents, artifacts, and runtime chat prompts.
Gemini workflow placement
Map AI workflow layers to Gemini Gems, Gem instructions, Knowledge files, Gemini personalization, Connected Apps, Google AI Studio, Gemini API, Files API, File Search, tools, structured output, function calling, and Vertex AI system instructions.
API / internal agent systems workflow placement
Map AI workflow layers to API-based systems, internal agents, backend automation, retrieval/RAG, files, tools, function calling, orchestration, approvals, structured outputs, evals, tracing, batch, caching, realtime, embeddings, security, and governance.
Prompt Components for AI Workflow Controls
Reusable prompt components for adding evidence boundaries, verification checks, deep search, artifact reading, confidence scoring, and no-fabrication controls to AI workflows.
Grammar and Clarity Review Without Changing Claims
Use this prompt to review grammar, spelling, punctuation, clarity, sentence flow, terminology consistency, and readability while preserving the original claims and meaning.
Review an Academic Article Draft
Use this prompt to review an academic or research article draft for claim support, citation coverage, argument structure, academic register, and unsupported overclaims.
Generate Beginner-Friendly Code With Assumption Checks
Use this prompt to turn a technical goal into minimal, understandable code while checking missing context, avoiding automatic agreement, and preventing invented project details.
Plan a Behavior-Preserving Code Refactor
Use this prompt to plan a small behavior-preserving code refactor with explicit preserved behavior, risk areas, required checks, and test impact.
Review Code Against Language and Framework Best Practices
Use this prompt to review code quality, readability, maintainability, naming, modularity, error handling, dependency use, testability, and alignment with relevant language or framework guidance.
Review Test Coverage and Regression Risk
Use this prompt to identify missing test scenarios, weak assertions, setup gaps, and regression-sensitive paths after a code or configuration change.
Vibe Coding and the Loss of Engineering Ownership
A professional analysis of vibe coding, AI-assisted software development, and the engineering risk created when generated code is accepted without understanding, review, testing, and maintainability controls.
AI How-To Guides for Source Verification, Output Review, Code Review, and Prompt Setup
Step-by-step guides for source rules, AI output review, code and engineering review, prompt setup, context and memory boundaries, and publishing measurement.
Observed Classification Layers in ChatGPT
Client-side black-box analysis of observed ChatGPT classification artifacts across user access, prompt demand, and capability allocation.
Parallel Exploration in LLM Systems Is an Orchestration Pattern
A system-design view of parallel exploration in LLM systems: sequential autoregressive decoding at the base-model layer, with branching, evaluation, and synthesis added by orchestration.
Use web search for current or niche claims
Rules for when to use web search, how to select public sources, and how to cite current or niche factual claims.
Request web browsing — procedure
Step-by-step guide for requesting web browsing for current or niche public questions, with citation-grade outputs and fail-closed behavior.
AI Source Verification Guide for Factual Answers
Choose whether an AI answer should rely on uploaded files, cited public sources, or academic-style evidence review before you use it.
Fluency Is Not Factuality Why LLMs Can Sound Right and Be Wrong
Why fluent LLM outputs can still be wrong, and how to enforce evidence-locked answers with retrieval, provenance, and fail-closed gates.
Run a structured fact-check before the final answer
Verification workflow for checking claims, citations, evidence boundaries, Chain-of-Verification, and confidence before using AI-generated output.
AI How-To Guides for Source Verification, Output Review, Code Review, and Prompt Setup
Step-by-step guides for source rules, AI output review, code and engineering review, prompt setup, context and memory boundaries, and publishing measurement.
AI How-To Guides for Source Verification, Output Review, Code Review, and Prompt Setup
Step-by-step guides for source rules, AI output review, code and engineering review, prompt setup, context and memory boundaries, and publishing measurement.
AI Prompt Templates and Workflows
Reusable prompts, prompt rules, workflow stacks, and setup guidance for document analysis, source-backed research, writing review, code review, SEO review, analytics, citations, and output verification.
AI Prompt Templates and Workflows
Reusable prompts, prompt rules, workflow stacks, and setup guidance for document analysis, source-backed research, writing review, code review, SEO review, analytics, citations, and output verification.
AI Prompt Templates and Workflows
Reusable prompts, prompt rules, workflow stacks, and setup guidance for document analysis, source-backed research, writing review, code review, SEO review, analytics, citations, and output verification.
AI Prompt Templates and Workflows
Reusable prompts, prompt rules, workflow stacks, and setup guidance for document analysis, source-backed research, writing review, code review, SEO review, analytics, citations, and output verification.
AI Prompt Templates and Workflows
Reusable prompts, prompt rules, workflow stacks, and setup guidance for document analysis, source-backed research, writing review, code review, SEO review, analytics, citations, and output verification.
Summarize Provided Material
Use this prompt to summarize files, notes, logs, reports, threads, or pasted excerpts without adding unsupported claims.
Using ChatGPT Effectively at Work: A Practical Guide
A practical guide to using ChatGPT effectively at work by choosing the right mode, tool, memory setting, and project structure for each task.
Web Retrieval Prompt Injection Boundary in LLM Systems
Threat model for web retrieval prompt injection in LLM systems, covering external content, tool routing, downstream actions, and control boundaries.
Choose a review policy for code or system design
Routing page for choosing the correct review policy for architecture, boundaries, or implementation against official sources.
Code Review — choose the correct engineering review path
Decision guide for routing code-related work to the correct review path: architecture boundaries, standards-backed implementation review, test coverage and regression risk, language/framework code quality, or behavior-preserving refactor planning.
Prompt Components for AI Workflow Controls
Reusable prompt components for adding evidence boundaries, verification checks, deep search, artifact reading, confidence scoring, and no-fabrication controls to AI workflows.
AI Prompt Templates and Workflows
Reusable prompts, prompt rules, workflow stacks, and setup guidance for document analysis, source-backed research, writing review, code review, SEO review, analytics, citations, and output verification.
When Human-Like Signals Fail-Cue Misalignment in Clowns and AI-Generated Outputs
An analysis of near-human cue misalignment in clowns, AI-generated faces, and AI-generated text, focusing on uncertainty, perception, and the limits of human-like simulation.
LLM-Led vs Orchestrator-Led Tool Execution
Comparison of LLM-led and orchestrator-led tool execution in LLM systems, including control-plane placement, reliability, observability, latency, cost governance, and security.
Sycophancy in LLM Assistants
Technical explanation of LLM sycophancy, belief-agreement bias, preference optimization, production behavior, and mitigation paths.
Prompt Engineering Guide for Daily Work (Deep Dive)
Deep dive on why prompts fail in daily work, how to design evidence-bounded prompt specifications, and how to evaluate them.