Using AI tools
Use ChatGPT, Claude, and Gemini for research, writing, and everyday work. Find guidance on files, memory, browsing, configuration, and checking results.
Start here
Begin with these resources. The sections below organize the rest of the topic by subject.
-
Skill
Summarizing Key Points
Try a complete Skill for summarizing files or notes using the material you provide.Open skill -
Guide
How to Use ChatGPT at Work: A Complete Professional Guide
Follow the guide to choosing models, configuring a workspace, and verifying professional work.Open guide -
Reference
Claude Projects, Skills, or Claude Code: What to Use When
Find where a reusable workflow belongs in Claude, including Projects, Skills, and Claude Code.Open reference
Set up your assistant
Choose where work belongs in ChatGPT or Gemini, pick a model and reasoning setting, and turn a prompt into a repeatable workflow.
-
Reference
ChatGPT Setup: Choosing Projects, Skills, Plugins, and Tools
Choose models and place workflows across Chat, Work, Codex, Projects, Skills, Plugins, existing GPTs, Scheduled Tasks, memory, and Library.Open reference -
Reference
Gemini Setup: Choosing Gems, AI Studio, API, or Vertex AI
Choose where a Gemini workflow belongs: Gems, personalization, connected apps, Google AI Studio, Gemini API, Vertex AI, or runtime prompts.Open reference -
Article
Beyond the prompt: AI models, reasoning, and speed
How model choice, reasoning effort, and speed settings affect quality, response time, and token use.Read article -
Article
Observed Classification Layers in ChatGPT: User Access, Prompt Demand, and Capability Allocation
A client-side black-box analysis of observed ChatGPT classification artifacts, separating user access, prompt demand, and capability allocation.Read article -
Article
User Prompt vs. Model Context: What an LLM Actually Receives
A user prompt is one part of model context. Learn which instructions, history, files, retrieved data, tools, and memory can become model-visible—and which may remain outside the current inference.Read article -
Guide
Prompt Engineering Guide: Build Reliable AI Workflows
Build reusable prompts with source rules, input checks, output structure, stop conditions, tool boundaries, and validation tests.Open guide
Write, summarize, and research
Copy-ready prompts and Skills for research, comparison, classification, editing, and rewriting.
-
Prompt Template
Research a Topic
Write a cited synthesis of up to 500 words covering key findings, disagreements, and evidence gaps.Open prompt template -
Prompt Template
Compare Two Documents or Versions
Separate substantive differences from wording changes and explain how meaning changed, with quoted evidence.Open prompt template -
Prompt Template
Classify Material With Your Labels
Classify supplied material into predefined labels without inventing new categories.Open prompt template -
Prompt Template
Review Grammar and Clarity
Improve grammar, clarity, terminology, and readability without changing claims.Open prompt template -
Prompt Template
Review an Academic Article Draft
Review claim support, citation coverage, argument flow, and overclaim risk.Open prompt template -
Skill
Humanizing Text
Rewrites robotic, formulaic, or unnaturally formal text so it reads naturally and professionally, while preserving its meaning, tone, and the author's voice.Open skill
Review websites and interfaces
Review search visibility and analytics, assess an interface, or write a design specification.
-
Guide
SEO Discoverability and GA4 Funnel Measurement Workflow
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.Open guide -
Skill
Reviewing Website SEO
Reviews a website's SEO against official search guidance and returns prioritized, evidence-backed recommendations.Open skill -
Skill
Reviewing UI/UX
Reviews an existing website or app interface against UI/UX best practices and accessibility standards, and returns prioritized design recommendations.Open skill -
Skill
Designing UI/UX Specifications
Produces a traceable UI/UX design specification for a new website or app interface, or for a redesign that implements approved review findings.Open skill
Files and memory
What an uploaded file or saved memory actually contributes to an answer, and how to control it.
-
Article
AI File Upload vs. Full-File Review: How to Verify Coverage
File upload does not prove full-file review. Learn how extraction, chunking, retrieval, and active context affect source coverage—and how to verify the output against the original file.Read article -
Article
LLM Memory vs. Context: 5 Architecture Boundaries
A vendor-agnostic model of five boundaries that separate stored state from model-visible context: invocation, persistence, retrieval, context assembly, and updates.Read article -
Guide
How to Control AI Memory and Context Sources
Identify whether prompts, files, past chats, saved memory, project context, retrieval, apps, or backend state influenced an AI answer—and remove unwanted context.Open guide
Connected apps and private data
What connected apps can read and do, and how to protect email and messages when an agent has access.
-
Article
Connected Apps and MCP Security: Permissions, Data, and Actions
Security analysis of connected apps, external tools, and remote MCP servers as capability, scope, approval, disclosure, and side-effect control surfaces.Read article -
Article
Gmail and WhatsApp AI Agents: Private-Message Security Risks
How Gmail and WhatsApp content can steer tool-using AI agents, and how least privilege, explicit approval, provenance, memory controls, and audit logs reduce risk.Read article -
Guide
Protect Gmail and WhatsApp Data in AI Agent Workflows
Protect Gmail and WhatsApp data when AI agents access private messages, attachments, tools, connected apps, and backend workflows.Open guide
Choose sources and evidence
Decide whether an answer may use only your files, cited public sources, current web results, or academic-style evidence.
-
Guide
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.Open guide -
Guide
AI Answers from Provided Files Only: Step-by-Step Workflow
Step-by-step guide for answers based only on files you provide, with file references for each factual claim.Open guide -
Guide
AI Answers With Authoritative Sources and Citations
Step-by-step workflow for answering public factual questions with authoritative sources, stable citations, and fail-closed handling when evidence is missing.Open guide -
Guide
How to Verify Current Facts With Web Search and Citations
Step-by-step guide for requesting web browsing for current or niche public questions, with citation-grade outputs and fail-closed behavior.Open guide -
Guide
Academic-Style AI Answers: Evidence and Citation Workflow
Procedure for running Evidence-Gated Academic Mode with authoritative sources, fail-closed verification, academic register, evidence labels, and confidence reporting.Open guide
Check answers before you rely on them
Why fluent or agreeable answers can be wrong, and procedures for checking claims, citations, and confidence.
-
Guide
How to Fact-Check AI Answers and Citations
Use a claim-level workflow to verify AI answers, citations, source support, uncertainty, and missing evidence before publishing or reuse.Open guide -
Guide
Check a draft AI answer with Chain-of-Verification
Technical guide for turning important factual claims into verification questions before writing the final answer.Open guide -
Guide
How to Add an Evidence-Based Confidence Score to AI Answers
Procedure for adding an evidence-based confidence score to non-sentinel answers while preserving fail-closed evidence behavior.Open guide -
Article
LLM Fluency vs Factuality: Why Fluent Answers Can Be Wrong
Why polished LLM answers can remain unsupported, plus system patterns for grounding claims with retrieval, provenance, validation, and fail-closed controls.Read article -
Article
LLM Sycophancy — When Agreement Overrides Evidence
A primary-source review of LLM sycophancy: operational definitions, user-belief effects, preference-model incentives, the GPT-4o rollback, and release evaluation.Read article -
Article
Cognitive Closure in AI Use: Why We May Stop Too Soon
How the need for cognitive closure may interrupt the evaluation, feedback, and revision needed to improve an AI-generated answer.Read article