AI assistants

Use this page when the main problem is how an assistant product behaves: evidence rules, memory boundaries, or browsing inside ChatGPT, Claude, Gemini, or a similar assistant.

When to use AI assistants

• Use this page when the work happens inside a chat assistant product, not inside an agent loop or custom API integration.
• Use it when you need to control assistant source access, memory behavior, browsing, or platform placement.
• Use it when the same workflow must be configured in ChatGPT, Claude, Gemini, or similar assistant surfaces.

Before you start

• Know which assistant product you are using and what information it can access.
• Decide whether the task should use only uploaded material, cited public sources, or no external retrieval.
• Decide whether the workflow belongs in a chat, Project, Gem, GPT, Skill, Knowledge file, or API setup.

Core workflows

• Use ChatGPT effectively at work Use this when the main decision is which ChatGPT mode, tool, memory setting, or project structure to use.
• Choose where the assistant may get facts Use this when you need to decide whether the assistant may use files, public sources, or academic-style evidence.
• Request web browsing in an assistant Pro Use this when current or niche public information is required.
• Manage LLM memory boundaries Use this when assistant memory or project context affects answers.

Platform setup

Configure this topic in your AI tool

Use the platform mapping when this topic becomes a reusable workflow, project setup, assistant configuration, prompt file, knowledge source, or API/system instruction.

ChatGPT Projects, GPTs, Skills, files/sources, Custom Instructions, Memory, and runtime prompts. Open mapping → Claude Projects, Project Instructions, Project Knowledge, Skills, Claude Code surfaces, and runtime chat input. Open mapping → Gemini Gems, Gem instructions, Knowledge files, Memory, Connected Apps, AI Studio, Gemini API, Files API, File Search, and Vertex AI. Open mapping → API / internal systems System/developer instructions, retrieval, tools, orchestration, approvals, validation, evals, logging, and application state. Open mapping →

Also relevant in

• Prompt engineering
  The main problem is the prompt wording, reusable instruction, or output contract.
• Agents and workflows
  The main problem is multi-step orchestration, routing, or system boundaries.
• API integrations and tools
  The main problem is custom API integration, tool calling, or external system wiring.