Prompt engineering workflows

Use this topic to choose the right prompt-control workflow: define allowed sources, apply reusable prompt templates or components, verify claims before delivery, or route review work through a controlled prompt process.

When to use prompt engineering

• Use this page when the main problem is the prompt, review workflow, source boundary, output contract, or reusable prompt component.
• Use it when you need to decide where the AI may get facts.
• Use it when you need a repeatable prompt workflow for regular work.
• Use it when you need to check an answer, writing draft, or AI-assisted coding output before delivery.

Before you start

• Know the task, user input, source boundary, and expected output format.
• Decide whether the prompt is a one-off instruction, reusable component, workflow template, or system-level rule.
• Keep facts, source material, and verification requirements separate from the runtime task input.

Core workflows

Choose the workflow that matches the prompt-control problem you need to solve now.

• Use a prompt workflow for everyday work Use this when you want a repeatable way to write prompts for regular work.
• Choose which sources AI may use Use this before writing a factual prompt that depends on files, public sources, or both.
• Verify claims before final output Pro Run a deliberate claim-check pass before the final answer.
• Code Review — choose the correct review path Route code or system-design work to the right review path.

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

• AI assistants
  The main problem is how ChatGPT, Claude, Gemini, or another assistant behaves.
• Agents and workflows
  The main problem is orchestration, routing, memory, or multi-step system behavior.
• API integrations and tools
  The main problem is SDK/API wiring, tool calls, web access, or external systems.