Skip to main content

Prompts Overview

Prompts are reusable AI instructions that you create once and use everywhere—in chat, via API, or inside workflows.

📖 Building Your First Prompt guide walks through creating a prompt from scratch, understanding every setting, and deploying it to your team.

What Prompts Do​

Instead of retyping the same complex instructions every time you need a specific AI task, you create a prompt once and reuse it whenever needed.

Think of prompts like templates for your most valuable AI conversations. If you've spent time crafting the perfect instructions to get AI to analyze customer feedback in exactly the way your business needs, you don't want to retype those instructions every single time. You save them as a prompt.

Why Prompts Matter​

Consistency - When your team uses the same prompt, everyone gets the same quality AI response every time. No more variation based on how well someone can write AI instructions.

Efficiency - Your best AI interactions become instantly available to your entire team. The sales manager who figured out the perfect way to summarize call notes can share that capability with the whole sales team.

Scalability - As you discover AI workflows that drive real business value, prompts let you standardize and distribute those workflows across your organization.

Common Use Cases​

  • Content translation that maintains your brand voice
  • Customer feedback analysis that identifies themes your business cares about
  • Document formatting that adapts your writing for different audiences
  • Data extraction from unstructured text
  • Code review with your team's standards
  • Meeting notes summarization in your format

Prompts vs. Chat vs. Workflows​

Direct chat with models:

  • One-off conversations
  • Exploring ideas
  • Figuring things out
  • Trying different approaches

Prompts:

  • Repeatable AI tasks
  • Standardized instructions
  • Consistent outputs
  • Shareable across team

Workflows:

  • Multi-step processes
  • Combining prompts with logic and integrations
  • Complex automations
  • Data processing pipelines

Prompts sit in the middle—more structured than free-form chat, simpler than full workflows.

How Prompts Work​

At its core, a prompt is:

  1. Instructions for the AI (what to do)
  2. Variables for dynamic inputs (what changes each time)
  3. Model configuration (which AI, what settings)
  4. Sharing settings (who can use it)

When someone runs your prompt:

  • In chat - They see input fields for variables, run it, get results
  • Via API - External systems pass variables programmatically, get JSON responses
  • In workflows - The prompt becomes a node that processes data and passes output to the next step

The same prompt works in all three contexts. Build once, use everywhere.

Getting Started​

Ready to create your first prompt? The Building Your First Prompt guide walks through every step with a real example.

Or jump to: