AI tips

type Tip = {
  title: "Give the model the role and the reader";
}

Say who it is writing as and for whom (e.g. 'a CFO who skims'). Output changes more from audience than from adjectives.

type Tip = {
  title: "Paste the source, don't describe it";
}

Paste call notes, docs or logs. Summaries of summaries lose the details that matter.

type Tip = {
  title: "Ask it to flag gaps instead of guessing";
}

Add 'If the input doesn't support an answer, write NEEDS REVIEW.' This cuts made-up details in customer-facing work.

type Tip = {
  title: "Use structure for reusable outputs";
}

Request fixed sections or a table so status updates and POC docs look the same every week.

type Tip = {
  title: "Iterate in two passes";
}

First ask for a draft, then ask it to critique the draft as the skeptical buyer, then revise.

type Tip = {
  title: "Keep a personal prompt library";
}

Save prompts that worked with your [BRACKET] variables. Our prompts page is a starting point.

type Tip = {
  title: "Check your company's data policy first";
}

Don't paste customer data, credentials or contracts into tools your company hasn't approved.

type Tip = {
  title: "Verify every number and claim";
}

Treat model output as a draft. Check figures, product capabilities and competitor claims before they reach a customer.

type Tip = {
  title: "Use AI for demo data, not demo truth";
}

Generate fake but realistic sample data; never let the model invent features your product doesn't have.

type Tip = {
  title: "Turn tribal knowledge into runbooks";
}

Paste Slack threads and ask for numbered steps with verification and rollback. Then test the runbook once yourself.

type Tip = {
  title: "Prep with a role-play";
}

Ask the model to play the skeptical buyer or security reviewer and run through your demo or answers.

type Tip = {
  title: "Learn how your tools connect to AI";
}

Standards like the Model Context Protocol let assistants reach your tools and data; understanding them is quickly becoming part of deployment work.