Skip to content
Data McFly.

writing · tag

Production AI

9 posts tagged “Production AI.”

All tags
Your Agent Is Only as Safe as the Tools You Let It Call
Production AI· Sep 6, 2026· 3 min read

Your Agent Is Only as Safe as the Tools You Let It Call

The model isn't your attack surface. The pile of MCP servers and integrations you wired up in an afternoon is. Agent security is a permissions problem before it's a prompt problem.

Read
The Handoff Is the Product
Production AI· Aug 19, 2026· 3 min read

The Handoff Is the Product

Everyone designs the happy path and bolts escalation on later. But what your agent does when it doesn't know is the entire customer experience.

Read
If You Can Build It in a Weekend, So Can Your Competitor
Production AI· Jul 24, 2026· 5 min read

If You Can Build It in a Weekend, So Can Your Competitor

Wrapping a model isn't a moat. Where AI actually creates defensibility for a startup — and where it just commoditizes you alongside everyone else.

Read
Can You Trust an AI Agent With Your Customer Data?
Production AI· Jul 17, 2026· 5 min read

Can You Trust an AI Agent With Your Customer Data?

The data-privacy and security questions every founder should ask before letting an agent touch customers, payments, or PII — in plain language, not a compliance lecture.

Read
Guardrails: The Boring Work That Keeps AI Out of the Headlines
Production AI· Jun 28, 2026· 3 min read

Guardrails: The Boring Work That Keeps AI Out of the Headlines

Every AI failure that makes the news shares a missing guardrail. They're the unglamorous constraints that turn a confident-but-risky agent into one you can actually trust.

Read
Why Your AI Demo Won't Survive Real Users
Production AI· Jun 28, 2026· 3 min read

Why Your AI Demo Won't Survive Real Users

The demo was flawless. Then real users touched it. The gap between a demo that wows and a system that survives is the unglamorous work that decides whether AI ships.

Read
Evals for People Who Aren't ML Engineers
Production AI· Jun 27, 2026· 3 min read

Evals for People Who Aren't ML Engineers

Evals sound like data-science jargon. They're just a way to test whether your AI is any good, on purpose, on a cadence. Here's how to build your first one with a spreadsheet.

Read
The 70/30 Method: Building With AI Agents Without Betting the Company on Them
Production AI· Jun 15, 2026· 4 min read

The 70/30 Method: Building With AI Agents Without Betting the Company on Them

Why I let AI agents handle about 70% of the work and keep 30% for senior judgment — and how that ratio keeps AI projects out of the ditch.

Read
How I Build AI Agents That Actually Ship
Production AI· Aug 1, 2025· 3 min read

How I Build AI Agents That Actually Ship

Most AI agents die in the demo. Here's the process I use to get them into production — and the unglamorous parts that decide whether they survive contact with real users.

Read
Loading…