# Range (ep. 5)

Posted 2026-10-23 · Video: https://www.youtube.com/watch?v=m37WYs6bj0Y

> Range means looking at your work from more fields than the task seems to need.

**The prior it challenges:** You can only build what your job title says you can

## Transcript

Rethink your priors.

This is part three of four in my mini series within a series on Felix Rieseberg's post, How to be more ambitious, a tutorial for humans with models.

This one is range.

Range means looking at your work from more fields than the task seems to need. More fields than would have been economical in the past.

Felix points out that every heist movie spends the first thirty minutes assembling the crew.

His first trick comes from The Art of Innovation, by Tom Kelley and Jonathan Littman. Replace the nouns with verbs.

A quarterly review isn't a deck. It's getting busy people to believe a story about cause and effect, and to decide under uncertainty, in thirty minutes.

His second trick is to assemble the crew. Pretend the deck has to be amazing, or aliens blow up Earth. Who does humanity bring in?

An analyst, a journalist and an editor. And a red team: a short seller and a forensic accountant.

But don't slip into role play. Don't ask the model to write like a short seller. Ask it to do what a short seller does to research their position. Same rule as depth. No cosplaying.

One requirement for all of it: your model needs a computer where it can install software, and access to the data it needs, through MCP connectors or other means.

So here's mine. I'm not an iOS developer. I shipped a native iOS app anyway. It's called YaySoon. Agents did the screens, the privacy manifest and the App Store prep, and submitted it to Apple review.

My job title did not change.

I'm also not an infrastructure guy. Agents built me a private data service anyway. Postgres, an MCP server, sign-in.

Every agent gets its own scoped identity, every action is audited, and the big moves wait at an approval gate.

Range is fun. I just want a paper trail with it.

Next time, why this is so hard for us in the first place.

Anyway. Start from the outcome. Or don't. I'm not your manager. Follow for more.

---
Rethink your priors by Eduardo Martínez. AI implementation. Outcomes over tools. And everything else.
YouTube: https://www.youtube.com/@rethinkyourpriors · Instagram: https://www.instagram.com/rethinkyourpriors/ · Work with Eduardo: https://edumartinez.ai/