Framework

5 min read

The four layers of working with AI, and why we stopped climbing them everywhere

The four layers of working with AI, and why we stopped climbing them everywhere

BY Tim Van Gehuchten

Head of Technology & Product Operations

TL;DR

TL;DR

Working with AI comes in two modes: you hand it a task and review the result, or you let it pick up work on its own while you get on with something else. Four layers sit between them: prompt, context, harness and loop. The team deliberately stopped short of climbing all four everywhere, because engineering, product and design each need a different level of autonomy.

Read more on LinkedIn

READ NEXT

READ NEXT

‹ iPhone Duo, from an engineer's seat

28 colleagues, a quiz and a tray of brownies ›

NOVEMBER FIVE

If the product is core to your business, you can't afford to get the team wrong.

LET’S TALK

Get in touch

When your digital product is the business, the margin for error is different. So is the team you need.

If that's where you are, let's talk.

Reach out

Get in touch

When your digital product is the business, the margin for error is different. So is the team you need.

If that's where you are, let's talk.

Reach out