Andy Longstaffe

[Boris Cherny @bcherny]

I talk to engineers at other companies every day and hear the same thing: one person is 10x'ing their output with Claude but the rest of the org hasn't caught up.

Watching teams adopt AI, I keep seeing the same 4 steps.

I mapped them out here: Steps of AI Adoption https://t.co/kQnRAUMKpP

[Andy Longstaffe @andylongstaffe]

Engineering needs more product thinkers

https://t.co/G0v0VKNzKl

[Andy Longstaffe @andylongstaffe]

Go -> Rust..... what gives?

https://t.co/MtHrBRScCh

[Andy Longstaffe @andylongstaffe]

https://t.co/cCtnLks5Kw

[Addy Osmani @addyosmani]

https://t.co/0DyFIXJueI

[Andy Longstaffe @andylongstaffe]

Spawning agents is not the skill. Anyone can run 20.

The real skill is designing the system around the one serial resource that cannot be cloned or parallelized. That resource is your attention.

[Andy Longstaffe @andylongstaffe]

https://t.co/gNklhNNNOe
The best thing you can do for your stakeholder is avoid building unnecessary things.

[Andy Longstaffe @andylongstaffe]

https://t.co/TKK7G4HYMG
Fast is good….

[Andy Longstaffe @andylongstaffe]

https://t.co/pBuWBfrVGL
UI and MCP

[Teddy Riker @teddy_riker]

https://t.co/dyiVwtFQNJ

[Andy Longstaffe @andylongstaffe]

https://t.co/yXd5IzSzBp

Agentic developer workflows

[Andy Longstaffe @andylongstaffe]

Keeping the intent
https://t.co/Vn0AiAja4O

[Andy Longstaffe @andylongstaffe]

Could two systems potentially look like different packages or implementations in the same service or app? 🤔

[Andy Longstaffe @andylongstaffe]

https://t.co/EGdTG5oEDk

Speed vs Scale versions !!

[Andy Longstaffe @andylongstaffe]

Scale versions are all about reducing uncertainty and producing a stable system that is understandable, fixable and maintainable.

[Andy Longstaffe @andylongstaffe]

Speed versions are all about reducing uncertainty for the business and getting valuable feedback asap.

[Andy Longstaffe @andylongstaffe]

“Sure, I’ll have the Speed version ready in 3 days. Then the Scale version in about 6 weeks.”

[Andy Longstaffe @andylongstaffe]

now argue the complete opposite. same confidence. same detail. make me believe this instead."

[Andy Longstaffe @andylongstaffe]

Cognitive offloading vs surrender

https://t.co/EzQLICOxxC

[Andy Longstaffe @andylongstaffe]

If you can’t reason about which of the two answers is right, you’ve found a place where you were about to surrender.

[Andy Longstaffe @andylongstaffe]

Ask the model to argue against itself. Most models will produce a confident answer and then, when prompted, produce an equally confident counter-argument. That second pass is cheap and it breaks the borrowed-confidence effect.

[Andy Longstaffe @andylongstaffe]

https://t.co/E4XsNWdjaa