Patrick Robinson retweeted
Now you’re basically a manager. So, AI should keep working while you’re away from the keyboard - just like you kept coding when your manager was away.
“Every engineer is now a team leader, a manager, and your direct reports are the models and agents you use...but a team of two people who always pair-programmed together would not be much of a team, nor would a team where no one worked when the team leader was in a meeting.”
Patrick Robinson retweeted
“Your job has fundamentally changed. It is no longer to write code, and LLMs are not here to help you write better code faster.
Your job is to help the LLM write better code faster.”
Bingo.
Replying to @josephfcox
Here is Proton CTO's AI manifesto, that I obtained multiple copies of 404media.co/manifestos-fear-…
My youngest was needing a diaper change while dressed as Captain America. I told my wife "you're changing America's butt"
Working on a monster truck derby game for my son.
I'm willing to lax on some of the realism in the physics for the grandeur of seeing large vehicles do flips...
Patrick Robinson retweeted
Skills can call other skills. They're basically composable functions written in English.
So, like a function, I prefer naming skills with a leading verb:
/open-pr
/audit-instructions
/review-pr-comments
One of the greats! 😢
In lieu of flowers, memorial contributions may be made to:
Johns Hopkins Alzheimer’s Disease Research Center Fund
alzresearch.org/giving/
Alzheimer’s Foundation of America Caregiver Resources
alzfdn.org/donate/
Photo Credit: Tommy Garcia
Patrick Robinson retweeted
In 2026, if I'm creating anything digital by hand from scratch, I'm probably doing it wrong.
Not just code.
Branches
PRs
Tests
Plans
Docs
Skills
Charts
Slides
Summaries
Visualizations
If AI can gen it, I let it.
Then I tweak it.
Patrick Robinson retweeted
Skills are relevant at different times. So I consider running these skills at different points in my day:
Before starting work, I validate my plan:
/grill-me
/audit-ticket
/deep-research
Before my PR, I ensure quality:
/security-review
/code-review or /ultrareview
/simplify
After getting PR comments, I respond to them:
/address-pr-comments
On a scheduled cadence, I check for opportunities:
/improve-codebase-architecture
/security-review
/audit-instructions
One of my favorite moments in @burkeholland's presentation.
Projects looks awesome! Well done! 🙌🏻
👀 LinkedIn putting hidden text with instructions for AI... Thanks Grok @bot for not following them!
Patrick Robinson retweeted
You’re not being lazy enough.
Tickets
Code
Config
Tests
Branches
PRs
Docs
Reports
Requests
All of it should be generated by an agent.
Then, add your human judgement on top.
Patrick Robinson retweeted
I've been coaching on AI adoption for the past couple years now, so I'll be talking about that on Nov 10! Come check it out!
Join Lean TECHniques Staff Engineer and @Microsoft MVP @danielwarddev on November 10 as he discusses what works in helping teams build AI habits that stick. Daniel will draw on DORA research and his own experience coaching teams.
Register below 👇
hubs.li/Q04CtzXL0
Scope creep usually starts in the requirements, not the agent. Keep each story at the smallest deliverable value with INVEST, Given/When/Then, and the side quests dry up.
nitter.cf/onpardev/status/211374…
My wife just offered to be the PM on my household AI projects. First one is taking over PM'ing for the video game I made for my son, Space Pup.
space-pup-sigma.vercel.app
Patrick Robinson retweeted
You can’t build a software factory unless your team first does at least some of its product engineering through a factory as opposed to local coding agents.
This means centralizing your agents into one shared configuration that the team can optimize together. Once work starts flowing through the factory infra, you’ll have a baseline to measure and improve.






















