Sabitlenmiş Tweet
mager
32K posts
mager
@mager
Agentic Engineer @Uber ⚙️ Building @loooomxyz and @kotsuorg ❤️ KLM
Chicago Katılım Ocak 2007
4.1K Takip Edilen11K Takipçiler
Heard this was the new instagram. Pro-tip: hire the photographer for Tokyo so you get some great photos of your Papa-Daughter adventure 🥰 @OlympiaOhanian
English
My mager-bench scoreboard is up! mager-bench-web.vercel.app
So far I've only benchmarked Haiku, but I learned a lot in the process.
Post: mager.co/blog/2026-07-0…
English
Coding with AI showed you could give models powerful tools and dramatically improve their usefulness.
We're seeing the same thing happen now for all knowledge work. The agent can use the computer as you would and gain context from all the apps you use.
The future is exciting!
English
people are using LLMs to invent new math
we're using it to find undiscovered TUI spinners
Kit Langton@kitlangton
OPENCODE II — 𝓛𝓘𝓠𝓤𝓘𝓓 𝓒𝓡𝓞𝓦𝓝
English
great time to run “/impeccable live” on it!
if you use impeccable and have never tried it, i encourage you to give it a try.
will post video soon
ClaudeDevs@ClaudeDevs
Claude Code on desktop now has an in-app browser. Claude can pull up docs, designs, or any other site. It can read, click through, and interact the same way it does with your local dev servers. It's sandboxed and configurable: you choose whether sessions persist.
English
My 'dangerously skip permissions' flag isn't nearly dangerous enough. Two asks for the Claude Code team: agents that can start /goal themselves, and a permanent grant for computer use. I signed the waiver, let me live my yolo life!
English
if you want to help beta test OpenCode 2.0
v2.opencode.ai
- data in separate db which we might wipe
- stuff will be broken
- use /report to send us issues
- v1 plugins won't work, v2 api not final
there is a built in skill that you can ask for basically anything
English
@AlisonRosen Just stumbled upon this throwback gem alisonrosen.com/2010/08/luncht…
English
The factory pattern is showing up everywhere in AI tooling. Saw @zachlloydtweets from Warp demo it @aiDotEngineer in SF. Keeping an eye on where else this lands.
Post here: mager.co/blog/2026-07-0…
English
Hey I built this and have been sharing it with friends if you want to check it out hmu plz
signüll@signulll
what app do you guys use to create context for ai? e.g. where do you share your links to articles you want to remember, thoughtful/fun images or memes, things you want to read, things you want to watch (youtube vids, tiktok’s, reels), things you want to listen to, interesting tweets, spotify tracks, even clever musings you write to yourself, etc. this is all so fragmented right now. ideally you’d love a place where all of this magically lives & is highly queryable / organizable, etc. i.e. when you use claude/gpt, it should able to reference this database easily for context too. there needs to be a first class citizen here but i think it’s sorta missing.
English
@ToKTeacher @emilfagerholm I would have never understood it unless I listened to Brett explain it multiple times on TokCast!
English
Uber is automating beyond the SDLC #GoGetIt
Praveen Neppalli@praveenTweets
Agentic AI adoption is on fire at @Uber, and it's changing the way we build, not just in engineering, but across the entire company. Today, 99% of our engineers use AI tools. More than 70% of pull requests are attributed to local or cloud agents. And our engineers have built 2,500+ agent skills across the software development lifecycle. Those numbers are exciting, but they led us to a much bigger question: How do we bring agentic AI beyond engineering? Finance. Legal. Operations. Marketing. Customer Support. HR. Procurement. These functions run on complex workflows that are often manual, highly nuanced, and spread across dozens of systems. You can't automate them effectively by looking at process diagrams or documentation. You have to understand how the work actually gets done. So we created something called Agentic Pods. The idea is simple. We handpicked ~30 of our most AI-proficient engineers (people with deep knowledge of Uber's systems) and paired each of them with a domain expert from a business function. Then we gave every pod just two weeks. • Days 1 – 2: Shadow the expert. Observe every step. Document workflows. Ask questions. Build intuition. • Day 3: Prioritize opportunities based on scale, repetition, business impact, and data availability. • Days 4 – 5: Build a working agent alongside the person doing the job. • Days 6 – 9: Validate with several others performing the same work. Does it generalize? Does it actually make their job better? • Day 10: Ship. In just the past two months, we've run 16 Agentic Pods across 16 different business functions. • Capital allocation across 150 cities: 15 hours → 30 minutes. • Financial pacing reports: 2 days → 10 minutes. • Marketing web quality assurance: 2 weeks → 50 minutes. • Support workflow creation: 9,000 manual workflows → self-service automation. The productivity gains are impressive, but what surprised us most wasn't the speed. • It was how quickly engineers embedded in unfamiliar domains uncovered opportunities that had been hiding in plain sight. • The biggest wins rarely come from automating one task. They come from rethinking an entire workflow. Once you redesign the workflow around AI, you often eliminate handoffs, remove unnecessary approvals, replace legacy tooling, reduce vendor spend, and dramatically accelerate decision-making. • The workflow becomes the unit of automation - not the individual task. • The most impactful agent skills cut across teams, orgs, functions, tools, and systems. The biggest lesson? The best AI opportunities are rarely visible from the outside. You discover them by sitting next to the people doing the work, understanding every friction point, and building with them, not for them. We're now forming a dedicated team to scale this further and go deeper. They'll deeply understand the work, redesign it from the ground up, and use AI to fundamentally change how the business operates. It's exciting times!
English
mager retweetledi
Agentic AI adoption is on fire at @Uber, and it's changing the way we build, not just in engineering, but across the entire company.
Today, 99% of our engineers use AI tools. More than 70% of pull requests are attributed to local or cloud agents. And our engineers have built 2,500+ agent skills across the software development lifecycle.
Those numbers are exciting, but they led us to a much bigger question:
How do we bring agentic AI beyond engineering?
Finance. Legal. Operations. Marketing. Customer Support. HR. Procurement.
These functions run on complex workflows that are often manual, highly nuanced, and spread across dozens of systems. You can't automate them effectively by looking at process diagrams or documentation. You have to understand how the work actually gets done.
So we created something called Agentic Pods.
The idea is simple.
We handpicked ~30 of our most AI-proficient engineers (people with deep knowledge of Uber's systems) and paired each of them with a domain expert from a business function.
Then we gave every pod just two weeks.
• Days 1 – 2: Shadow the expert. Observe every step. Document workflows. Ask questions. Build intuition.
• Day 3: Prioritize opportunities based on scale, repetition, business impact, and data availability.
• Days 4 – 5: Build a working agent alongside the person doing the job.
• Days 6 – 9: Validate with several others performing the same work. Does it generalize? Does it actually make their job better?
• Day 10: Ship.
In just the past two months, we've run 16 Agentic Pods across 16 different business functions.
• Capital allocation across 150 cities: 15 hours → 30 minutes.
• Financial pacing reports: 2 days → 10 minutes.
• Marketing web quality assurance: 2 weeks → 50 minutes.
• Support workflow creation: 9,000 manual workflows → self-service automation.
The productivity gains are impressive, but what surprised us most wasn't the speed.
• It was how quickly engineers embedded in unfamiliar domains uncovered opportunities that had been hiding in plain sight.
• The biggest wins rarely come from automating one task. They come from rethinking an entire workflow. Once you redesign the workflow around AI, you often eliminate handoffs, remove unnecessary approvals, replace legacy tooling, reduce vendor spend, and dramatically accelerate decision-making.
• The workflow becomes the unit of automation - not the individual task.
• The most impactful agent skills cut across teams, orgs, functions, tools, and systems.
The biggest lesson? The best AI opportunities are rarely visible from the outside.
You discover them by sitting next to the people doing the work, understanding every friction point, and building with them, not for them.
We're now forming a dedicated team to scale this further and go deeper. They'll deeply understand the work, redesign it from the ground up, and use AI to fundamentally change how the business operates.
It's exciting times!
English
Maggie's Refuel is a high-end gas station opening soon in LA that will offer freshly baked pastries, lattes on tap, pressed juice, and more.
Jordi: "Everything inside the modern gas station is trying to kill me. It's almost end-to-end, wall-to-wall poison."
Karine Hsu@karine_hsu
Maggie's Refuel, a new high-end gas station brand just opened in LA ~ "Maggie’s Refuel is a high-end convenience store brand planning to modernize and innovate the current gas station experience. Think Autogrill meets 7-Eleven Japan: matcha, local croissants, premium CPG, and yes, a soft-serve cone - all alongside a gas (or EV) fill-up."
English
@yoda @DylanAbruscato I once saw John Daly pound a beer, smoke a whole cig in 1 minute, then crush a drive 350 yards.
English
Whenever I see things like this, I’m reminded just how insane it was that we had 2.4M concurrent players on HQ Trivia
English
@ad0rnai @Madisonkanna @dexhorthy The way I would describe it: automating the full SDLC, with self improvement built in
English
Today @Madisonkanna and I talked with @dexhorthy about software factories, fighting slop, and why 3 AM incidents are essential for building intuition. An overview:
0:06 Conversations and themes at this year's conference
1:14 What is a software factory?
2:39 X vs. Twitter
2:56 Favorite open-source model
3:14 Solving AI slop, seeking leverage
5:28 Will models ever learn intuition?
English