@aiDotEngineer

We gather the world's best AI engineers, leaders, founders, and researchers, and publish all their best work for free, through conferences and workshops. Help!

 https://ai.engineer
youtube.com/@aidotengineer
Joined March 2021
  • Tweets3.5K
  • Following103
  • Followers65.7K
896Media
First AIE Code Summit speakers: @poteto, Principal Engineer @ SpaceX @steve_yegge, Engineer, Writer, Advisor @zachbruggeman, Principal Software Engineer @ Ramp Nov 10-12, SF. Come hang out with us. Apply at ai.engineer/code
AI Engineer Code Summit speaker announcement featuring Lauren Tan, Principal Engineer at SpaceX; Steve Yegge, Engineer, Writer, Advisor, Independent; and Zach Bruggeman, Principal Software Engineer at Ramp. Black and white artwork with three speaker portraits and yellow text: November 10–12, SF. Apply at ai.engineer/code.

ALT AI Engineer Code Summit speaker announcement featuring Lauren Tan, Principal Engineer at SpaceX; Steve Yegge, Engineer, Writer, Advisor, Independent; and Zach Bruggeman, Principal Software Engineer at Ramp. Black and white artwork with three speaker portraits and yellow text: November 10–12, SF. Apply at ai.engineer/code.

13
25
9
323
588,668
AI Engineer 🔜 CODE Summit🌉 retweeted
Zach Lloyd
@zachlloydtweetsOct 16
Here's my take on what a software factory really is This is my talk from @aiDotEngineer NYC, and I decided to record a version for everyone to watch on X. tl;dr - software engineering is becoming factory engineering, and there's new work (especially factory benchmarking) that engineers should start focusing on.
28
55
13
766
75,257
AI Engineer 🔜 CODE Summit🌉 retweeted
Jai Bhagat
@ChaiWithJai8h
Today is very timely day for this talk from @mkanat at @aiDotEngineer - not SecOps related. But many folks will be wondering which workloads they can pause and stop… and what’s worth keeping around if we can just start fresh on many work streams. youtu.be/bU5gDVyu_28?is=N99q…

Does Code Quality Still Matter? It Depends on This — Max Kanat-Alexander, Capital One

Every senior engineer's answer is "it depends." Max Kanat-Alexander...

youtube.com
1
4
956
AI Engineer 🔜 CODE Summit🌉 retweeted
Max Kanat-Alexander
@mkanat16h
Does code quality even matter anymore? My keynote at @aiDotEngineer NYC 2026 just came out on YouTube: youtube.com/watch?v=bU5gDVyu…

Does Code Quality Still Matter? It Depends on This — Max Kanat-Alexander, Capital One

Every senior engineer's answer is "it depends." Max Kanat-Alexander...

youtube.com
1
1
10
1,229
AI Engineer 🔜 CODE Summit🌉 retweeted
Basis
@trybasis12h
"Nobody wants their agent to move 37 their tax return." @mitch_troy: review agent work like a PR. Blast radius, and how much you trust the author. "For agents to diffuse, they need to be simple. For teams to trust them, they need to be reliable." From @aiDotEngineer NYC.
1
2
24
3,934
Laptops open. Workshop day at AI Engineer New York, October 12. A few photos of the people on the other side of the podium. Photos by Ad Image.
Attendees sit at a workshop table with open laptops; one person types while others look toward the front of the room.

ALT Attendees sit at a workshop table with open laptops; one person types while others look toward the front of the room.

An attendee in a yellow top looks toward the workshop stage, seated among other participants with laptops open.

ALT An attendee in a yellow top looks toward the workshop stage, seated among other participants with laptops open.

An instructor speaks at a podium beside a presentation screen in a room of workshop participants with laptops.

ALT An instructor speaks at a podium beside a presentation screen in a room of workshop participants with laptops.

5
1,537
AI Engineer 🔜 CODE Summit🌉 retweeted
Rafael Pato
@rafpato17h
I’m gonna be in SF for a week and attend @aiDotEngineer ! Would love to connect IRL with some more people from here ✌🏼let me know if you’ll be around
1
1
6
755
Your agent's compute needs change mid-run. @akshat_b of @modal walks through CPU and memory demand in Ramp's sandboxes. Provisioning every sandbox for a brief peak can leave capacity reserved when it isn't needed. #AIEngineerNY
3
2
33
4,294
Your human evals need calibration too. @cwolferesearch explains the loop: define quality, have multiple people rate the same examples, then use their disagreements to improve the guidelines. #AIEngineerNY
2
1
14
1,941
AI Engineer 🔜 CODE Summit🌉 retweeted
Somi
@somi_aiOct 21
An agent Monzo built in-house now writes over 10% of their merged PRs. 1,800+ tasks a day. At a bank. Pretty sure Slack's the reason it spread. You just @ it in a thread like any coworker. Felipe Felisola Caso + Francesco Galletta of @monzo at @aiDotEngineer
1
6
967
AI Engineer 🔜 CODE Summit🌉 retweeted
Simular
@SimularAIOct 20
At the @aiDotEngineer World’s Fair, our CEO @angli_ai explored a future where one person could have a fleet of autonomous computers. That's what we are building with @sai_borg. your robosecretary. It starts with work you can reliably delegate to one computer. Then you start imagining what you could do with 10. Then 100. And Sai manages them for you. Build the thing you keep saving for someday #simular
2
4
1
13
1,614
Inside Grok Bot: is the agent harness dead? @jediahkatz of @SpaceXSI explains why smarter models let Cursor remove prompts and guardrails, and why Grok Bot is adding them back. Watch his AI Engineer New York talk: youtube.com/watch?v=7Y4sbZgB…
Jediah Katz holds a microphone in front of agent-harness diagrams and illustrated agents. The graphic reads "Is the Agent Harness Dead?" and carries AI Engineer New York and SpaceX logos.

ALT Jediah Katz holds a microphone in front of agent-harness diagrams and illustrated agents. The graphic reads "Is the Agent Harness Dead?" and carries AI Engineer New York and SpaceX logos.

5
7
9
87
34,143
Turn today's code reviews into tomorrow's agent context. @tommoor of @linear shares a daily loop: pull lessons from merged PRs and reverts into AGENTS.md or related docs. Keep the guidance concise. 78 seconds from AI Engineer New York. #AIEngineerNY
4
1
16
2,073
The full AI Engineer New York photo gallery is live. Workshop tables, whiteboard conversations and a few familiar faces. Find yourself: ai.engineer/nyc/2026/photos Photos by Ad Image. #AIEngineerNY
An attendee smiles and gestures while speaking with another attendee among rows of conference seats.

ALT An attendee smiles and gestures while speaking with another attendee among rows of conference seats.

A side view of a workshop room, with attendees working at open laptops and an instructor speaking at a podium.

ALT A side view of a workshop room, with attendees working at open laptops and an instructor speaking at a podium.

Three attendees pose behind large AIE letters in front of the event sponsor backdrop.

ALT Three attendees pose behind large AIE letters in front of the event sponsor backdrop.

Several attendees gather beside a booth’s whiteboard and laptop for a conversation.

ALT Several attendees gather beside a booth’s whiteboard and laptop for a conversation.

2
1
11
2,022
Fast vector search is only useful if the right documents survive filtering. Aaron Linsky explains Bridgewater's tradeoff between post-filtering and pre-filtering, and why the team switched to turbopuffer. 66 seconds from AI Engineer New York. #AIEngineerNY
2
3
13
2,098
What wakes your agent up? Aparna Dhinakaran of @ArizeAI walks through Signal's triggers, sandbox, proxy, traces and saved outputs. 78 seconds from AI Engineer New York. What should survive between runs? #AIEngineerNY
6
1
15
2,188
Six months building a data dictionary is AI engineering. So are evals that catch wrong business answers and permissions that limit what an agent can change. @sunyuzheng with Microsoft's Marco Casalaina, joining us at AIE Shanghai on Nov 5 and 6.
YZ | 立正
@sunyuzhengOct 16
BMW's test cars have 5,000 sensors. AI could query the data—but first came ~6 months building a data dictionary. My interview with Marco Casalaina of @Microsoft: youtu.be/KpQwWNkyEsQ He'll demo agent identity at @aiDotEngineer Shanghai, Nov 5–6. ai.engineer/shanghai/2026
2
2
10
2,605
How much of a large context window is actually useful? @steveonjava asks the question. Neeraj Deshmukh of Blitzy explains how code graphs connect dependencies and retain their source. 79 seconds from AI Engineer New York. #AIEngineerNY
2
3
10
2,122
Should every agent wait in the same approval queue? @jxxf contrasts a ticket summarizer with an agent that can deploy to production. One review process can delay small experiments and divide reviewers' attention. 77 seconds from AI Engineer New York. #AIEngineerNY
8
6
22
5,428
Load more