AI Native Engineers London Meetup #4
Hosted by
AI Native Engineers London
In-Person
Address available to attendees
Ready to join in on the fun?
Hi friends,
Our next AI for Engineers London Meetup is coming up on September 28! Join us for an evening of practical talks on AI engineering, where we'll explore how teams build, optimize, and experiment with modern AI systems—from making frontier models more affordable to the infrastructure behind coding agents.
🗣 Call for Proposals
Have an idea or story to share? Submit your talk proposal through our CFP form and take the stage at one of our upcoming meetups!
🕑 Event Schedule
18:00 - Doors open
18:30 - Intro and announcements
18:40 - Stop Paying for Frontier Models - RL Nabors
19:05 - Building a UI That Builds Itself - Alexey Taktarov
19:35 - Open Mic talks - show your project, open source work or a small demo of what you learned recently
Mingle until 21:00
🤝 Organized by
This event made possible thanks to the support from AI Coding Summit organizers – GitNation
🤝 Hosted by
Kudos to our friends BNY!
BNY is a global financial services platforms company at the heart of the world's capital markets. For more than 240 years BNY has partnered alongside clients, using its expertise and platforms to help them operate more efficiently and accelerate growth. Today BNY serves over 90% of Fortune 100 companies and nearly all the top 100 banks globally. BNY supports governments in funding local projects and works with over 90% of the top 100 pension plans to safeguard investments for millions of individuals. As of June 30, 2026, BNY oversees $62.6 trillion in assets under custody and/or administration and $2.2 trillion in assets under management
📸 Photography & Video Notice
Please note that photography and video recording will take place during this event. By registering and attending, you acknowledge and agree that your image, voice, and likeness may be captured and used by BNY and GitNation for promotional, marketing and communications purposes, in accordance with the event Photo Release.
👍 Code of Conduct
By registering for this event you agree to comply with our CoC
📩 Contact
events@gitnation.org
Presentations
Rachel Nabors
Stop Paying for Frontier Models
Most of use reach for a frontier model by default and pay for it on every call, in latency, in energy, in cash, and in everything that leaves their stack. For most of those calls, a small local model would do the job.
RL Nabors, former Meta/React core team member and AWS alum, covers the vocabulary you need to reason about model performance (capability evals, golden datasets, LLM-as-judge) and walks through real cases: a local agentic harness replacing a frontier call, an in-browser moderation classifier defended with production-trace evals, and a generative summarization feature where the rubric turns out to be harder than the model. You'll leave with a framework for deciding when to choose large and off-prem or small and local models, and how to measure your way to the answer instead of guessing.
You will learn:
- The vocabulary to reason about model performance (capability evals, golden datasets, LLM-as-judge).
- A framework for deciding when a small or local model can replace a frontier one and when it can't.
- A repeatable process for building capability evals from your own production traces, not someone else's benchmark.
- Working examples of using eval results to iterate on prompts and ship with confidence instead of vibes.
Alexey Taktarov
Building a UI That Builds Itself
What if an AI agent could customize its own UI outside the chat and update it on the fly? As humans, some tasks that we work on are better done visually than in text format. That's why I started this experiment, where I give an agent a skill and teach it how to work in a highly visual workspace it can extend and update with custom UIs. I'll walk you through how we designed a skill, a CLI, and a front-end app that work in tandem to make it possible. How we spent weeks figuring out the best and most minimal design system an agent can use to generate "slop-free" designs. The project is completely open-sourced and available on https://moi.computer/
Platform Sponsors
Supercharge your dev team with AI code reviews
Get your free trial now
Torc is a community-first platform bringing together remote-first software engineer and developer opportunities from across the globe. Join a network that’s all about connection, collaboration, and finding your next big move — together.
Join our community today!
Ready to join in on the fun?
Platform Sponsors
Supercharge your dev team with AI code reviews
Get your free trial now
Torc is a community-first platform bringing together remote-first software engineer and developer opportunities from across the globe. Join a network that’s all about connection, collaboration, and finding your next big move — together.
Join our community today!
AI Native Engineers London Meetup #4
Hosted by
AI Native Engineers London
In-Person
Address available to attendees
Hi friends,
Our next AI for Engineers London Meetup is coming up on September 28! Join us for an evening of practical talks on AI engineering, where we'll explore how teams build, optimize, and experiment with modern AI systems—from making frontier models more affordable to the infrastructure behind coding agents.
🗣 Call for Proposals
Have an idea or story to share? Submit your talk proposal through our CFP form and take the stage at one of our upcoming meetups!
🕑 Event Schedule
18:00 - Doors open
18:30 - Intro and announcements
18:40 - Stop Paying for Frontier Models - RL Nabors
19:05 - Building a UI That Builds Itself - Alexey Taktarov
19:35 - Open Mic talks - show your project, open source work or a small demo of what you learned recently
Mingle until 21:00
🤝 Organized by
This event made possible thanks to the support from AI Coding Summit organizers – GitNation
🤝 Hosted by
Kudos to our friends BNY!
BNY is a global financial services platforms company at the heart of the world's capital markets. For more than 240 years BNY has partnered alongside clients, using its expertise and platforms to help them operate more efficiently and accelerate growth. Today BNY serves over 90% of Fortune 100 companies and nearly all the top 100 banks globally. BNY supports governments in funding local projects and works with over 90% of the top 100 pension plans to safeguard investments for millions of individuals. As of June 30, 2026, BNY oversees $62.6 trillion in assets under custody and/or administration and $2.2 trillion in assets under management
📸 Photography & Video Notice
Please note that photography and video recording will take place during this event. By registering and attending, you acknowledge and agree that your image, voice, and likeness may be captured and used by BNY and GitNation for promotional, marketing and communications purposes, in accordance with the event Photo Release.
👍 Code of Conduct
By registering for this event you agree to comply with our CoC
📩 Contact
events@gitnation.org
Presentations
Rachel Nabors
Stop Paying for Frontier Models
Most of use reach for a frontier model by default and pay for it on every call, in latency, in energy, in cash, and in everything that leaves their stack. For most of those calls, a small local model would do the job.
RL Nabors, former Meta/React core team member and AWS alum, covers the vocabulary you need to reason about model performance (capability evals, golden datasets, LLM-as-judge) and walks through real cases: a local agentic harness replacing a frontier call, an in-browser moderation classifier defended with production-trace evals, and a generative summarization feature where the rubric turns out to be harder than the model. You'll leave with a framework for deciding when to choose large and off-prem or small and local models, and how to measure your way to the answer instead of guessing.
You will learn:
- The vocabulary to reason about model performance (capability evals, golden datasets, LLM-as-judge).
- A framework for deciding when a small or local model can replace a frontier one and when it can't.
- A repeatable process for building capability evals from your own production traces, not someone else's benchmark.
- Working examples of using eval results to iterate on prompts and ship with confidence instead of vibes.
Alexey Taktarov
Building a UI That Builds Itself
What if an AI agent could customize its own UI outside the chat and update it on the fly? As humans, some tasks that we work on are better done visually than in text format. That's why I started this experiment, where I give an agent a skill and teach it how to work in a highly visual workspace it can extend and update with custom UIs. I'll walk you through how we designed a skill, a CLI, and a front-end app that work in tandem to make it possible. How we spent weeks figuring out the best and most minimal design system an agent can use to generate "slop-free" designs. The project is completely open-sourced and available on https://moi.computer/
Get in touch!
hi@guild.host