The Hallway Track
19 tracked signals on ai-engineering.
Agentic AI's autonomous reasoning has driven compute demand 100-1000x higher, going 'parabolic,' says Jensen Huang.
“One engineer, a really good engineer today is working with an agent, but a really great engineer in the future is going to be orchestrating a whole bunch of agents who are going to be orchestrating a whole bunch of sub aents to do work.”
Impeccable's author shares hard-won lessons on engineering advanced agent skills beyond simple prompts.
“let's talk about the dark arts of skill engineering”
2026 survey of 1,048 AI engineers finds AI engineering is a discipline, not a job title
“the newest engineers have never known software without this”
AI engineering evals are fundamentally data science, and teams keep repeating avoidable eval mistakes.
“I'm saying that using LLM judges kind of blindly without validating your validators is bad.”
A skill checklist and shared rubric is needed to distinguish good agent skills from bad ones.
“Skill hell is where you have all of these skills available freely available that you can download, contribute to, you can figure out on your own, but you don't really know how the pieces all work together.”
Building production AI systems requires a four-phase framework—requirements, system design, evaluation, optimization—not just vibe coding.
“Specs are the new code. The art is in defining the product requirements, the system design, and evaluate criteria so you can be confident that your AI coding buddies are building the right thing.”
Building agentic systems requires the same engineering disciplines (systems thinking, workflow design) as pre-GenAI software development.
“When you're building agents, not just using them to write code, you start getting into architecting agentic systems.”
Developers building cost-efficient AI apps over-optimize the model instead of the end-to-end system and data access.
“developers get right into thinking about optimizing the model versus optimizing the system”
Evals are broken and often misleading, but engineers should still use them well in agentic workflows.
“evals are broken and you should use them anyway”
AI-written code is rising from ~10% today toward 40-50% by year-end, and AI is increasingly the harness, not just the model
“this is my argument around why AI engineering will be the last job, why you guys all have job security and why you guys will take over the world”
AI may become a general-purpose technology driving long-term productivity growth like the steam engine.
Practitioners debate whether AI agent loops live up to their hype in production software factories
Domain-specific agents will play a critical role in the future of how we build AI systems.
“agents are deterministic software that harness the non-deterministic results produced by models in pursuit of some desired objective”
Mutagent proposes an 'Agentic AI engineer' that automates the build-test-deploy-monitor loop for building AI agents at scale.
“the bottleneck basically becomes the human review and the human yeah, building time”
Two AI educators built an 'AI research OS' to turn 10,000+ scattered notes into a queryable personal research memory.
“I spent 18 months turning my second brain into my living research memory.”
Developers waste effort optimizing the model instead of the end-to-end system and data access.
“when AI has access to the right data, it spends more time reasoning and coming up with the right outcomes and higher quality outcomes”
Small improvements in AI accuracy can translate into outsized jumps in real-world usefulness and task coverage.
“small improvement accuracy somehow literally huge improvement in like usefulness”
AI Engineer World's Fair 2026 will be the largest AIE event ever, hosting roughly 600 attendees.
“we're expecting this to the largest AIE that we've ever had”
Swyx demos a vibe-coded internal scheduling app for his AI Engineer conference at Microsoft Build.
“It's basically sort of a binpacking problem where we have all these open slots.”