AI Engineer World's Fair 2026
Talks from AI Engineer World's Fair 2026, drafted from the AI Engineer channel's own playlists. Editorial metadata is best-effort parsed and under review.
Event 1
-
201 ↓7
The UX of AI: Making AI-Powered Apps Your Users Don't Hate - Kathryn Grayson Nanz, Progress Software
4.2K views 127 likes 13 comments
-
202
Are LLM Performance Benchmarks Reliable? — Ashok Chandrasekar & Jason Kramberger, Google
4.2K views 12 likes 0 comments
-
203 ↓8
Your AI Product Will Fail Unless You Can Explain It - Veronica Hylak, Hey AI
4.1K views 213 likes 17 comments
-
204 ↓8
Deterministic Infra for Non-Deterministic AI Agents - Nishant Gupta, Meta Superintelligence Labs
4.1K views 80 likes 10 comments
-
205 ↓8
Building GTM AI Agents: Lessons from Deploying to 6,000 Users — Sait Izmit, Snowflake
4K views 64 likes 1 comments
-
206 ↑161
Operating Distributed Inference Systems at Scale — Nishant Gupta & Naman Ahuja, Meta
4K views 22 likes 1 comments
-
207 ↓9
From Agent Traces to Agent Simulations — Rustem Feyzkhanov, Snorkel AI
3.9K views 69 likes 2 comments
-
208 ↓9
Evals-Driven Development for a Mental Health AI Coach — Akele Reed & Dave Revere, SonderMind
3.9K views 95 likes 7 comments
-
209 ↓9
Building Agents Is Trivial Now, Context Is the Next Frontier — Jeff Ng, Unblocked
3.9K views 71 likes 8 comments
-
210 ↓9
Stop AI Agent Hallucinations: 5 Techniques + Production Patterns - Elizabeth Fuentes, AWS
3.8K views 112 likes 15 comments
-
211 ↓8
The Desktop Frontier — Ahmad Osman, Osmantic
3.8K views 84 likes 6 comments
-
212 ↓10
Continual Learning for AI Agents: From Failures to Durable Improvements - Soheil Feizi, RELAI
3.8K views 83 likes 3 comments
-
213 ↓9
The Future of Evals: From LLM as a Judge to Agent as a Judge — Aparna Dhinakaran, Arize AI
3.7K views 74 likes 3 comments
-
214 ↓9
Multiplayer agentic engineering — Arjun Singh, Superconductor
3.7K views 19 likes 2 comments
-
215 ↓9
The Missing Layer: Design Taste in AI Agents — Hassan El Mghari, Together AI
3.7K views 81 likes 5 comments
-
216 ↓9
SimulationMaxxing: How we ship agents 20× faster — Aman Gupta (Nubank) + Shreya Rajpal (Snowglobe)
3.7K views 78 likes 3 comments
-
217 ↓9
AI Agents for Performance: Ship Faster, Pay Less — Rajat Shah, Netflix
3.7K views 69 likes 1 comments
-
218 ↓9
DeepSWE: A Contamination-Resistant Coding Benchmark — James Shi, Datacurve
3.6K views 71 likes 8 comments
-
219 ↓9
The Last Human Code Review: Building Trust in AI-Generated Code — Itamar Friedman, Qodo
3.6K views 64 likes 6 comments
-
220 ↓8
The State of Model Routing — NVIDIA, Cognition, OpenRouter
3.5K views 19 likes 7 comments
-
221 ↓10
RLM: Recursive Language Models for Large Codebases - Shashi, Superagentic AI
3.5K views 72 likes 2 comments
-
222 ↓9
Benchmarking Coding Agents on New vs Legacy Codebases — Denys Linkov, Wisedocs
3.3K views 45 likes 6 comments
-
223 ↓9
How Autoresearch is changing ML research — Zhengyao Jiang, Weco
3.3K views 74 likes 1 comments
-
224 ↓9
Your Finance Agent's Bottleneck Is You — Ramana Siddanth Emani, Auditoria AI
3.2K views 56 likes 3 comments
-
225 ↓9
Lessons from Studying Every Memory System — Shlok Khemani, Independent
3.2K views 99 likes 4 comments
