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
-
51 ↑31
You Can't Prompt the Room: The Last Skill AI Won't Replace - Balázs Horváth, VisualLabs
1.6K views 29 likes 1 comments
-
52 ↑31
Using RL Agent to Detect and Remediate ETL Pipeline Failures - Anna Marie Benzon
1.6K views 24 likes 0 comments
-
53 ↑31
Autonomous Agents for Scientific Tasks - Sina Shahandeh, Radicait
1.6K views 55 likes 3 comments
-
54 ↑31
The Prompt is the Platform - Dominik Tornow, Resonate HQ
1.6K views 43 likes 1 comments
-
55 ↑31
Chat and citations won't save your vertical AI - Atul Ramachandran, Filed Inc
1.6K views 57 likes 3 comments
-
56 ↑31
Browser Agents Don't Need Better Models. They Need Better Eyes. - Kushan Raj, ARK
1.6K views 47 likes 4 comments
-
57 ↑31
The Factory That Dreams: 39 AI Agents, No Framework - Rushabh Doshi, Machinecraft
1.6K views 27 likes 3 comments
-
58 ↑31
Semantic Blindness: 500,000 Sensors Confused an LLM - Raahul Singh & Vanč Levstik, Phaidra
1.6K views 31 likes 6 comments
-
59 ↑31
Stop Renting Your Cognitive Infrastructure - Thiyagarajan Maruthavanan, Kalmantic Labs
1.5K views 38 likes 0 comments
-
60 ↑31
Why Your Agent Disagrees With Itself (And What To Do About It) - Diane Lin, Datadog
1.5K views 37 likes 4 comments
-
61 ↑31
Your Agents Need a Save Button - Hamza Tahir, ZenML
1.4K views 30 likes 9 comments
-
62 ↑31
Skills are the New SDKs - Elvin Aghammadzada, DataRobot
1.4K views 33 likes 2 comments
-
63 ↑31
Voice In, Visuals Out: The Agony and the Ecstasy - Allen Pike, Forestwalk Labs
1.4K views 23 likes 6 comments
-
64 ↑32
A Song of Types and Agents - Roberto Stagi, Ratel
1.3K views 26 likes 0 comments
-
65 ↑32
SWE-Marathon: Evaluating Coding Agents at Billion-Token Scale - Rishi Desai, Abundant AI
1.3K views 41 likes 3 comments
-
66 ↑32
Agents Need Receipts, Not More Tool Calls - Armanas Povilionis, Alithea Bio
1.3K views 33 likes 6 comments
-
67 ↑32
The 100-Tool Agent Is a Trap - Sohail Shaikh & Ankush Rastogi, Prosodica
1.2K views 32 likes 1 comments
-
68 ↑33
The Miranda Hypothesis: How Hamilton Poisoned Persona Evals - Jacob E. Thomas, Results Gen
1.2K views 21 likes 1 comments
-
69 ↑31
OpenClaw in Your Hand: Building a Physical AI Terminal - Lech Kalinowski, Callstack
1.2K views 20 likes 1 comments
-
70 ↑32
AI-Driven Multi-Document Correlation for Financial Compliance - Varsha Shah, Independent
1.2K views 21 likes 1 comments
-
71 ↑32
Enterprise Agents Have a Structure Problem - Ishita Daga, Tesla
1.2K views 21 likes 3 comments
-
72 ↑32
Develop at Idea Velocity - Jeffrey Lee-Chan, Snapchat
1.2K views 14 likes 1 comments
-
73 ↑32
Stop Evaluating Models Like It's the 50s - Alejandro Vidal, Mindmakers
1.1K views 31 likes 0 comments
-
74 ↑32
Agents Need Feature Flags - Sachin Gupta
1K views 29 likes 1 comments
-
75 ↑32
From Tokens to Cells: Foundation Models for Single-Cell Biology - Akram Baharlouei, Altos Labs
1K views 30 likes 1 comments
