AIE CODE 2025
Talks from AIE CODE 2025, drafted from the AI Engineer channel's own playlists. Editorial metadata is best-effort parsed and under review.
Event 1
-
1 —
Don't Build Agents, Build Skills Instead – Barry Zhang & Mahesh Murag, Anthropic
1.5M views 30K likes 606 comments
-
2 —
No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer
639.5K views 18K likes 424 comments
-
3 —
Claude Agent SDK [Full Workshop] — Thariq Shihipar, Anthropic
149.4K views 2.9K likes 151 comments
-
4 —
Defying Gravity - Kevin Hou, Google DeepMind
106K views 2.3K likes 92 comments
-
5 —
How Claude Code Works - Jared Zoneraich, PromptLayer
100K views 1.9K likes 59 comments
-
6 ↑3
Making Codebases Agent Ready – Eno Reyes, Factory AI
56.7K views 1.2K likes 48 comments
-
7 ↑3
Spec-Driven Development: Agentic Coding at FAANG Scale and Quality — Al Harris, Amazon Kiro
56.5K views 829 likes 18 comments
-
8 ↑4
Amp Code: Next Generation AI Coding – Beyang Liu, Amp Code
52.5K views 1.3K likes 43 comments
-
9 ↑4
DSPy: The End of Prompt Engineering - Kevin Madura, AlixPartners
49.6K views 886 likes 46 comments
-
10 ↑4
OpenAI + @Temporalio : Building Durable, Production Ready Agents - Cornelia Davis, Temporal
37.9K views 734 likes 42 comments
-
11 ↑9
Building Cursor Composer – Lee Robinson, Cursor
26.3K views 526 likes 28 comments
-
12 ↑11
Building Intelligent Research Agents with Manus - Ivan Leo, Manus AI (now Meta Superintelligence)
21.8K views 344 likes 24 comments
-
13 ↑11
Your MCP Server is Bad (and you should feel bad) - Jeremiah Lowin, Prefect
21.3K views 435 likes 29 comments
-
14 ↑11
Hard Won Lessons from Building Effective AI Coding Agents – Nik Pash, Cline
19.8K views 464 likes 45 comments
-
15 ↑14
RL Environments at Scale – Will Brown, Prime Intellect
14.6K views 328 likes 11 comments
-
16 ↑14
Code World Model: Building World Models for Computation – Jacob Kahn, FAIR Meta
14.3K views 329 likes 12 comments
-
17 ↑14
Build a Prompt Learning Loop - SallyAnn DeLucia & Fuad Ali, Arize
12.9K views 236 likes 27 comments
-
18 ↑14
Efficient Reinforcement Learning – Rhythm Garg & Linden Li, Applied Compute
12.3K views 300 likes 2 comments
-
19 ↑14
How METR measures Long Tasks and Experienced Open Source Dev Productivity - Joel Becker, METR
11.1K views 150 likes 10 comments
-
20 ↑14
Building durable Agents with Workflow DevKit & AI SDK - Peter Wielander, Vercel
9.1K views 134 likes 4 comments
-
21 ↑15
The 3 Pillars of Autonomy – Michele Catasta, Replit
8.5K views 150 likes 7 comments
-
22 ↑15
Why Agent Hype can fall short of reality – Joel Becker, METR
8.5K views 163 likes 6 comments
-
23 ↑15
Identity for AI Agents - Patrick Riley & Carlos Galan, Auth0
8.3K views 125 likes 5 comments
-
24 ↑19
Automating Large Scale Refactors with Parallel Agents - Robert Brennan, OpenHands
6.8K views 122 likes 10 comments
-
25 ↑19
AI Kernel Generation: What's working, what's not, what's next – Natalie Serrino, Gimlet Labs
6.4K views 159 likes 6 comments
