AIE Europe 2026
Talks from AIE Europe 2026, drafted from the AI Engineer channel's own playlists. Editorial metadata is best-effort parsed and under review.
Event 1
-
76 —
Why your agents need decision traces, not just documents — Zach Blumenfeld, Neo4j
11.7K views 228 likes 12 comments
-
77 —
Agents on the Canvas in tldraw — Steve Ruiz, tldraw
11.5K views 236 likes 14 comments
-
78 —
Malleable Evals: Why Are We Evaluating Adaptive Systems with Static Tests? — Vincent Koc, OpenClaw
11.2K views 163 likes 21 comments
-
79 —
I Gave an AI Agent the Keys to My Life (Here's What Happened) — Radek Sienkiewicz (@velvetshark-com)
11.2K views 213 likes 17 comments
-
80 —
Combine Skills and MCP to Close the Context Gap — Pedro Rodrigues, Supabase
10.9K views 213 likes 2 comments
-
81 —
Fast Models Need Slow Developers — Sarah Chieng, Cerebras
10.4K views 234 likes 23 comments
-
82 —
Taste & Craft: A Conversation with Tuomas Artman, CTO Linear & Gergely Orosz, @pragmaticengineer
10.3K views 150 likes 9 comments
-
83 —
The End of Apps — Kitze, Sizzy.co
10.2K views 286 likes 19 comments
-
84 —
Why TTS Models Now Look Like LLMs — Samuel Humeau, Mistral
10.2K views 266 likes 9 comments
-
85 —
Building a Chess Coach — Anant Dole and Asbjorn Steinskog, Take Take Take
10.2K views 277 likes 21 comments
-
86 —
Skill Issue: How We Used AI to Make Agents Actually Good at Supabase — Pedro Rodrigues, Supabase
10.1K views 175 likes 11 comments
-
87 —
Don't Build Slop (4 Levels of AI Agent Maturity) - Ara Khan, Cline
9.9K views 178 likes 4 comments
-
88 —
Code Mode: Let the Code do the Talking - Sunil Pai, Cloudflare
9.8K views 222 likes 8 comments
-
89 —
Building Agent Interfaces: Lessons from Chrome DevTools (MCP) for Agents — Michael Hablich, Google
9.4K views 144 likes 1 comments
-
90 —
Vibe Engineering Effect Apps — Michael Arnaldi, Effectful
9.4K views 193 likes 9 comments
-
91 —
Why Eval++ Is the Next Great Compute Primitive — Sunil Pai & Matt Carey, Cloudflare
9.3K views 178 likes 14 comments
-
92 —
What Do Models Still Suck At? - Peter Gostev, Arena.ai, BullshitBench
9.1K views 204 likes 12 comments
-
93 —
Why building eval platforms is hard — Phil Hetzel, Braintrust
9.1K views 191 likes 7 comments
-
94 —
Beyond Code Coverage: Functionality Testing with Playwright MCP — Marlene Mhangami, Microsoft
9K views 238 likes 18 comments
-
95 —
Skill issue: Lessons from skilling up coding agents to use Langfuse - Marc Klingen, Clickhouse
8.8K views 168 likes 3 comments
-
96 —
Building Interactive UIs in VS Code with MCP Apps — Marlene Mhangami & Liam Hampton, GitHub
8.7K views 162 likes 5 comments
-
97 —
AIE Miami Day 2 ft. Cerebras, OpenCode, Cursor, Arize AI, and more!
8.6K views 129 likes 4 comments
-
98 —
Why More Context Makes Your Agent Dumber and What to Do About It — Nupur Sharma, Qodo
8.4K views 131 likes 8 comments
-
99 —
Why Can't Anyone Answer Questions About the Business? — Garrett Galow, WorkOS
8.3K views 129 likes 1 comments
-
100 —
Two Roads to Durable Agents: Replay vs. Snapshot — Eric Allam, CEO, Trigger.dev
8K views 160 likes 15 comments
