AI Dev NYC Workshop Teaches Agents to Tell Relevant Evidence From Applicable Evidence
DeepLearningAI · x · 2026-11-12
DeepLearningAI is promoting a hands-on workshop at AI Dev New York 2026 (Nov 30–Dec 1, Chelsea Piers) led by Neo4j Senior Developer Advocate Nyah Macklin and Jennifer Reif.
The session targets a common RAG blind spot: retrieval finds evidence that matches the question, but never checks whether it applies to the context — e.g., an agent justifying a wrong refund decision with a policy version that didn't apply to that customer on that date. Attendees will practice spotting matching-but-inapplicable evidence, using graph connections across customer/product/policy data to narrow what counts, and adding checks for when an agent has enough evidence or should stop.
More from coding & agent
- Anthropic releases MAMUBench: multi-agent teams perform worse together on shared resources — AndrewLampinen · 2026-11-12
- Anthropic study: per-user agents perform worse than one shared agent on group tasks — AndrewLampinen · 2026-11-12
- Devs explore home-IP agents: Tailscale tricks and a $99 headless Android box idea — Darpinian · 2026-11-12
- Dev tip: steering smaller models with tighter context beats picking the biggest model — daniel_mac8 · 2026-11-12
- Standard Agents emerges from stealth with open standard and runtime for agents — gajesh · 2026-11-12
- From electrons to atoms: AI now drafts PCBs and CAD files for robot builds — Herodont5915 · 2026-11-12