Neo4j talk: turn agent memory into a context graph, then distill it into skills
AI Engineer · youtube · 2026-10-09
A talk by Will Lyon, Senior Product Manager at Neo4j, at the AI Engineer World's Fair 2026 on turning agent memory into skills that actually work.
Core argument: agents finish a task and forget what they learned; memory built on embeddings and retrieval isn't enough — recall isn't actionable knowledge. Agents need knowledge that is connected, typed and traceable.
Context graph: Neo4j models agent memory as a context graph with short-term, long-term and reasoning memory, covering entity extraction and resolution, shared ontologies, and decision traces that let many agents learn from each other.
From memory to skills: Neo4j research treats skills as typed execution graphs, with checks for grounding, coverage and coherence, plus alerts when a skill goes stale — addressing the problem of unverifiable prose skills.
Demo: the Neo4j Agent Memory Service (NAMS) distills a patient-intake skill from a healthcare conversation, with skill composition and governance shown in the dashboard.
More from coding & agent
- Claude Code Pushes Urgent Security Update Across All Installations — umeshonai · 2026-10-23
- Claude cut a 2.6-hour video export to 20 minutes — but only after being told to rebuild the server — byhewar · 2026-10-23
- 3 flight-booking rules my AI agent checks that I'd never do by hand — Efistoffeles · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23