--- schema: 1 type: video title: >- Context Graphs for Explainable, Decision-Aware AI Agents — Andreas Kollegger & Zaid Zaim, Neo4j description: >- Prescribing drug X is correct 99% of the time for symptom Y. For the 1% where it is fatal, statistical reasoning does not help you. Andreas Kollegger calls this reference class validation: before the agent acts, it has to know which group it is in. Context graphs give agents the why. Not just knowledge and tools but the policies, rules, and prior decisions that explain why a certain action is right in a given context. The decision making framework in this talk has five stages: frame the problem with its causality and environment, pull in global rules and past precedent, run a risk value analysis, either act or escalate to someone with authority, and write the full reasoning chain back into the graph. That last step is the point. Every decision becomes precedent. Future agents inherit it. Speaker info: - https://x.com/akollegger - https://www.linkedin.com/in/akollegger - https://github.com/akollegger --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/abvQEhvRI_c-context-graphs-for-explainable-decision-aware-ai-agents Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- canonical: 'https://liquidgold.cc/watch/abvQEhvRI_c' markdown: 'https://liquidgold.cc/watch/abvQEhvRI_c.md' llms: 'https://liquidgold.cc/watch/abvQEhvRI_c/llms.txt' parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T10:18:10.597Z' language: null children: [] videoId: abvQEhvRI_c durationSeconds: 999 publishedAt: '2026-05-28T14:00:18.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 25 endSeconds: 117 watch: 'https://liquidgold.cc/watch/abvQEhvRI_c?t=25' heldReason: rights - ordinal: 1 text: null startSeconds: 25 endSeconds: 117 watch: 'https://liquidgold.cc/watch/abvQEhvRI_c?t=25' heldReason: rights - ordinal: 2 text: null startSeconds: 129 endSeconds: 244 watch: 'https://liquidgold.cc/watch/abvQEhvRI_c?t=129' heldReason: rights - ordinal: 3 text: null startSeconds: 129 endSeconds: 244 watch: 'https://liquidgold.cc/watch/abvQEhvRI_c?t=129' heldReason: rights - ordinal: 4 text: null startSeconds: 256 endSeconds: 369 watch: 'https://liquidgold.cc/watch/abvQEhvRI_c?t=256' heldReason: rights - ordinal: 5 text: null startSeconds: 369 endSeconds: 381 watch: 'https://liquidgold.cc/watch/abvQEhvRI_c?t=369' heldReason: rights - ordinal: 6 text: null startSeconds: 381 endSeconds: 470 watch: 'https://liquidgold.cc/watch/abvQEhvRI_c?t=381' heldReason: rights - ordinal: 7 text: null startSeconds: 481 endSeconds: 566 watch: 'https://liquidgold.cc/watch/abvQEhvRI_c?t=481' heldReason: rights - ordinal: 8 text: null startSeconds: 578 endSeconds: 664 watch: 'https://liquidgold.cc/watch/abvQEhvRI_c?t=578' heldReason: rights - ordinal: 9 text: null startSeconds: 578 endSeconds: 664 watch: 'https://liquidgold.cc/watch/abvQEhvRI_c?t=578' heldReason: rights - ordinal: 10 text: null startSeconds: 674 endSeconds: 776 watch: 'https://liquidgold.cc/watch/abvQEhvRI_c?t=674' heldReason: rights - ordinal: 11 text: null startSeconds: 674 endSeconds: 776 watch: 'https://liquidgold.cc/watch/abvQEhvRI_c?t=674' heldReason: rights - ordinal: 12 text: null startSeconds: 776 endSeconds: 786 watch: 'https://liquidgold.cc/watch/abvQEhvRI_c?t=776' heldReason: rights - ordinal: 13 text: null startSeconds: 786 endSeconds: 907 watch: 'https://liquidgold.cc/watch/abvQEhvRI_c?t=786' heldReason: rights - ordinal: 14 text: null startSeconds: 907 endSeconds: 917 watch: 'https://liquidgold.cc/watch/abvQEhvRI_c?t=907' heldReason: rights --- # Context Graphs for Explainable, Decision-Aware AI Agents — Andreas Kollegger & Zaid Zaim, Neo4j Prescribing drug X is correct 99% of the time for symptom Y. For the 1% where it is fatal, statistical reasoning does not help you. Andreas Kollegger calls this reference class validation: before the agent acts, it has to know which group it is in. Context graphs give agents the why. Not just knowledge and tools but the policies, rules, and prior decisions that explain why a certain action is right in a given context. The decision making framework in this talk has five stages: frame the problem with its causality and environment, pull in global rules and past precedent, run a risk value analysis, either act or escalate to someone with authority, and write the full reasoning chain back into the graph. That last step is the point. Every decision becomes precedent. Future agents inherit it. Speaker info: - https://x.com/akollegger - https://www.linkedin.com/in/akollegger - https://github.com/akollegger --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/abvQEhvRI_c-context-graphs-for-explainable-decision-aware-ai-agents Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- Canonical: https://liquidgold.cc/watch/abvQEhvRI_c · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks > Missing: no stored document chunks are available.