Crew

Why your agents need decision traces, not just documents — Zach Blumenfeld, Neo4j

May 29, 2026 · 20:12

Zach Blumenfeld from Neo4j argues that context graphs—a graph-based layer storing decision traces, precedence, and causal chains—extend standard RAG to make AI agents more accurate and explainable. A financial analyst agent, for example, can reject or accept a request by retrieving past decision traces and structurally similar precedents via graph embeddings, not just semantic similarity. Neo4j's one-command tool `uvx create-context-graph` scaffolds a full-stack app with backend, frontend, demo data, and MCP server, supporting 22 built-in domains or custom ontology generation. The underlying `neo4j-agent-memory` package handles entity extraction through a spaCy-to-GLiNER-to-LLM pipeline with deduplication and integrates with pydantic AI, LangGraph, Crew, Google ADK, and others. The episode also covers data connectors for GitHub, Notion, Jira, and Slack, and the ability to store and query decision traces with timestamps, though automated trace quality evaluation is still evolving.

Two Roads to Durable Agents: Replay vs. Snapshot — Eric Allam, CEO, Trigger.dev

May 10, 2026 · 16:36

Eric Allam, CEO of Trigger.dev, argues that durable agents require two separate strategies: context durability via an append-only log of LLM interactions, and execution durability via OS-level snapshot and restore. He contrasts this with the replay model, which wraps every step in a journal but becomes unwieldy as agents run for hours. Trigger.dev built snapshot-and-restore on Firecracker microVMs, achieving snapshots as small as 14 MB compressed with sub-second save and hundred-millisecond restore times. The approach preserves files, memory, and subprocesses that a journal cannot capture. Allam notes that IBM mainframes in 1966 pioneered checkpointing, and that Trigger.dev will open-source the tool as FCRun.