Skip to content
All tags

#audit

2 posts
tech

Agent Platform Deep Dive (Part 6) — Observability, Evidence, and Artifacts: Structured Traces, Claim-to-Source Lineage, and Versioned Outputs

Observability is a first-class capability, not logging added after the fact: a structured trace connects FlowRun→StepRun→SkillInvocation→ProviderCall→ToolInvocation→GuardResult→EvidenceItem→ArtifactVersion. The Evidence Store traces every claim back to its source, excerpt, citation, confidence, and conflicts. Artifact versioning supports approve/reject/regenerate without deleting history. Context Snapshots allocate token budgets by category and record automatic compression when a block exceeds its budget. Procedural, episodic, and semantic memory can be written only through proposals reviewed by a human.

tech deep-dive

Building a Taiwan Stock Research Agent (Part 8): The Boundary Between Research and Paper Orders—Content-Addressed Execution Contracts

Three frozen Pydantic contracts weld the boundary between a research artifact and order-placement authority shut: content addressing, eight hard gates, and paper-only execution, while the agent never touches credentials.