Tracing, Observability, and Evals for Agent Systems
A practical look at tracing, operator-facing observability, and trace-aware evals in the live harness-engineering demo after adding persisted trace summaries and lightweight eval fixtures.
term
AI Engineering
Human-in-the-Loop Done Properly
A practical look at human-in-the-loop design in the live harness-engineering demo: approval as explicit workflow state, not a chat courtesy, plus a new pending-action inspection surface for operators.
Memory Architecture for Agents: Context, Sessions, and State
A practical look at memory architecture in the live harness-engineering demo: separating working context, durable session state, and retrieval memory instead of calling everything memory.
Vector Databases Explained: History, Internals, and Why Agentic AI Depends on Them
A deep technical guide to vector databases: what they are, how they evolved, how they work internally, and how to use them with embeddings, RAG, and agents.
Durable Execution Is the Difference Between a Demo and a System
Checkpointing, approval-safe pause/resume, and replay-friendly run history are what turn an agent demo into an operational system. A practical look at the live harness-engineering repo after adding persisted run …
Orchestration Patterns: Loops, Graphs, Managers, and Handoffs
A practical look at orchestration patterns for agent systems, grounded in the live harness-engineering demo after adding workflow graph export for its approval-gated runner.
Tool Calling, Schemas, and the Rise of MCP
Function calling and MCP make tool interfaces more portable and legible, but they do not replace retries, approvals, state, tracing, or orchestration. A practical look at the live harness-engineering demo after adding an …
Agentic Harness Engineering White Paper
A comprehensive white paper on agentic harness engineering: the runtime, tooling, controls, evals, and governance patterns that make AI agents reliable in production.
Anatomy of an Agent Harness
A practical teardown of the live harness-engineering demo: runner, tool registry, persistent state, CLI surface, provider boundary, and traces—and why those parts matter more than agent theater.
Why Agentic Harness Engineering Matters More Than Prompt Engineering
Production-grade agent systems fail less because of clever prompts than because of the runtime around the model: typed tools, explicit workflow state, approvals, retries, traces, and resumable execution.
