What is Trace?

A correlated record of one request or task across model calls, retrieval, tools, state transitions, retries, approvals, and evaluations.

Why does Trace matter?

It lets you reconstruct where time, cost, and failure entered a multi-step workflow.

Propagate one trace identifier through the agent harness and attach redacted spans for each model and tool operation.

A trace should record operational evidence, not expose hidden model reasoning, secrets, or unredacted sensitive content.

Start with

OpenTelemetry GenAI Semantic Conventions
OpenTelemetry's GenAI SIG (launched April 2024) defines the standard schema for agent telemetry. Span names, attributes, and content-capture rules converge across vendors so agent traces mean the…
Phase 14: Agent Engineering

Lessons that name Trace in a title or section

Capstone: Stateless Tool Ecosystem
A production agent system is a set of boundaries, not a pile of features. This capstone separates a readable in-process simulation from the protocol clients, authorization server, sandbox, and…
Phase 13: Tools & Protocols
The Harness as a Library — Subagents and Session Store
A harness you can import: built-in tools, subagents for context isolation, hooks, W3C trace propagation, session persistence.
Phase 14: Agent Engineering
FinOps for LLMs — Unit Economics and Multi-Tenant Attribution
Traditional FinOps breaks on LLM spend. Costs are token-transactions, not resource-uptime. Tags don't map — an API call is a transaction, not an asset.
Phase 17: Infrastructure & Production

ObservabilityThe ability to understand an AI system's behavior from recorded inputs, outputs, state transitions, tool calls, timings, costs, errors,…
Agent StateThe explicit data an agent carries across steps, such as the current objective, completed actions, tool results, open questions, budgets,…
Time to First Token (TTFT)The elapsed time from submitting a generation request until the client receives the first output token or content event under a defined…
Evaluation (Eval)A defined process for measuring model or system behavior on representative tasks using explicit success criteria, data, scorers, and…
Audit LogA durable, access-controlled record of security- or accountability-relevant events, including who or what acted, what changed, when it…
Shadow TrafficA copy of live request traffic sent to a candidate system for observation while the candidate response remains outside the primary user…