$ cat glossary/
glossary/
the terms this site uses, defined in a sentence, each pointing at the essay that goes deep
- agent harness
- An agent harness is the execution scaffold around a language model: the tool-calling loop, the context plumbing, the sandboxing, the permissions, and the gates that decide what runs next.
- critic agent
- A critic agent reviews another agent's output for quality or correctness and returns non-binding advice instead of a binding verdict.
- gatekeeper agent
- A gatekeeper agent is an automated pipeline boundary check that issues a proceed, revise, or escalate verdict and halts the run on failure.
- harness engineering
- Harness engineering is the practice of designing and reshaping the scaffold an agent runs inside: where the gates sit, what each role is allowed to read, how work gets routed, and what happens when a check fails.
- multi-agent pipeline
- A multi-agent pipeline sequences distinct agent roles that pass artifacts forward through gated handoffs.
- orchestrator agent
- An orchestrator agent coordinates a multi-agent pipeline by triaging tasks, spawning specialists, tracking run state, and routing work between stages without performing specialist tasks itself.
- context engineering
- Context engineering is the practice of deciding what goes into a model's context window at runtime: what gets retrieved, what gets injected before the model reads anything, what gets compressed, and what stays out.
- run accounting
- Run accounting records the per-stage costs of one pipeline run, listing the model, tokens used, duration, and confidence in each value.