The glossary.
The agent-replay vocabulary, defined in plain language. Every entry opens with a one-paragraph canonical definition you can quote, states the boundary the tool can't cross, and shows a real replay receipt — verbatim output, never a mockup.
Deterministic replay
Deterministic replay is the practice of re-running an AI agent's recorded work without re-running the model.
Agent drift
Agent drift is the unplanned change in an AI agent's behavior across runs of the same job: the instructions stay the same, but the agent's routing, tool use, or output diverges from the workflow it was trusted to run — pushed by model updates, shifting context, accumulated memory, or a world that changed under the agent's assumptions.
Run receipt
A run receipt is a per-run audit trail for an AI agent workflow: a machine-checkable record, written at the end of each run by the harness that executed the calls, of what actually ran — every step with its outcome against an explicit assertion, its timing, and the run's measured LLM token count.
Level-0 (zero-token) replay
Level-0 (zero-token) replay is the default mode of deterministic replay, in which an AI agent's recorded tool calls are re-executed with no model in the loop: the LLM client is never constructed, never called, and never billed, so the run costs exactly zero tokens by construction.
Snapshot testing for AI agents
Snapshot testing for AI agents is the practice of recording a known-good agent run — the ordered tool calls it made, with their arguments and results — as a committed baseline, then comparing every later run against that baseline and failing loudly when they diverge.
Session-to-skill (skill compilation)
Session-to-skill extraction — skill compilation, in Reelier's vocabulary — is the practice of turning a finished agent session into a reusable skill: the transcript of what the agent did is parsed, the repeatable tool calls are lifted out, and the result is compiled into a standalone artifact, typically a SKILL.md file, that can be reviewed, versioned, and run again without re-deriving the plan.
Recording MCP tool calls
Recording MCP tool calls is the practice of capturing every tool call an AI agent makes over the Model Context Protocol — the typed JSON request and the typed result, in order — into a durable trace file while the job runs once as usual.
Regression testing for AI agents
Regression testing for AI agents is the practice of re-verifying an agent's established behavior after something changes — a model version, a prompt edit, a tool schema, an upstream API — so a job that worked last week is proven to still work now instead of assumed to.
Idempotent write gating
Idempotent write gating is a safety policy for re-running an AI agent's recorded work: every tool call is classified by its side effect — read, idempotent write (an operation that converges when retried, like a PUT or an upsert), or destructive (one that compounds, like a send or a charge) — and on re-execution only reads fire by default.
Assertion grammar for agent outputs
An assertion grammar is the small, fixed language a replay tool uses to check an AI agent's outputs mechanically: pass/fail predicates evaluated against the typed responses the agent's tool calls return, never against its prose.
Agent memory vs deterministic replay
Agent memory and deterministic replay both carry an AI agent's past work into its next run — which is where the confusion between them starts.
Headless agent
A headless AI agent is an agent that runs without a user interface: no chat window, no person watching the run, no one to ask mid-task.