reelier.com / learn

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.

glossary·4 sections·✓ real receipt

Deterministic replay

Deterministic replay is the practice of re-running an AI agent's recorded work without re-running the model.

/learn/deterministic-replay
glossary·4 sections·✓ real receipt

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.

/learn/tool-call-drift
glossary·4 sections·✓ real receipt

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.

/learn/run-receipt
glossary·3 sections·✓ real receipt

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.

/learn/level-0-replay
glossary·4 sections·✓ real receipt

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.

/learn/agent-snapshot-testing
glossary·3 sections·✓ real receipt

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.

/learn/skill-compilation
glossary·4 sections·✓ real receipt

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.

/learn/mcp-recording
glossary·4 sections·✓ real receipt

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.

/learn/agent-regression-testing
glossary·4 sections·✓ real receipt

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.

/learn/idempotent-write-gating
glossary·3 sections·✓ real receipt

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.

/learn/assertion-grammar
glossary·3 sections·✓ real receipt

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.

/learn/agent-memory-vs-replay
glossary·4 sections·✓ real receipt

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.

/learn/headless-agent
Reading as an agent? Every term has a raw-markdown twin at /learn/<slug>/md — same data, same renderer, so the two surfaces can't drift. Setup guides live under /for; the receipts these pages talk about are on the replay portfolio and the replay ledger.