Documentation / WagerCall v0
Understand the environment before evaluating the agent.
Learn the WagerCall model from first action to canonical record. These documents explain version identity, reproducibility, evidence boundaries, and reliable MCP behavior without substituting a built-in score for evaluator judgment.
Start with the first workflowSix deep references
Read by task or follow the sequence.
Each page begins with a concrete outcome and keeps the essential explanation visible.
Documentation
Run a first inspectable agent workflow.
A WagerCall workflow is a short loop: choose a versioned environment, read its contract, act through the authoritative server, and inspect the resulting evidence. Start with the concepts before automating repeated trials.
Documentation
How WagerCall turns decisions into evidence.
WagerCall separates pure game rules from application authority and persistence. That boundary keeps an agent's observable choices understandable without moving randomness, authorization, or accounting into the client.
Documentation
Design a controlled agent evaluation workflow.
WagerCall supplies environments and evidence, while the evaluator owns the question, experimental controls, repetitions, and interpretation. A useful workflow states those choices before the first run.
Documentation
Know exactly what a reproducible Session means.
Deterministic mode fixes how WagerCall constructs an environment. It does not force an AI agent to be deterministic, and it does not make unlike action trajectories directly equivalent.
Documentation
Read canonical replay without overclaiming it.
A WagerCall Session record orders the evidence needed to inspect an authoritative transition. Replay can reconstruct what the engine produced; it cannot reveal an agent's hidden reasoning or certify a broad conclusion.
Documentation
Test how an agent behaves through MCP.
WagerCall's strict ten-tool contract creates observable tests for discovery, schema use, legal-action selection, optimistic concurrency, idempotency, and recovery. This is product-specific behavioral evaluation, not general MCP protocol conformance.
Prefer a checklist?
Move from concepts to practical guides.
Apply the documentation to comparisons, Session review, and MCP client testing.