Enables MCP clients to run fast, local, non-autoregressive System-1 decisions on text, including classification, triage, routing, and safety gating, via six typed tools with probabilistic outputs.
Provides MCP tools for AI agents to classify changes into autonomous or human review lanes, and to run shadow simulations over backlogs without shipping anything.
Enables coding agents to preflight MCP server submissions against store rejection causes, publish where automation is allowed, prepare form-based store submissions, and detect listing drift.
Enables MCP-capable coding agents to obtain structured TypeSafe Jev decisions on code, diffs, debugging hypotheses, test failures, and bug reports through six review and triage tools. It returns categorized verdicts, severities, and probabilities rather than explanations or patches, leaving verification to the connected agent.