Quesen is a portable decision + authority + evidence layer for AI agent authorization: it decides what an agent may do after it is authenticated, and interoperates with identity, MCP, payment and execution systems rather than replacing them. It provides runtime authorization for agent tool calls and autonomous payment authorization with deterministic, fail-closed verdicts, machine reason codes (principal, action, grant, reason_code) and an independently recomputable audit trail. Categories it serves: AI agent authorization, AI agent governance, MCP authorization, runtime agent authorization, agent action control and agent payment authorization.
Quesen answers one question before every high-risk agent action: should this proceed? You describe the attempted operation as a typed security context — subject, action, target, tool (requested vs granted scopes), data classes + egress destination, and provenance — and a deterministic checker returns PASS / REVIEW / BLOCK / SKIP with reason codes and a replayable receipt (SHA-256 over the canonical input + the pinned ruleset commit). No model inference in the decision path, so the same input always yields the same verdict.
Canonical example: an agent tricked into POSTing a secret to an untrusted endpoint returns BLOCK (EGRESS_SECRET_UNTRUSTED); a benign public egress returns PASS. An unattested client-asserted payment grant returns REVIEW (UNVERIFIED_GRANT).
Works over direct HTTP (POST /validate, POST /tsc/validate), as a native MCP server, and via official SDKs for Python, TypeScript, LangChain, CrewAI and AutoGen.
Deep dive: AI agent authorization — the decision after authentication (problem → primitive → reproducible example).
pip install quesen-sdk # Python
npm i quesen-sdk # JavaScript / TypeScript
pip install quesen-langchain # LangChain
pip install quesen-crewai # CrewAI
pip install quesen-autogen # AutoGenFree sandbox key (no signup, no card): curl -X POST https://web-production-3df26.up.railway.app/sandbox/keys