Send branch evidence
Progress signals, verified artifacts, cost, tool calls, risk events, authorization budget, and the pinned policy reference.
A live x402 runtime checkpoint API for autonomous agents that need external continue, stop, prune, abstain, or escalate decisions with verifiable execution receipts. The paid endpoint now issues x402 Payment Required challenges for real USDC settlement on Base mainnet.
Internal self-checks share the same context and incentives as the branch they judge. Agent Decision Gate supplies an independent policy boundary and a receipt another runtime can verify.
Progress signals, verified artifacts, cost, tool calls, risk events, authorization budget, and the pinned policy reference.
Continue, prune, stop, abstain, or escalate, plus reason codes and remediation that a calling agent can execute directly.
Persist the canonical request, decision, policy, and receipt with a public integrity view and branch-chain verification.
Start with one paid evaluation endpoint. Discovery, pricing, examples, and verification remain free machine-readable surfaces.
/v1/branches/evaluatePaid x402 live endpoint. Returns 402 with PAYMENT-REQUIRED until a valid Base mainnet payment signature is supplied.
/v1/receipts/verifyRecompute receipt integrity and, when stored, verify the D1 registration, R2 payload, and previous chain link.
/.well-known/agent.jsonCanonical machine entry point with absolute links, capabilities, trust boundaries, and integration routes.
/v1/openapi.jsonOpenAPI 3.1 contract for tool generation, autonomous integration, request validation, and endpoint discovery.
The service repeats concrete task language in public machine-readable routes, so an agent can find it by intent and decide whether it is worth calling.
agent runtime checkpointUse when an agent needs an outside decision before continuing an expensive branch.
agent branch evaluation APIUse when the runtime needs continue, prune, stop, abstain, or escalate.
agent execution receipt APIUse when another agent or operator needs a portable receipt for a branch decision.
agent claim audit APIUse before promoting claims that may exceed the available evidence.
agent payment guardrailUse before tool calls, wallet actions, or spend that needs authorization context.
chain of evidence APIUse as a narrow checkpoint inside verifiable autonomous research workflows.
A returned receipt is not just evidence of a past decision. It becomes the handle for the next checkpoint when the same run and branch continue.
Call /v1/branches/evaluate with previous_receipt_hash: null and store the returned receipt integrity hash.
For the same run_id and branch_id, submit the last receipt.integrity_hash as previous_receipt_hash.
Use /v1/recurring-checkpoints, receipt lookup, and receipt verification to keep a portable execution audit chain.
The service makes narrow, testable claims. That boundary is part of the product, not a disclaimer hidden after the fact.
Agents can inspect the service, generate a client from OpenAPI, receive an x402 payment challenge, and verify returned receipts using public routes.
$ curl https://agentdecisiongate.com/.well-known/agent.json $ curl https://agentdecisiongate.com/v1/openapi.json $ curl https://agentdecisiongate.com/v1/pricing $ curl https://agentdecisiongate.com/health