ProcureGraph

Autonomous procurement for AI workloads — agents buy evidence before they buy services.

ProcureGraph is the layer that makes it safe for an AI agent to spend a company's money on outside vendors. It buys evidence before it buys services, it lets deterministic code — never the language model — decide who gets paid, and it proves every dollar on a tamper-evident ledger.

The governing principle

The model proposes; deterministic code decides; the payment rail executes. The LLM never computes money and never holds a credential.

Two separate jobs, and neither is ever done by the model:

• Who is best? → a deterministic tournament scores vendors on measured evidence.
• Who is allowed? → a deterministic policy engine enforces the mandate's rules.

A bad vendor loses the tournament; a malicious action hits the policy wall.

How a mission runs

1. A mandate defines the outcome and the budget.
2. The agent buys evidence — paying vendors cent-sized fees to be measured on a real task.
3. It selects the winner by arithmetic on those measurements.
4. It pays on a scoped, single-use credential.
5. It verifies the delivered outcome on a held-out sample.
6. It reconciles every cent to a mandate, a vendor, a receipt, and a transaction.

Where to go next

• Product Overview — the complete what, why, and how.
• Architecture — clean architecture, DDD, and the durable state machine.
• System Diagrams — components, the mission graph, sequences, domain classes, and the data model.
• Guardrails & Policy — the deterministic gate and the trust model.

Foundations

• Python 3.12 · FastAPI · LangGraph · PostgreSQL 16 · React + Vite + TypeScript · Docker.
• Two payment rails: x402 micropayments on Monad, and a Rain scoped virtual card.
• Full observability: OpenTelemetry, self-hosted Langfuse, and a hash-chained evidence ledger. 100% branch coverage on authored code.