-
-
AgentPass landing page highlighting intent-based spend governance and PayPal sandbox integration.
-
Operator account creation screen for setting up scoped API keys and spending policies.
-
Main governance overview dashboard monitoring active agents, commitments, and audit events.
-
Modal dialog for registering an autonomous AI agent with custom framework and model selection.
-
Agent registry showing active or killed operational status and scoped execution capabilities.
-
Permissions and spend controls panel configured with transaction limits and blocklists.
-
Intent verification engine catching constraint conflicts on a simulated agent purchase.
-
Human-in-the-loop approval queue for reviewing flagged transactions exceeding thresholds.
-
Multi-agent delegation hierarchy managing scoped budget subsets and authorization graphs.
-
Transaction ledger tracking authorized holds and PayPal sandbox settlements chronologically.
-
Emergency circuit breaker to instantly revoke agent credentials and freeze active orders.
-
Tamper-evident, hash-verified SHA-256 compliance log tracking all policy events.
-
Real-time spend velocity, intent match rates, and interactive risk scoring simulator.
-
Operator profile management, Argon2id credentials, and secure PayPal sandbox rails.
AgentPass: Autonomous AI Finance Governance and Intent Firewall
Inspiration
As autonomous AI agents (built on frameworks such as CrewAI and powered by models such as Gemini 2.0 Flash) evolve from passive assistants to active economic actors capable of making purchases and executing workflows, a massive security gap emerges. Without strict financial guardrails, LLM agents are vulnerable to prompt injection, hallucinated checkouts and runaway spending. AgentPass was built to solve this, as a microsecond policy enforcement and semantic intent firewall between autonomous agents and financial rails like PayPal Sandbox.
What It Does
AgentPass is the full admin control plane + execution gateway for AI commerce autonomy:Agent Registry & Scoped Credentials: API keys scoped agp_live_ with capabilities ecommerce:search and ecommerce:purchase.
Deterministic Spend Controls: Enforces hard limits including Max Per-Transaction, Daily Spend Ceilings, Monthly Budgets and Human Approval Thresholds.
Semantic Intent Verification: Converts natural language user instructions into positive priorities and negative constraints, so that conflicting purchases are avoided (e.g. blocking gaming laptops when college portability is needed).
Multi-Agent Delegations: . Supports parent-child authorization graphs (detects cycles, budget limits on subsets).
Emergency Circuit Breakers: Features a Kill Switch to immediately remove financial permissions from individual agents or the entire platform.
Tamper-Evident Audit Logs: Maintains a cryptographically chained SHA-256 audit trail of all policy evaluations, approvals and settlements
How We Built It
Frontend: Built with React, Tailwind CSS and Vite. Responsive dashboard layout with real-time risk scoring, velocity graphs and enforcement breakdown charts.
Backend & Security: FastAPI, PostgreSQL, Redis, Docker, Argon2id credential rotation, PayPal Sandbox webhook receiver rails.
AI & Governance Engine: Integrates CrewAI and Gemini 2.0 Flash for real-time assessment of intent consistency and multi-signal risk scoring.
Challenges we faced Connecting natural language and deterministic limits:
Translating loose human instructions (e.g. “Prioritize battery life, under $1000”) into tight runtime constraints without breaking the agent’s autonomous workflow required careful prompt structuring and robust fallback parsing.
Low-Latency Policy Enforcement: Spend checks, intent verification, and risk scoring must operate within microsecond windows prior to the order payloads being sent to the PayPal Sandbox REST API gateway.
Technical Architecture & Risk Formula
AgentPass computes transaction authorization probability and risk scoring using multi-signal heuristics. For instance, risk scoring velocity and transaction limits are evaluated using models represented as:
$$RiskScore = \alpha(\text{Amount}) + \beta(\text{VelocityCount}) + \gamma(\text{IntentConflict Penalty})$$
Where thresholds are deterministically evaluated at the gateway prior to initiating PayPal capture settlements.