# DEFS Agent Defense

> DEFS Agent Defense (defs.ai) is managed AI-agent fraud defense for credit unions and community banks: a done-for-you service. Members' AI agents are already trying to pay bills, move money and file disputes. DEFS checks every agent request before money moves, stops the rogue ones, and sends the credit union real-time alerts and a monthly outcome report. No new dashboard to staff and no new analyst to hire.

Status: early stage. The demo environment (https://demo.defs.ai) uses test data only. Every engagement starts on test data in a sandbox.

## Key facts
- Who it's for: credit union and community bank fraud and risk teams.
- Scope: non-card money movement started by AI agents through online banking: bill pay, transfers between accounts, external transfers and ACH, and disputes.
- How it works: (1) you set the rules in one kickoff session; (2) every agent request passes through DEFS before money moves, and DEFS allows in-policy actions from verified agents, holds new payees and new destinations for the member to approve on their own device, and stops forged or replayed credentials, unknown payees, over-limit amounts and known rogue agents; (3) you get the results: a monthly outcome report and real-time alerts for critical events.
- People: anything unusual goes to a DEFS reviewer, a real person. Outside review hours, anything unclear is safely held. DEFS never defaults to "allow."
- Credentials: DEFS checks the credentials agents already carry: Cloudflare Web Bot Auth, Visa Trusted Agent Protocol and Google AP2 today, with Mastercard Agent Pay and other issuers in progress.
- Control stays with the credit union: your limits, your kill switch, your tamper-evident audit trail, and a named human reviewer on your account.

## Links
- [Home](https://defs.ai/): service overview and FAQ
- [Full text for LLMs](https://defs.ai/llms-full.txt)
- [Book a demo](https://defs.ai/book)
- [Live demo environment, test data only](https://demo.defs.ai/)

## Guides (defs.ai/learn)
- [All guides](https://defs.ai/learn/): AI agents and online banking, for credit unions and community banks
- [How can credit unions protect members from AI agent fraud in agentic payments?](https://defs.ai/learn/protect-members-from-ai-agent-fraud): Check each agent payment at the moment money would move, with rules that sit outside the AI model.
- [How should credit unions handle AI agents logging into online banking?](https://defs.ai/learn/ai-agents-online-banking): Treat it as a money-movement question, not just a login question.
- [How do you stop AI-agent account takeover and unauthorized transfers?](https://defs.ai/learn/stop-ai-agent-account-takeover): Check every agent request at the moment money would move, not only at login.
- [How do you verify an AI agent? Visa TAP, Mastercard Agent Pay, Web Bot Auth and AP2 explained](https://defs.ai/learn/how-to-verify-ai-agents): You verify an AI agent by checking a cryptographic credential it sends with each request, not by trusting its name, user agent or IP address.
- [How should credit unions set limits for AI agents doing bill pay and transfers?](https://defs.ai/learn/ai-agent-limits-bill-pay-transfers): Set limits for each agent, not just for each account: which operations it may perform, how much per payment and per day, and which payees and destinations it may use.
- [Agentic commerce fraud readiness checklist for credit unions](https://defs.ai/learn/agentic-commerce-fraud-readiness-checklist): A credit union is ready for agentic commerce when it can answer five questions about any agent request: which agent is this, which member sent it, what was it allowed to do, who approved anything new, and how do we stop it right now.
- [How to evaluate AI agent security for credit unions](https://defs.ai/learn/evaluate-ai-agent-security-credit-unions): Start by naming the problem you are solving: governing your institution's own AI agents, recognizing agents at a card checkout, or controlling outside agents that members send into online banking to move money.
- [How do credit unions stop Zelle and P2P scams, and do those controls work for AI agents?](https://defs.ai/learn/scam-controls-for-ai-agent-transfers): Credit unions cut P2P scam losses with a well-known set of controls: holds or extra checks on payments to new recipients, lower limits for new users and new payees, step-up approval above a dollar threshold, transaction monitoring and member education.
- [How do credit unions prevent ACH and external transfer fraud when an AI agent starts the transfer?](https://defs.ai/learn/ai-agent-ach-external-transfer-fraud): Check the agent's request before the transfer is created.
- [Can a smaller credit union get managed fraud monitoring for AI agent activity?](https://defs.ai/learn/managed-ai-agent-fraud-monitoring): Yes.