---
title: "AI agents · Solutions"
description: "Runtime verification for AI agents. QWED checks tool calls before they run, messages between agents, and checkout totals before payment, and records each decision."
url: https://qwedai.com/solutions/ai-agents
---

# Runtime verification for agent actions, before they run.

Agents call tools, talk to other agents and spend money. QWED adds a check at each of those points: tool calls before they run, messages between agents, and checkout totals before payment.

[Contact](https://qwedai.com/contact) [Read the documentation](https://docs.qwedai.com/open-responses/overview)

What QWED checks here

-   Tool calls
-   Agent outputs
-   Messages between agents
-   Checkout and payment

With Open Responses, QWED A2A, QWED UCP and MCP server

## Agents act at machine speed. So do their mistakes.

An agent that is wrong does not pause to ask. It acts.

Nobody checked any of it

### Without QWED

-   **A destructive tool call** An agent calls a shell tool with rm -rf /.

-   **A total that does not add up** One agent tells another that items worth 150.00 come to 999.99.

-   **Tax applied wrong at checkout** Tax of 8.25% on $100 is charged as $8.00 just before payment goes through.

Each one checked before it is used

### With QWED

1.  **A destructive tool call** Open Responses A blocked tool pattern, so the call never runs.

    BLOCKED · DENY
2.  **A total that does not add up** QWED A2A The items come to 150.00, so the message is held.

    VERIFIED · DENY
3.  **Tax applied wrong at checkout** QWED UCP 8.25% of $100 is $8.25, so payment is held.

    VERIFIED · DENY

What is proven correct goes through, with a record of why.

QWED returns the decision; your integration acts on it.

## What QWED checks

Four packages cover the places where an agent acts. None of them asks a model to judge the result.

-   Open Responses

    ### Tool calls

    ToolGuard blocks dangerous tools and patterns, ArgumentGuard checks argument types and ranges, and SafetyGuard flags personal data, prompt injection and budget.

-   Open Responses

    ### Agent outputs

    MathGuard recomputes totals, SchemaGuard checks JSON against a schema, and StateGuard enforces allowed state changes.

-   A2A

    ### Messages between agents

    A trust boundary with allowlists and rate limits, exact checks on money totals, and a signed attestation on every decided result.

-   UCP

    ### Checkout and payment

    Total must equal subtotal minus discount plus fulfilment, tax and fees, and the checkout must move through valid states.

-   MCP server

    ### Exact answers in MCP clients

    Lets Claude Desktop, VS Code and other MCP clients run Python calculations in a restricted subprocess instead of guessing.

## Where it fits

1.  Your AI

    Decides to call a tool, send a message or complete a purchase.

2.  QWED

    Checks the call, the message or the totals against your rules.

3.  Your systems

    Only checked actions reach your tools, other agents and payment systems.

Good to know

-   Open Responses blocks tools from a list you configure. It is not a sandbox, and its pattern scanning is a heuristic.
-   In QWED A2A, only finance checks can return verified; logic and code checks alone are not enough to act on.
-   The MCP server runs code with the server’s privileges, so connect only clients you trust.

## Get started

-   ### [Open Responses](https://qwedai.com/platform/open-responses)

    v0.6.1 Beta

    Guards for agent tool calls and outputs. Works with the OpenAI Responses API, LangChain and LlamaIndex.

    ```
    $ pip install qwed-open-responses
    ```

-   ### [QWED A2A](https://qwedai.com/platform/a2a)

    v0.3.0 Alpha

    A zero-trust interceptor for messages between agents, using the Agent-to-Agent protocol.

    ```
    $ pip install qwed-a2a
    ```

-   ### [QWED UCP](https://qwedai.com/platform/ucp)

    v0.3.0 Alpha

    Checks for Universal Commerce Protocol checkouts before the money moves.

    ```
    $ pip install qwed-ucp
    ```

-   ### [MCP server](https://qwedai.com/platform/mcp)

    v0.2.2 Beta

    Verification tools for Claude Desktop, VS Code and other MCP clients.

    ```
    $ pip install qwed-mcp
    ```

### Building with AI agents?

Tell us what your AI does and where a mistake would hurt.

[Contact](https://qwedai.com/contact)

## Other fields

-   [Banking and payments](https://qwedai.com/solutions/banking)
-   [Legal](https://qwedai.com/solutions/legal)
-   [Tax](https://qwedai.com/solutions/tax)
-   [Cloud infrastructure](https://qwedai.com/solutions/cloud)
-   [Software delivery](https://qwedai.com/solutions/software-delivery)