Paradym with Vercel AI SDK

How to integrate Paradym MCP with Vercel AI SDK v6

Trusted by

GET STARTED FOR FREE GET A DEMO

30 min · no commitment · see it on your stack

Introduction Also integrate Paradym with TL;DR What is Vercel AI SDK What is the Paradym MCP server Supported Tools & Triggers Creating MCP Server - Stand-alone vs Composio SDK Step-by-step Guide Complete Code Conclusion How to build Paradym MCP Agent with another framework Explore Other Toolkits FAQ

Connect Paradym without Auth hassles

We manage OAuth, API Key, token refresh, and scopes, you just build.

Try for Free

Introduction

This guide walks you through connecting Paradym to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Paradym agent that can issue sd-jwt verifiable credential for a user, verify authenticity of a presented credential, list all credentials issued to an email address through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Paradym account through Composio's Paradym MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Paradym with

OpenAI Agents SDK Claude Agent SDK Claude Code Claude Cowork Codex OpenClaw Hermes CLI Google ADK LangChain Mastra AI LlamaIndex CrewAI

TL;DR

Here's what you'll learn:

How to set up and configure a Vercel AI SDK agent with Paradym integration
Using Composio's Tool Router to dynamically load and access Paradym tools
Creating an MCP client connection using HTTP transport
Building an interactive CLI chat interface with conversation history management
Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

streamText: Core function for streaming responses with real-time tool support
MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
OpenAI Provider: Native integration with OpenAI models

What is the Paradym MCP server, and what's possible with it?

The Paradym MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Paradym account. It provides structured and secure access to your verifiable credential workflows, so your agent can perform actions like issuing credentials, verifying identity claims, managing credential lifecycles, and supporting interoperability across digital identity standards.

Automated credential issuance: Instruct your agent to issue new verifiable credentials to users or systems, supporting protocols like SD-JWT VCs and AnonCreds.
Seamless credential verification: Enable your agent to verify the authenticity and validity of credentials presented by others, streamlining onboarding and trust checks.
Credential lifecycle management: Allow your agent to update, revoke, or renew existing credentials, ensuring full control over your digital identity assets.
Interoperability with identity standards: Leverage your agent to work across OpenID4VC, DIDComm, and other standards for maximum compatibility and flexibility.
Audit and usage tracking: Task your agent to retrieve detailed logs or status reports on credential activity, helping you maintain compliance and visibility.

Supported Tools & Triggers

Tools

Activate CertificateTool to activate a certificate for use in a project.

Archive AnonCreds Credential TemplateTool to archive an AnonCreds credential template in a project.

Archive mDoc Credential TemplateTool to archive an mDoc credential template.

Archive Presentation TemplateTool to archive a presentation template in a project.

Archive SD-JWT VC Credential TemplateTool to archive an SD-JWT VC credential template in a project.

Create AnonCreds Credential TemplateTool to create a new AnonCreds credential template.

Create CertificateTool to create a new self-signed X.

Create DIDComm Connection InvitationTool to create a DIDComm connection invitation.

Create DIDComm Issuance OfferTool to create a DIDComm credential issuance offer.

Create OpenID4VC Credential OfferTool to create an OpenID4VC credential offer.

Create OpenID4VC Verification RequestTool to create an OpenID4VC verification request.

Create Presentation TemplateTool to create a new presentation template.

Create Project WebhookTool to create a new webhook for a project.

Create SD-JWT VC Credential TemplateTool to create a new SD-JWT VC credential template with selective disclosure capabilities.

Create Trusted EntityTool to create a new trusted entity for a project.

Deactivate CertificateTool to deactivate a certificate in a project.

Delete DIDComm ConnectionTool to delete a DIDComm connection from a project.

Delete DIDComm InvitationTool to delete a DIDComm invitation from a project.

Delete Trusted EntityTool to delete a trusted entity from a project.

Delete Project WebhookTool to delete a webhook endpoint from a project.

Get AnonCreds Credential TemplateTool to retrieve a specific AnonCreds credential template by ID.

Get AnonCreds Credential Template JSON SchemaTool to retrieve the JSON schema for an AnonCreds credential template.

Get DIDComm ConnectionTool to retrieve a specific DIDComm connection by ID.

Get DIDComm ConnectionsTool to retrieve a list of DIDComm connections for a project.

Get DIDComm InvitationTool to retrieve a specific DIDComm invitation by ID.

Get DIDComm Issuance SessionTool to retrieve a specific DIDComm issuance session by ID.

Get DIDsTool to retrieve a list of Decentralized Identifiers (DIDs) for a specific project.

Get mDoc Credential TemplateTool to retrieve a specific mDoc credential template by ID.

Get mDoc Credential Template JSON SchemaTool to retrieve the JSON schema for an mDoc credential template.

Get OpenID4VC Issuance SessionTool to retrieve a specific OpenID4VC issuance session by ID.

Get OpenID4VC Verification SessionTool to retrieve a specific OpenID4VC verification session by ID.

Get Presentation TemplateTool to retrieve a specific presentation template by ID.

Get Presentation TemplatesTool to retrieve a list of presentation templates for a project.

Get Project MembersTool to retrieve a list of project members.

Get Project ProfileTool to retrieve the default profile for a project.

Get ProjectsTool to retrieve a list of all projects accessible to the authenticated user.

Get Project WebhooksTool to retrieve a list of webhooks configured for a specific project.

Get SD-JWT VC Credential TemplateTool to retrieve a specific SD-JWT VC credential template by ID.

Get SD-JWT VC Credential Template JSON SchemaTool to retrieve the JSON schema for an SD-JWT VC credential template.

Get Trusted EntitiesTool to retrieve trusted entities for a specific project.

Get Trusted EntityTool to retrieve a specific trusted entity by ID.

Issue Direct SD-JWT VCTool to directly issue an SD-JWT VC credential without exchange protocol.

List AnonCreds Credential TemplatesTool to retrieve all AnonCreds credential templates for a project.

List CertificatesTool to retrieve all X.

List Certificate Signing RequestsTool to retrieve all certificate signing requests for a project.

List DIDComm InvitationsTool to retrieve all DIDComm invitations for a project.

List DIDComm Issuance OffersTool to list all DIDComm issuance offers within a project.

List DIDComm Mediator ConnectionsTool to retrieve connections for a DIDComm mediator.

List DIDComm MediatorsTool to retrieve all DIDComm mediators for a project.

List DIDComm Verification RequestsTool to list all DIDComm verification sessions for a project.

List Issued CredentialsTool to list metadata for all issued credentials within a project.

List mDoc Credential TemplatesTool to retrieve all mDoc credential templates for a project.

List OpenID4VC Issuance SessionsTool to retrieve all OpenID4VC issuance sessions for a project.

List OpenID4VC Verification SessionsTool to retrieve all OpenID4VC verification sessions for a project.

List SD-JWT VC Credential TemplatesTool to retrieve all SD-JWT VC credential templates for a project.

Receive DIDComm InvitationTool to receive and process an external DIDComm invitation.

Revoke CertificateTool to revoke a certificate in a project.

Send DIDComm Basic MessageTool to send a basic DIDComm message to a connection.

Send Custom DIDComm MessageTool to send a custom DIDComm message to a connection.

Unarchive AnonCreds Credential TemplateTool to unarchive an archived AnonCreds credential template.

Unarchive mDoc Credential TemplateTool to unarchive an archived mDoc credential template.

Unarchive SD-JWT VC Credential TemplateTool to unarchive an archived SD-JWT VC credential template.

Update DIDComm ConnectionTool to update a DIDComm connection.

Update mDoc Credential TemplateTool to update an existing mDoc credential template.

Update Presentation TemplateTool to update an existing presentation template.

Update ProjectTool to update an existing project's name and verification data access settings.

Update Project ProfileTool to update the default profile for a project.

Update SD-JWT VC Credential TemplateTool to update an existing SD-JWT VC credential template.

Update Trusted EntityTool to update an existing trusted entity in a project.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before you begin, make sure you have:

Node.js and npm installed
A Composio account with API key
An OpenAI API key

Getting API Keys for OpenAI and Composio

OpenAI API Key

Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
Keep the API key safe.

Composio API Key

Log in to the Composio dashboard.
Navigate to your API settings and generate a new API key.
Store this key securely as you'll need it for authentication.

Install required dependencies

bash

npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

@ai-sdk/openai: Vercel AI SDK's OpenAI provider
@ai-sdk/mcp: MCP client for Vercel AI SDK
@composio/core: Composio SDK for tool integration
ai: Core Vercel AI SDK
dotenv: Environment variable management

Set up environment variables

bash

OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

OPENAI_API_KEY: Your OpenAI API key for GPT model access
COMPOSIO_API_KEY: Your Composio API key for tool access
COMPOSIO_USER_ID: A unique identifier for the user session

Import required modules and validate environment

typescript

import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

What's happening:

We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
The dotenv/config import automatically loads environment variables
The MCP client import enables connection to Composio's tool server

Create Tool Router session and initialize MCP client

typescript

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["paradym"],
  });

  const mcpUrl = session.mcp.url;

What's happening:

We're creating a Tool Router session that gives your agent access to Paradym tools
The create method takes the user ID and specifies which toolkits should be available
The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
This session provides access to all Paradym-related tools through the MCP protocol

Connect to MCP server and retrieve tools

typescript

const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();

What's happening:

We're creating an MCP client that connects to our Composio Tool Router session via HTTP
The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
The type: "http" is important - Composio requires HTTP transport
tools() retrieves all available Paradym tools that the agent can use

Initialize conversation and CLI interface

typescript

let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to paradym, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();

What's happening:

We initialize an empty messages array to maintain conversation history
A readline interface is created to accept user input from the command line
Instructions are displayed to guide the user on how to interact with the agent

Handle user input and stream responses with real-time tool feedback

typescript

rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

What's happening:

We use streamText instead of generateText to stream responses in real-time
toolChoice: "auto" allows the model to decide when to use Paradym tools
stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
onStepFinish callback displays which tools are being used in real-time
We iterate through the text stream to create a typewriter effect as the agent responds
The complete response is added to conversation history to maintain context
Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Paradym and Vercel AI SDK:

typescript

import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["paradym"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to paradym, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Paradym agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

Real-time streaming responses for a better user experience with typewriter effect
Live tool execution feedback showing which tools are being used as the agent works
Dynamic tool loading through Composio's Tool Router with secure authentication
Multi-step tool execution with configurable step limits (up to 10 steps)
Comprehensive error handling for robust agent execution
Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

How to build Paradym MCP Agent with another framework

OpenAI Agents SDK

Use Paradym MCP with OpenAI Agents SDK

Claude Agent SDK

Use Paradym MCP with Claude Agent SDK

Claude Code

Use Paradym MCP with Claude Code

Claude Cowork

Use Paradym MCP with Claude Cowork

Codex

Use Paradym MCP with Codex

OpenClaw

Use Paradym MCP with OpenClaw

Hermes

Use Paradym MCP with Hermes

CLI

Use Paradym MCP with CLI

Google ADK

Use Paradym MCP with Google ADK

LangChain

Use Paradym MCP with LangChain

Mastra AI

Use Paradym MCP with Mastra AI

LlamaIndex

Use Paradym MCP with LlamaIndex

CrewAI

Use Paradym MCP with CrewAI

Explore Other Toolkits

Supabase

Oauth2Api Key

Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure.

Codeinterpreter

No Auth

Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms.

GitHub

Oauth2

GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place.

TOOLKIT MARKETPLACE

FAQ

What are the differences in Tool Router MCP and Paradym MCP?

With a standalone Paradym MCP server, the agents and LLMs can only access a fixed set of Paradym tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Paradym and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Vercel AI SDK v6?

Yes, you can. Vercel AI SDK v6 fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Paradym tools.

Can I manage the permissions and scopes for Paradym while using Tool Router?

Yes, absolutely. You can configure which Paradym scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Paradym data and credentials are handled as safely as possible.

Used by agents from

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for free Get a demo↗

Harsha GaddipatiCo-founder, Slashy

Karan skipped his own birthday party to fix our critical issue. It was 10 pm and he diverted his Waymo to help us instead. This really sets the bar, shows you the commitment you need to have when users rely on your software.

Abhi AryaCo-founder, Opennote

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it has immensely helped in keeping new users on the platform.

Nirman DaveCEO, Zams

We chose Composio over Pipedream because it delivered depth where it mattered. It supported niche tools and tricky edge cases that other platforms simply ignored. Giving us confidence to scale without compromising.

Ryan YuFounder, Extra Thursday

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down in the complexities of managing agent auth would have been a death sentence for Extra Thursday.

Tomisin JenrolaFounder & CEO, SwarmZero

Before partnering with Composio, adding tool integrations was a slow, resource-intensive process. Each integration could take weeks or months of engineering time, and maintaining them meant constantly keeping up with API changes.

Jerome LeclancheCo-Founder, Ingram Technologies

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Harsha GaddipatiCo-founder, Slashy

Abhi AryaCo-founder, Opennote

Nirman DaveCEO, Zams

Ryan YuFounder, Extra Thursday

Tomisin JenrolaFounder & CEO, SwarmZero

Jerome LeclancheCo-Founder, Ingram Technologies

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Harsha GaddipatiCo-founder, Slashy

Abhi AryaCo-founder, Opennote

Nirman DaveCEO, Zams

Ryan YuFounder, Extra Thursday

Tomisin JenrolaFounder & CEO, SwarmZero

Jerome LeclancheCo-Founder, Ingram Technologies

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

How to integrate Paradym MCP with Vercel AI SDK v6

Table of Contents

Connect Paradym without Auth hassles

Introduction

Also integrate Paradym with

TL;DR

What is Vercel AI SDK?

What is the Paradym MCP server, and what's possible with it?

Supported Tools & Triggers

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

How the Composio SDK works

Step-by-step Guide

Prerequisites

Getting API Keys for OpenAI and Composio

Install required dependencies

Set up environment variables

Import required modules and validate environment

Create Tool Router session and initialize MCP client

Connect to MCP server and retrieve tools

Initialize conversation and CLI interface

Handle user input and stream responses with real-time tool feedback

Complete Code

Conclusion

How to build Paradym MCP Agent with another framework

OpenAI Agents SDK

Claude Agent SDK

Claude Code

Claude Cowork

Codex

OpenClaw

Hermes

CLI

Google ADK

LangChain

Mastra AI

LlamaIndex

CrewAI

Explore Other Toolkits

Supabase

Codeinterpreter

GitHub

FAQ

What are the differences in Tool Router MCP and Paradym MCP?

Can I use Tool Router MCP with Vercel AI SDK v6?

Can I manage the permissions and scopes for Paradym while using Tool Router?

How safe is my data with Composio Tool Router?

Used by agents from

Never worry about agent reliability