Get an email from Lima

Lima is on it!

Check your inbox.
Oops! Something went wrong while submitting the form.
for Marketing

Model Relevance Protocol
MRP Workforce

MRP agents can get complex work done with just a few simple low-level tools, a long-context model and optional docs.

What can MRP agents do?

Give an MRP agent a natural language task, and it'll be able to figure out how to get the job done with just a few very simple tools.

HubSpot MRP

Generate a few records to pre-populate my CRM like a live demo environment. I want Contacts, Deals, Companies, Notes, Logged Emails and Calls. Use Dummy numbers.

Google Docs MRP

Generate a Google Doc titled “AI Agent Use-Cases and Building Techniques”. Break down each AI Agent use-case and building technique in-depth.

Webflow MRP

Generate a new blog post about AI Agents and add to the "Blog Post" collection. Return the full content for me to review and approve. Once I've approved, publish it and share the link to the live page.

Notion MRP

Generate a task management system with an inline-database for projects, another for tasks. Use a relation field to link the tasks to the projects. Add 3 x example projects.

Without an AI Agent

Manual content creation and publishing.
Prone to human error.
Lost opportunity due to slowness.
Wasting time jumping around different tools.

With an AI SEO Agent

From research to publishing all on autopilot.
Follows the same process every time.
Creates content immediately when triggered.
Integrates with any CMS and tech stack.
What can MRP workforces do?

Give an MRP agent a natural language task, and it'll be able to figure out how to get the job done with just a few very simple tools.

Without an AI Agent

Manual content creation and publishing.
Prone to human error.
Lost opportunity due to slowness.
Wasting time jumping around different tools.

With an AI SEO Agent

From research to publishing all on autopilot.
Follows the same process every time.
Creates content immediately when triggered.
Integrates with any CMS and tech stack.
Introduction

Model Relevance Protocol

What does an MRP look like at an agent level? And why might you want to use them as an extension to, or instead of MCPs? Let's dive in.

What is a Multi-Agent System?

A multi-agent system (MAS) is a group of intelligent agents that interact and work together towards achieving common goals. Agents in a MAS combine their individual capabilities and knowledge to collaborate on solving problems that are beyond the scope of any individual agent.

Some key characteristics of a multi-agent system are:

  • Composed of multiple autonomous agents
  • Agents have particular capabilities and expertise
  • Agents communicate and coordinate with other agents
  • Decentralized control and decentralized data
  • Emergent global behavior from local agent interactions
Benefits of a Multi-Agent System

Some of the key benefits of developing a multi-agent system are:

  • Modularity - Agents can be added or removed as needed
  • Robustness - System continues operation if some agents fail
  • Scalability - Easy to expand system by adding agents
  • Flexibility - Agents can be customized for different roles
  • Faster problem solving - Parallelization of work across agents
  • Broader intelligence - Combination of multiple skill sets
How to Build a MAS with Relevance AI

Relevance AI provides a no-code platform for easily building intelligent multi-agent systems. Here are the key steps:

  • Identify the Goals and Scope - Define the objectives and outcomes you want to achieve an map out different tasks and workflows required.
  • Create and Train Agents - Use pre-built agents or create custom agents. Train agents on specific domains and give them specialized skills
  • Define Agent Interactions  - Model how agents will communicate and work together
  • Deploy and Iterate - Deploy your multi-agent system. Monitor performance and add/adjust agents as needed
How to Build a MAS with Relevance AI

Relevance AI provides a no-code platform for easily building intelligent multi-agent systems. Here are the key steps:

  • Identify the Goals and Scope - Define the objectives and outcomes you want to achieve an map out different tasks and workflows required.
  • Create and Train Agents - Use pre-built agents or create custom agents. Train agents on specific domains and give them specialized skills
  • Define Agent Interactions  - Model how agents will communicate and work together
  • Deploy and Iterate - Deploy your multi-agent system. Monitor performance and add/adjust agents as needed

Create high quality SEO content at scale.

Produces high-quality SEO pages at scale for rapid growth.

Trigger AI Agent to create content automatically

The Model Context Protocol standardise how tools are shared and accessed. You can think of an MCP as a bundle of tools packaged together in a way that lets AI assistants use them through a shared interface. This makes it possible for agents built on one platform, to use tools developed on another.

What is an MRP?

The Model Relevance Protocol takes things a step further. Instead of packaging multiple tools into one server, an MRP is about having one agent with a couple of low-level tools that it can use to complete complex workflows. Like a generic API or code step tool that the agent can figure out how to use, instead of 30+ tools that are hyper-specific.

MRPs are an extension to MCP

MRPs allow your AI assistants to complete work that isn't possible with just the tools packaged into an MCP bundle alone. Instead of writing out every step or copying detailed API calls, you can just connect your agent to the relevant MRP agent and ask for what you want in plain language. The specialist MRP agent handles the rest.

MCP - Many good tools

Your AI assistant can use any tool that an integration provider has packaged up for you. Each tool will be very reliable, and do its job well. However, it will only be able to complete work that it has tools for. If the API changes, you have to update any tool that is affected, and any tool that require strongly formatted inputs.

MRP - 1+ simple tool

Your AI assistant can use any tool that an integration provider has packaged up for you. Each tool will be very reliable, and do its job well. However, it will only be able to complete work that it has tools for. If the API changes, you have to update any tool that is affected, and any tool that require strongly formatted inputs.

MRP agents can get complex work done with simple tools

With just a single generic API call tool, and some API documentation, this Notion MRP agent was able to create a full task management system with relational databases, and a few example projects and tasks.

Before, it would have taken hours to build out each individual tool needed to create a page, create the databases each with custom properties, create projects and tasks and add them to the database and link them together and more. You'd have to do that all over again if you wanted a different kind of Notion management system too.

Now, all you need to do to get started is clone the agent, connect your Notion account, and give it a task.

Triggers

MRP workforces, are mindblowing

Trigger your Agents tasks with our growing list of native integrations or even build your own.

This makes things more flexible:

No training on your data

Your data remains private and is never utilized for model training purposes.

SOC 2 (Type II) & GDPR Compliant

We are SOC 2 (Type II) certified and GDPR compliant, ensuring top-tier data security and privacy.

Choose where to store your data

Choose between US, EU, and AU data-centers. We also support single tenant or private cloud deployment.

Sync your Hubspot CRM to enable automatic AI Agent responses to activities.
Configure your AI Agent to manage new emails directly from your Gmail inbox.
Set up your AI Agent to automatically handle actions from WhatsApp messages.
Freshdesk support tickets will automatically engage your AI Agent, ensuring prompt responses.
Integrate with Zapier to trigger your AI Agent across more than 6000+ apps.
Trigger your AI agent from your own HTTP endpoints.
For prototyping and deploying AI workers and automations.
Testimonials

Thousands of businesses have already seen transformational results

Join the thousands of other teams empowering their workforce with AI.

Relevance AI is my number 1 favorite automation tool out of all of them. it's super underrated
Jake George
Founder, Synthoria Labs
I'm looking at almost every single thing our business does and creating an AI tool or Agents to either improve the process, speed it up or add value in a different way using Relevance.
Michael Viney
Venture Capital Fund
Head of IT
Started working with Relevance AI for marketing agents to automate workflows. Pretty rad
Steve Armenti
VP Revenue Marketing,
Digital Ocean
Why I love Relvance AI? Even though it's a no-code platform the use cases are unlimited and you can customize it any way you want and DO anything you want.
Ben Van Sprundel
Ben AI
AI Consultant and Youtuber
[With Relevance AI] I just discovered something that made my jaw drop! In just 3 minutes, I accessed more intel about a prospect than most people gather in hours of research.
Avi Hacker
The AI Consulting Network
Founder and CEO
I love building with Relevance and have created some incredibly powerful production workflows for my team and our clients.
Sam Rahmanian
Eftsure
CRO
You're going to find it pretty tough to find another tool that is as powerful and easy to use as Relevance AI
Marcus Taylor
Venture Harbour
Founder and CEO
Started working with Relevance AI for marketing agents to automate workflows. Pretty rad
Steve Armenti
Digital Ocean
VP Revenue Marketing
Why I love Relvance AI? Even though it's a no-code platform the use cases are unlimited and you can customize it any way you want and DO anything you want.
Ben Van Sprundel
Ben AI
AI Consultant and Youtuber
Our GTM team is constantly improving systems and processes to enable the next phase of growth, [by] AI Agents from Relevance AI
Sam Rahmanian
Eftsure
CRO
I'm looking at almost every single thing our business does and creating an AI tool or Agents to either improve the process, speed it up or add value in a different way using Relevance.
Michael Viney
Venture Capital Fund
Head of IT
[With Relevance AI] I just discovered something that made my jaw drop! In just 3 minutes, I accessed more intel about a prospect than most people gather in hours of research.
Avi Hacker
The AI Consulting Network
Founder and CEO
You're going to find it pretty tough to find another tool that is as powerful and easy to use as Relevance AI
Marcus Taylor
Venture Harbour
Founder and CEO
Relevance AI has been a game-changer for us to rapidly develop LLM powered tools and agents for our clients.
Shane Rosse
Allience App
CTO
Relevance AI's impact on our organization is undeniable. Their combination of innovative tools and agents, supportive team, and constant development makes them a key partner in our AI strategy.
Luke Thompson
Action VFX
COO
Started working with Relevance AI for marketing agents to automate workflows. Pretty rad
Steve Armenti
Digital Ocean
VP Revenue Marketing
Why I love Relvance AI? Even though it's a no-code platform the use cases are unlimited and you can customize it any way you want and DO anything you want.
Ben Van Sprundel
Ben AI
AI Consultant and Youtuber
Our GTM team is constantly improving systems and processes to enable the next phase of growth, [by] AI Agents from Relevance AI
Sam Rahmanian
Eftsure
CRO
I'm looking at almost every single thing our business does and creating an AI tool or Agents to either improve the process, speed it up or add value in a different way using Relevance.
Michael Viney
Venture Capital Fund
Head of IT
[With Relevance AI] I just discovered something that made my jaw drop! In just 3 minutes, I accessed more intel about a prospect than most people gather in hours of research.
Avi Hacker
The AI Consulting Network
Founder and CEO
You're going to find it pretty tough to find another tool that is as powerful and easy to use as Relevance AI
Marcus Taylor
Venture Harbour
Founder and CEO
Relevance AI has been a game-changer for us to rapidly develop LLM powered tools and agents for our clients.
Shane Rosse
Allience App
CTO
Relevance AI's impact on our organization is undeniable. Their combination of innovative tools and agents, supportive team, and constant development makes them a key partner in our AI strategy.
Luke Thompson
Action VFX
COO