Claude 4 Models: Enhanced AI Performance Now Available

You can now access the latest Claude 4 models—Sonnet v4 and Opus v4—directly in Relevance!

Claude 4 brings improved capabilities to your AI workflows with particular enhancements for coding tasks. While Sonnet v4 maintains the same pricing as previous versions, Opus v4 offers premium performance at a higher price point (5x Sonnet's cost) for your most demanding applications.

➡️ Access two new model options – Choose between cost-effective Sonnet v4 or premium Opus v4

➡️ Leverage improved coding capabilities – Get better results for programming tasks and technical workflows

➡️ Maintain budget control – Sonnet v4 keeps the same pricing as v3.5 and v3.7

➡️ Make informed decisions – Community feedback is mixed, with 200k context window compared to competitors' larger windows

➡️ Explore Anthropic's latest technology – Experience the newest advancements in AI capabilities

With Claude 4 models, you can enhance your AI applications with Anthropic's latest advancements while choosing the performance tier that fits your specific needs and budget.

To try these models, simply select "Claude Sonnet v4" or "Claude Opus v4" from the model options in Relevance.

Give the new Claude 4 models a test drive and share your experience with us!

AgentOS: Total Visibility and Control Over Your AI Workforce

You can now manage your entire AI workforce from a mission control center with comprehensive monitoring, scheduling, and governance tools!

AgentOS provides the infrastructure layer that transforms how you manage AI agents at scale. It bridges the gap between successful pilots and enterprise-wide deployment by giving you complete visibility, control, and confidence in your AI operations as you scale from a few agents to dozens across departments.

✅ Advanced scheduling – Run agents on fixed times or recurring intervals to automate workflows without manual intervention

✅ Intelligent queuing – Prioritize tasks based on business logic to ensure critical operations happen first

✅ Comprehensive logging – Track every agent action with detailed records of what happened, when, and why

✅ Performance analytics – Monitor real-time metrics across your entire AI workforce to identify optimization opportunities

✅ Governance controls – Instantly pause, resume, or override agent behavior when needed

With Relevance, you can confidently scale your AI implementation from pilot to production while maintaining complete visibility and control over your entire AI workforce.

Check out our docs to learn more about giving your agent tasks, bulk scheduling agent tasks, setting recurring schedules, extracting metadata from your agent's tasks, and more.

Start managing your AI workforce with enterprise-grade confidence today!

2000+ Integrations: Connect Your AI Workforce to Your Entire Tech Stack

You can now seamlessly connect your AI agents to over 2,000 tools and platforms across your technology ecosystem!

Relevance AI's massive integration library eliminates one of the biggest obstacle in AI implementation: connecting your intelligent agents to the systems where your business data actually lives. These native integrations enable your AI workforce to access, modify, and work with information across your entire tech stack without manual transfers or human intervention.

✅ Access your complete tech ecosystem – Connect to Google Workspace, Salesforce, Slack, Asana, and thousands more platforms

✅ Enable end-to-end automation – Eliminate manual data transfers with agents that work across multiple systems in one workflow

✅ Reduce process times by up to 80% – Eliminate context-switching and manual data handling that previously slowed your team

✅ Benefit from semantic understanding – Agents intelligently work with each platform's unique data structure and context

To explore the integration library, visit the Integrations section in your Relevance AI dashboard and discover how to connect your agents to your essential business tools.

Start building truly connected AI workflows today!

Workforce: Build visual multi-agent AI teams without code

You can now design and deploy entire teams of specialized AI agents working together - all through an intuitive visual canvas with zero coding required!

Workforce transforms how organizations implement AI by enabling the creation of sophisticated multi-agent systems that collaborate seamlessly. Instead of isolated single-purpose assistants, you can now orchestrate specialized AI teams that handle complex, multi-step processes through a simple drag-and-drop interface.

✅ Create specialized agent teams – Drag and drop agents onto a visual canvas for better results than "do-everything" agents

✅ Design workflows visually – Define how agents interact and collaborate without writing a single line of code

✅ Deploy complex solutions in minutes – Implement what previously required weeks of engineering in a single afternoon

✅ Enable non-technical experts – Subject matter experts can now design AI systems perfectly matched to their domain knowledge

✅ Integrate with human workflows – Build hybrid teams where AI agents and human colleagues collaborate seamlessly

With Workforce, you can transform complex business processes into efficient, automated workflows where each agent focuses on what it does best while working in concert with others.

To start building your first multi-agent system, access Workforce through your Relevance AI dashboard and select "Create New Workforce" to open the visual canvas.

Workforce is available now to all users on a Pro plan or higher.

Start orchestrating your AI dream team today and unlock the true potential of collaborative artificial intelligence!

https://relevanceai.com/workforce

You can now build powerful, custom AI agents just by describing what you need in everyday language!

Invent transforms how you create AI solutions by eliminating technical barriers. Simply describe the agent you want in plain English, and Invent builds it instantly—complete with all necessary tools and capabilities tailored to your specific needs and workflows.

➡️ Build custom agents without code – Just describe what you need in natural language

➡️ Go from idea to working solution in minutes – No more waiting for technical resources or development time

➡️ Create truly customized solutions – Get agents tailored to your specific terminology, data, and standards

➡️ Empower subject matter experts – Let the people who know the work best create their own AI solutions

➡️ Deploy specialized agents for any workflow – From compliance checking to customer support to research assistance

With Invent, anyone in your organization can turn their ideas into powerful AI agents, dramatically reducing time-to-value and democratizing access to custom AI solutions.

To start creating your own agents with Invent, simply navigate to Relevance AI platform and select the "Invent" option. Or get started here - it's that easy!

Learn more about why we built Invent, with a BTS look at the team 👉 HERE

Start building your custom AI workforce today!

Gemini 2.5 Pro and Flash: Powerful New Models for Your Agents

You can now build smarter, more capable agents with Google's latest AI models - Gemini 2.5 Pro and 2.5 Flash!

These powerful new models are available immediately, giving your agents enhanced reasoning, improved context handling, and faster performance. Choose between Pro for complex tasks requiring deep reasoning or Flash for quicker, more efficient responses.

➡️ Access cutting-edge AI capabilities – Leverage Google's most advanced models directly in your agents

➡️ Choose the right model for your needs – Pro for complex reasoning or Flash for speed and efficiency

➡️ Enhance your agents' performance – Get better responses with improved context understanding

➡️ Deploy immediately in production – No waiting period, available right now for all your agents

➡️ Optimize your token usage – Be mindful of context size to maintain optimal performance

To implement these new models, simply select "Gemini 2.5 Pro" or "Gemini 2.5 Flash" when configuring your agent's model settings.

Smarter agents start here—harness OpenAI’s most advanced models to date‍

The new o3 and o4-mini models represent a significant leap in AI capabilities, designed to think more deeply before responding. These powerful models are now fully integrated into Relevance, allowing you to create smarter agents and enhance your existing workflows with minimal effort.

➡️ Access cutting-edge AI – Leverage OpenAI's smartest models to date for your agents

➡️ Enhance reasoning capabilities – Benefit from models trained to think longer before responding

➡️ Improve complex task handling – Tackle more sophisticated problems with greater accuracy

➡️ Seamlessly integrate – Select these models when creating or editing agents

➡️ Optimize LLM and vision steps – Choose o3 or o4-mini for specific workflow components

With these new OpenAI models, you can build more capable agents that deliver better results for your real-world tasks, whether you're a curious explorer or an advanced AI researcher.

To start using these models, simply select "o3" or "o4-mini" when creating a new agent or editing an existing one, or choose them specifically in your LLM and vision steps.

Try these powerful new models today and experience the next generation of AI capabilities in your Relevance workflows!

Leverage Google’s latest AI in just a few clicks—no API key needed (unless you want to)
‍
You can now use Google Gemini Flash 2.0 as a native agent model in your workflows!

We've integrated Google's powerful Gemini models directly into our agent platform, starting with Gemini Flash 2.0.

Use it right away with our built-in access or connect your own Gemini API key for greater flexibility and control. Either way, you'll be building sophisticated, high-performance agents with Google's state-of-the-art AI capabilities

➡️ Access cutting-edge AI – Harness Google's Gemini Flash 2.0 model directly in your agents

➡️ Choose your setup – Use our built-in access or connect your own Gemini API key

➡️ Enhanced performance – Benefit from Google's latest advancements in AI capabilities

➡️ Future-ready platform – More Google models coming soon to expand your options

➡️ Seamless workflow integration – Build agents with the same familiar interface

With native Gemini models, you can create more powerful, responsive agents that leverage Google's AI expertise while maintaining the simplicity and flexibility of our platform.To use Gemini Flash 2.0, simply select it as your agent model during setup. You can use it immediately or optionally enter your own Gemini API key.

Stay tuned for more Google models coming soon to expand your agent capabilities!‍

Saved Filter Views: Customize and Preserve Your Task Filters‍

You can now save your custom filter configurations across sessions, eliminating the need to recreate them every time you navigate away!

Saved Filter Views lets you create and maintain personalized task filtering setups that persist in your browser's local storage. Whether you need to quickly access specific tasks, prioritize certain workflows, or monitor particular agents, your custom views remain just a click away.

➡️ Create custom filter views – Press the "+" button in the views tabs section or click "save view" on default tabs

➡️ Manage your views easily – Right-click any view for options to duplicate, rename, or delete

➡️ Quick rename functionality – Simply double-click on any view button to rename it

➡️ Access your views across pages – Available on both the activity center and agent task full screen pages

➡️ Smart space management – If you have more than 5 views, the system shows only default tabs plus your current selection

With Saved Filter Views, you'll save valuable time by instantly accessing your most important task views without recreating complex filter combinations.

To use this feature, look for the views tabs section at the top of your task lists in the activity center or agent task pages.

Start organizing your workflow more efficiently with custom filter views today!

New OpenAI Models: Supercharge Your Agents with GPT-4.1 Series

You can now access OpenAI's latest and most powerful models directly in Relevance AI!

The newly released GPT-4.1 series brings significant improvements across the board, with enhanced capabilities and performance compared to previous models. These models are available immediately as agents, in the LLM step, and in the vision step.

➡️ GPT-4.1 – OpenAI's flagship model that outperforms GPT-4o "across almost every dimension" and even beats the now-deprecated 4.5 preview on many benchmarks

➡️ GPT-4.1 Mini – Impressive performance that surpasses even GPT-4o on several benchmarks while maintaining efficiency

➡️ GPT-4.1 Nano – OpenAI's fastest and most cost-effective model, perfect for tasks requiring quick responses and budget optimization

➡️ Seamless integration – Available immediately as agents, in the LLM step, and in the LLM vision step

With these new models, you can build more capable, responsive, and intelligent agents that deliver better results for your specific use cases while optimizing for performance and cost.

To try these new models, simply select them when creating or editing agents or choose them in your LLM and vision steps.

Test these powerful new models today and share your feedback on how they perform on your real-world tasks!

Agent Version Control: Safely Manage and Track Your Agent Changes

You can now save, track, and restore different versions of your agents with complete confidence!

Agent Version Control gives you powerful version management for your AI agents. Create draft versions when you're not ready to publish, view a complete history of changes, and easily restore previous versions if something doesn't work as expected.

➡️ Save agents as drafts – Make changes without affecting your published agent

➡️ Track version history – See all previous versions of your agent in one place

➡️ Restore previous versions – Quickly revert to any earlier version when needed

➡️ Document your development process – Each save creates a new version automatically

➡️ Maintain stability – Only published agents can run, ensuring production reliability

With Agent Version Control, you can experiment with confidence, collaborate more effectively with your team, and maintain a complete history of your agent's evolution.

To access version control for an agent, go to Agent Profile, click on the 'three dots' icon > 'Show version history'.

Start protecting your agent development process with version control today!

Relevance Recommended Models: Smart Model Selection for Optimal Performance

You can now leverage pre-configured AI models optimized for either cost-efficiency or maximum performance!

Relevance Recommended Models provide intelligent model selection that balances your needs for performance and budget. We've carefully selected and pre-configured two specialized model options that automatically update as better alternatives emerge, eliminating the need for manual model switching or staying current with the latest AI advancements.

✅ Cost-optimized model (Default) – Get excellent performance at reduced costs for all users

✅ Performance-optimized model – Access the absolute best performance available (Premium plans only)

✅ Automatic updates – Benefit from the latest models without manual switching or research

✅ Pre-configured settings – Skip complex model selection decisions and configuration

✅ Future-proof workflows – Your agents automatically improve as better models emerge

With Relevance Recommended Models, you can focus on building powerful agents while we handle the complex task of selecting and updating the optimal AI models for your specific needs.

To select your preferred model, simply choose between "Cost-optimized" (default) or "Performance-optimized" when configuring your agents and LLM tools.

Start building with confidence knowing you're always using the optimal model for your needs!

MCP Server Integration: Use Your Relevance AI Tools in External AI Clients

You can now connect your Relevance AI tools to Claude, Cursor, and other AI clients that support MCP servers!

The MCP Server integration creates a bridge between your Relevance AI workspace and external AI clients, allowing you to leverage your custom tools across multiple platforms. This means the powerful tools you've built in Relevance AI can now be accessed and utilized by your favorite AI assistants outside our platform.

➡️ Extend tool availability – Use your Relevance AI tools in Claude, Cursor, and other MCP-compatible AI clients

➡️ Maintain a single source of truth – Update tools in one place and have changes reflect everywhere

➡️ Customize your integration – Select exactly which tools to expose to external clients

➡️ Simple configuration – Generate MCP server settings with just a few clicks

➡️ Seamless workflow integration – Access your specialized tools wherever you work with AI

With MCP Server integration, you can create tools once in Relevance AI and use them across your entire AI ecosystem, maximizing your investment and maintaining consistency across platforms.

To set up your MCP Server:
1. Go to your Relevance AI workspace
2. Under "Tools", navigate to "Export Tools" → "MCP Server"
3. Select the tools you want to share and click "Generate MCP Server Configuration"
4. Copy your MCP configuration into your preferred client:
  - For Cursor: Open Cursor settings → MCP tab → "Add new MCP server" → Paste into your mcp.json file

Start expanding your AI toolkit across platforms today!

Google Gemini 2.5 Pro Experimental: Advanced AI Power for Your Workflows

You can now integrate Google's cutting-edge Gemini 2.5 Pro Experimental model directly into your LLM Steps!

Access Google's latest AI breakthrough as a fully integrated LLM Step model. This release brings Google's most advanced large language model capabilities to your workflows, offering impressive performance based on recent benchmarks while maintaining complete control through your own API key.

➡️ Access cutting-edge AI capabilities – Leverage Google's most advanced model for superior results

➡️ Bring your own API key – Maintain full control over usage and billing through your Google account

➡️ Experiment in development – Test and refine your implementations before moving to production

➡️ Benchmark-leading performance – Benefit from Google's latest advancements in AI reasoning and generation

With Gemini 2.5 Pro Experimental, you can push the boundaries of what's possible in your AI applications while working with a model that's showing impressive results in benchmark testing.

Keen to power your agents with Gemini 2.5? 👇

To use it in Relevance, you’ll need to bring-your-own API key (for now!)

To access this feature, go to the LLM Step configuration and select "Google Gemini 2.5 Pro Experimental" from the model options.

If you're interested in trying out Relevance AI and Gemini, you can sign up to get started or book a demo to see it in action.

Prompt Comments: Add Notes to Your Agent and Tool Instruction

You can now add comments directly within your agent and tool prompts without affecting LLM processing!

Comments let you document your thinking, explain prompt engineering decisions, and collaborate more effectively with your team. These comments are automatically removed before sending instructions to the LLM, giving you a clean way to annotate your prompts without impacting performance.

✅ Document your prompt engineering decisions – Explain why you chose specific wording or parameters

✅ Leave notes for collaborators – Help team members understand your prompt structure and reasoning

✅ Add reminders for yourself – Track what you've tried and what works best

✅ Improve prompt maintainability – Make complex prompts easier to understand and update

✅ Streamline collaboration – Share knowledge about prompt design without cluttering instructions

To add comments to any prompt, simply click the "/" button while editing agent or tool instructions and select “Comment" from the menu.

How it works:
1️⃣ While editing an instruction, click “/**”
2️⃣ Select “Comment” from the menu
3️⃣ Type your note—your logic, your reminder, your prompt tip
4️⃣ The comment is automatically removed before the LLM sees it

With comments, you can build more maintainable, collaborative, and well-documented AI systems while keeping your actual LLM instructions clean and focused.

Experience the most powerful agent prompt editor in the industry today!

A Completely Redesigned Template Page

You can now build custom AI agents more intuitively with our completely redesigned template page!

We've refreshed the template page experience while maintaining all the functionality you love. The new design puts greater emphasis on effortless agent creation with Invent, making it simpler to visualize and customize your AI solutions. Clean layouts and improved visual hierarchy guide you through the creation process with confidence.

➡️ Clearer visual hierarchy – Find what you need faster with improved organization

➡️ Enhanced template browsing – Discover the perfect starting point for your custom agent

➡️ Streamlined customization – Modify templates with fewer clicks and more intuitive controls

➡️ Better visualization – See how your agent will function before deployment

➡️ Same powerful functionality – Enjoy all the capabilities you rely on in a more accessible format

With the redesigned template page, you can create sophisticated AI agents in less time, allowing your team to deploy custom solutions faster and with greater confidence.

To access the new template page, simply navigate to the Templates section from the left-hand menu.

Start building your perfect AI agent with our refreshed template experience today!

Folders: Organize Your Agents with Drag-and-Drop Simplicity

‍You can now organize your agents into custom folders for better workspace management and improved productivity!

Folders give you a simple yet powerful way to structure your growing collection of agents. Create logical groupings, drag and drop agents between folders, and maintain a clean, organized workspace that makes finding and managing your agents effortless.

➡️ Create custom folders - Establish logical categories for your different agent types

➡️ Drag and drop organization - Easily move agents between folders with intuitive controls

➡️ Rename folders anytime - Adapt your organizational system as your needs evolve

➡️ Delete folders when needed - Remove obsolete categories while preserving your agents

➡️ Streamline your workflow - Find the right agent quickly when you need it most

With Folders, you can transform a cluttered agent workspace into a well-organized system that helps your team work more efficiently and locate critical agents faster.

To use Folders, go to your agents page under the left hand side bar, then 'Add Folder'.

Start organizing your agents today and experience a cleaner, more efficient workspace!

Duplicate Triggers: Clone Your Existing Triggers in Seconds

You can now create exact copies of your triggers with just a few clicks, saving valuable setup time!

The new Duplicate Triggers feature lets you quickly replicate any existing trigger configuration without starting from scratch. When you need multiple similar triggers, simply use the dropdown menu to create an identical copy that you can then customize as needed.

➡️ Save time on repetitive setup - Clone complex trigger configurations instantly

➡️ Maintain consistency - Ensure identical settings across related triggers

➡️ Reduce errors - Eliminate mistakes that come from manual recreation

➡️ Streamline workflows - Create variations of successful triggers without rebuilding

With Duplicate Triggers, you can rapidly scale your automation workflows while maintaining perfect consistency across your trigger configurations.

If you're interested in duplicating any existing trigger, it’s now live in Agent Settings > Agent Profile > Triggers > Duplicate.

To duplicate a trigger, simply click on the 3 dots menu on any existing trigger and select the "Duplicate" option. Try it out today!

Redesigned "Add Step" Experience: Find and Use Tools Faster

You can now discover and add steps to your tools with a completely redesigned, more intuitive interface!

The reimagined "Add Step" experience makes building powerful tools easier than ever. We've reorganized everything to help you quickly find exactly what you need, whether it's your own custom tools, Relevance-built tools, or community-created solutions.

➡️ Use your own tools as steps - Easily incorporate any of your existing tools as building blocks

➡️ Access community tools - Leverage marketplace tools published by Relevance and community members (coming soon!)

➡️ Navigate by integrations - Find steps that connect with specific platforms and services

➡️ Browse by use case - Discover steps organized by common workflows and purposes

➡️ Build more efficiently - Spend less time searching and more time creating with our streamlined interface

With the redesigned "Add Step" experience, you can build more sophisticated tools faster by leveraging the collective intelligence of your own work and the broader community.

To explore the new interface, open any tool in the builder and click the "+ Add Step" button to add a new step.

Start building better tools with our improved "Add Step" experience today!

Tool Version Control: Save and Track Changes to Your Tools

You can now save your tools as drafts, track changes, and revert to previous versions when needed!

Version Control allows you to save tool versions before going live, track change history, and revert to older versions when necessary. Each version can be named and documented, providing clear visibility into tool modifications.

➡️ Prevent accidental changes – Save tools as drafts before making them live.

➡️ Track modifications – See who made changes and when.

➡️ Revert when needed – Roll back to previous versions to restore functionality.

➡️ Maintain clarity – Add names and descriptions to each version for documentation.

With Tool Version Control, you can safeguard your tool configurations, prevent accidental overwrites, and ensure smooth collaboration within your team.

To find version control for a tool, go to a tool, then go to ‘Build’  > ‘Show version history’.

Start managing your tool versions today!

Your AI agents can now run automatically on a recurring schedule—daily, weekly, monthly, or even on specific dates. No more manual triggering or forgetting important tasks!

How it works:

1️⃣ Go to ‘Edit Agent’

2️⃣ Select ‘Recurring Schedule’

3️⃣ Set the perfect cadence for your workflows

Use Cases:

✅ Automate daily reports (e.g., receive a Hacker News summary every morning)

✅ Schedule weekly lead generation outreach without manual intervention

✅ Trigger monthly performance reviews with AI-generated insights

✅ Set reminders for annual contract renewals and compliance tasks

With Recurring Schedules, your agents stay proactive—automating key workflows, reducing manual setup, and ensuring important tasks never slip through the cracks.

This is so much more than a simple reminder—it's true automation that integrates into your AI workflows, ensuring critical processes happen on time, every time. Another enterprise-ready feature built into Relevance AI’s Agent OS—giving your team the tools to automate, scale, and execute your AI workforce with confidence.

If you're interested in trying out Relevance AI and triggering an agent with a recurring schedule, it’s now live in Agent Settings > Recurring Schedule. Try it out today!

You can now use OpenAI's GPT-4.5 as an agent model in Relevance AI, giving you more flexibility in selecting the right model for your use case. It’s the latest and most advanced model—powerful, capable… and according to our engineers, insanely expensive.

What this means for you:

• GPT-4.5 is now available in model selection
• Expect cutting-edge performance—but at a premium
• Choose wisely based on your use case

Heads-up: Costs are significantly higher, so keep that in mind when using it in high-volume workflows.

To get started, select OpenAI GPT-4.5 in your agent settings and test how it fits into your workflows.  

If you're interested in trying out Relevance AI and OpenAI GPT-4.5, you can sign up to get started or book a demo to see it in action.

Project Snippets: Reusable Text Variables for Your Tools & Agents

Managing shared text across multiple agents and tools just got way easier!  

Introducing ‘Project Snippets’—a centralized way to store and reference reusable text in your Relevance AI workspace.  

With snippets, you can:  

✅ Store common strings (e.g., company names, greetings, standard messages) in one place

✅ Use them anywhere a variable is accepted (e.g., agents, tool inputs)  

✅ Avoid redundant updates—edit once, update everywhere

✅ Eliminate 'prop-drilling' by making shared text easily accessible  

How it works:  

Define a snippet and reference it using the `snippets.` prefix. Example: `{{ snippets.company_name }}`  

This means you can update once and apply everywhere—no more manually changing the same text across multiple tools!

You can find Snippets under the left hand side bar. Try it today and simplify your workflow!

You can now use Anthropic's Claude 3.7 Sonnet as an agent model in Relevance AI, giving you more flexibility in selecting the right model for your use case.  

To get started, select Claude 3.7 Sonnet in your agent settings and test how it fits into your workflows.  

Alongside this release, Anthropic also launched Claude Code—its first agentic coding tool. Our lead AI engineer, Aman Arora, put it to the test with the Relevance AI SDK, and the results were impressive:

➡️ Generated a 1,300+ LOC pull request with unit tests for the Relevance AI SDK—all without Aman writing a single line of code
➡️ Understood our public repo in minutes, following existing code patterns without explicit instructions
➡️ Ran tests, fixed errors, and created a PR—iterating on feedback and automatically resolving issues
➡️ Installed pytest-asyncio on its own to test async functions, demonstrating strong contextual reasoning
➡️ PR cost: $3.30 USD—a glimpse into the efficiency of agentic coding

If you're interested in trying out Relevance AI and Claude, you can sign up to get started or book a demo to see it in action.

Annual Plans Now Available: Save 10% with Yearly Billing

Relevance AI now offers annual subscription plans, giving you more flexibility and better value.  

With annual billing, you get:

✅ 10% discount compared to monthly plans  

✅ 12 months’ worth of credits upfront

✅ Longer validity for purchased top-ups  

✅ Flexible upgrade & downgrade options

How it works:

- If you upgrade your plan, the change takes effect immediately  

- If you downgrade or switch to a monthly plan, changes happen at the end of your billing cycle  

- If you upgrade your plan, any unused credits from an annual plan will be refunded when switching from yearly to monthly  

- On an annual plan, you can still buy top-up credits - what's good is they'll take longer to expire because of the yearly reset

Click on ‘Manage Plan’ to switch to annual billing today!

Edit & Reschedule Scheduled Messages with Ease

We’ve introduced an update to Schedule Messages, making it easier to edit and reschedule scheduled messages directly in Task View.

When managing scheduled messages, you often need to make quick changes—whether it's adjusting the content or rescheduling the send time. Previously, this meant canceling and recreating messages from scratch, but not anymore.

Now, you can:

➡️ Edit the content of a scheduled message before it sends

➡️ Reschedule a message without needing to cancel and recreate it

This means more flexibility and a smoother workflow experience.

To edit a scheduled message, simply navigate to Task View, make your changes, and save—no need to cancel and restart.

Next time you need to adjust a scheduled message, try it out directly in Task View!

Custom Tool Outputs: More Control Over How Data is Rendered

We now have the ability to customize tool outputs, allowing you to manually define how data is displayed instead of relying on automatic formatting.  

When building AI workflows, flexibility in data presentation is key. This update brings 8 Rendering Options:

✅ Auto

✅ Raw

✅ JSON

✅ Table

✅ Image

✅ HTML

✅ Markdown

✅ Hide  

These changes can be seen in three different areas:

• Agents
  • New agent task action view UI displays the selected output format.
  • Option to view the tool output in the agent timeline through the dropdown.
• Tool builder: Users can manually configure output formatting in tool configuration settings.  
  • To get started, head to the final tool output settings → configure → select manual output → add variable(s) → choose edit.
    

Before applying these settings, you’ll have the opportunity to preview how each rendering option affects the final output.  

This update provides greater flexibility in presenting data, ensuring tool outputs are displayed in the most relevant format for your workflow.  

If you're interested in trying out Relevance AI and Custom Tool Outputs, you can sign up to get started or book a demo to see it in action.

Now in Relevance AI: Attachments in Agent-Generated Emails

You can now add attachments to emails sent by AI agents in Relevance AI, allowing for more complete and professional communication.

When automating emails, you often need a way to send essential documents, reports, and media files, such as:

✅ Sending invoices and contracts as PDFs
✅ Sharing reports in CSV format
✅ Including images for marketing campaigns
✅ Attaching videos for client communications
✅ And much more!

With this update, your AI agents can now handle attachments seamlessly, eliminating manual steps and ensuring critical files are sent along with automated emails.

This applies to the following tool steps: ‘Send Email,’ ‘Send Gmail email,’ or ‘Send Outlook email’.

Here’s how it works:
1️⃣ Upload your file using the “File to URL” input, or generate a temporary link with the Python tool step
2️⃣ In the top right of your send email tool step, click the cog icon to open "Advanced Settings"
3️⃣ In the ‘File Attachments’ section, enter each "file name" and "download link" pair inside a JSON object (e.g., “file1.txt”: “https://example.com/file1.txt”)

Before sending, you’ll have the opportunity to review all attachment details, ensuring your files are correctly included.

This feature enhances AI-driven email automation by making it more complete, efficient, and professional—perfect for automated reporting, customer communications, and more.

If you're interested in trying out the new email attachment functionality, you can sign up to get started or book a demo to see it in action.

Big updates just dropped! Your AI agents can now connect and react to more platforms, making automation even more powerful.  

When automating workflows, you often need seamless integration across multiple tools.

These new updates enable:

✅ Automating actions based on ZoomInfo Intent Topics. Agents can now be triggered by ZoomInfo, perfect for customers leveraging ZoomInfo Intent Topics to stay ahead of key signals.

✅ Triggering AI workflows directly from Telegram messages. Your agents can now integrate seamlessly with Telegram!

• Trigger agents from Telegram messages
• Search through your message history
• Send messages
• …and more!

✅ Running AI workflows before, after, or exactly at a Google Calendar event. Set your AI agent in motion before, after, or exactly at the time of a Google Calendar event—perfect for automating workflows around meetings and key events.

✅ Backfilling Salesforce data with a One-Off Sync. Need to backfill Salesforce tasks or pull data you missed? Now you can! Just go to Advanced Settings > Execute Once Off Sync to run a single-time sync (excluding LIMIT queries).

• Fetches historical Salesforce data
• Ideal for backfilling missed records

✅ Generating and publishing LinkedIn posts from AI agents. Agents can now generate and publish LinkedIn posts directly.

✅ Using the Google Sheets API to send, retrieve, and update data. Easily send, retrieve, and update data within Sheets.

✨ To get started, explore the new integrations in your agent settings.  

Before enabling new triggers, you’ll have the opportunity to review automation details to ensure they align with your workflow needs.  

These enhancements make automation more connected, responsive, and intelligent—allowing your AI agents to work seamlessly across different tools.  

If you're interested in trying out Relevance AI and OpenAI o3 Mini, you can sign up to get started or book a demo to see it in action.

You can now use OpenAI o3 Mini as an agent model in Relevance AI, giving you more flexibility in selecting the right model for your use case.  

When working with AI-driven workflows, you often need an efficient, cost-effective model for tasks like:  

➡️ Running lightweight AI processes  

➡️  Generating responses at a lower cost  

➡️ Balancing model performance with budget optimization  

With OpenAI o3 Mini, your AI agents now have a new model option that improves efficiency while keeping costs under control.  

To get started, select OpenAI o3 Mini in your agent settings and test how it fits into your workflows.  

If you're interested in trying out Relevance AI and OpenAI o3 Mini, you can sign up to get started or book a demo to see it in action.

Your Agent Generator 'Gen' has leveled up, now allowing you to simulate the entire agent creation process in real time.  

When building AI agents, you often need a way to preview how they function before deploying them. With this new update, you can:  

✅ Run an End-to-End Simulation – Watch your AI agent operate before launch

✅ Gain Real-Time Insights – See how your AI agent performs at every step  

✅ Preview Tools & Capabilities – Review every aspect of your agent’s abilities in action

To get started, type your needs into the "I want an agent that..." field, such as:  

📌 "Generates employee satisfaction surveys"

Sit back and watch as your AI agent runs through every step of its workflow in real time.

This update makes agent building more transparent and intuitive, ensuring your AI works exactly as expected before going live.  

If you're interested in trying out the new Agent Inventor, you can sign up to get started or book a demo to see it in action.

We’ve improved our tools library—the skills your AI agents rely on—to help you build smarter, more capable agents.  

When creating AI workflows, having well-optimized tools is critical. This update brings:  

1️⃣ Smarter tools – All tools now follow our Tool Style Guide for better clarity, names, and discoverability.  

2️⃣ Enhanced performance – Default LLMs have been upgraded, delivering **faster, better results at reduced costs**.  

3️⃣ Expanded tool library – 31 brand-new tools added, including 5 tailored for **Google Calendar**.  

4️⃣ More customization – 19 new tool steps provide even greater flexibility to build and innovate.  

To get started, explore the updated tool library inside Relevance AI.  

This update makes AI tool-building more intuitive, powerful, and customizable than ever.  

📖 Learn more in our Tool Style Guide.

The wait is over. Building AI agents doesn’t have to be complicated. With Agent Generator, anyone can get started.  

This is for you if:

- You’ve thought, “AI agent building isn’t for me.” 🤷

- You’re unsure where to start 🤔

- You learn by doing and want an easy, hands-on approach 🙌

Agent Generator solves this by allowing you to describe what you need in plain English, instantly generating a blueprint to set up your AI agent.  

To get started, simply type your needs into the “I want an agent that…” field and watch as your personalized agent blueprint is created.  

Keen to power your agent building with Gen? 👇

For now, Agent Generator provides a fully personalized framework for your AI agent, including placeholders like “Get Instagram Account Analytics” for where your AI tools go. While it doesn’t automatically create or insert the AI tools yet, you can either build them yourself or browse through available tool templates (for now). More features coming soon!

If you're interested in trying out the new Agent Inventor, you can sign up to get started or book a demo to see it in action.

New models and features have landed in Relevance AI, expanding support for advanced AI capabilities.  

When working with AI-driven applications, having optimized models and training tools is key. These new updates include:  

✅ ModernBERT for Advanced RAG – Now leveraging ModernBERT Embed (released by the answer.ai team), a model trained from ModernBERT-base, bringing new embedding advancements to AI workflows. More details on the model are available here: https://huggingface.co/nomic-ai/modernbert-embed-base

✅ Expanded DSPy Support – We've added DSPy get training data, DSPy train, and DSPy run steps to train DSPy systems for response generation based on gold set answers.  

✅ Qwen 2.5 for AI Agents – Our tool-calling model suite now includes Qwen 2.5, known for exceptional coding & tool execution performance, achieving benchmarks comparable to GPT-4o.  

To get started, explore these new models and capabilities inside Relevance AI.  

Before using these updates, you’ll have the opportunity to review model specifications and tool integrations to ensure they align with your workflows.  

These enhancements bring more power, flexibility, and precision to AI agents, making your automation workflows even stronger.  

If you're interested in learning more, you can sign up to get started or book a demo to see it in action.

OpenAI o1 is now available in Relevance AI as a text, vision, and agent model—bringing enhanced capabilities to your AI workflows.  

When working with AI-driven processes, selecting the right model is key. Here’s what’s new with OpenAI o1:  

➡️ Larger Context – Supports double the input context and 6x the output context

➡️ New Agent Behavior – Uses tools more frequently than GPT-4o

➡️  Stronger Performance – Outperforms GPT-4o in tool calling and response generation

➡️  Higher Cost Consideration – Priced ~6x higher than GPT-4o, making it ideal for high-value AI tasks

Keen to power your agents with o1? 👇

To use it in Relevance, you’ll need to bring-your-own OpenAI API key (for now!)

To get started, configure OpenAI o1 as your agent model inside Relevance AI.  

OpenAI o1 offers advanced AI power, stronger tool usage, and expanded processing capabilities, making it a valuable option for complex automation tasks.  

If you're interested in learning more, you can sign up to get started or book a demo to see it in action.

We’ve introduced Agent Chat, a sleek, customizable chat UI that allows users to engage with their Relevance AI agents in a more intuitive and interactive way.  

When deploying AI agents, having a seamless chat experience can make all the difference. This update brings:  

✅ Conversational Interface – A clean, natural chat UI for user-friendly interactions  

✅ Embed Anywhere – Easily integrate Agent Chat into websites or use the customizable chat widget

✅ Full Customization – Adjust icons, colors, and message input text to align with your brand  

✅ Flexible Use Cases – Perfect for customer support agents and FAQ-powered AI assistants

To get started, configure Agent Chat in your Relevance AI dashboard and customize the chat UI to match your workflow.  

Before embedding, be mindful that interactions consume credits from your Relevance AI account, so plan usage accordingly.

This update allows you to enhance customer interactions, provide self-service support, and create a branded AI chat experience—all in one intuitive UI.  

If you're interested in trying out Relevance AI and Agent Chat, you can sign up to get started or book a demo to see it in action.

We've completely overhauled our tool embedding system, making it more intuitive, customizable, and user-friendly.  

When integrating AI tools, you often need seamless design customization and real-time previews. This update brings:  

✅ Live Preview – See how your tool embed will look before implementation

✅ Style Customization – Set your primary color scheme and adjust the CTA text

✅ User Guidance – Add helpful tips to guide users through the tool  

✅  Enhanced UI – A refreshed, cleaner interface for a better user experience  

To get started, configure your Custom Tool Embed settings within Relevance AI.  

This update makes embedding AI tools easier, more flexible, and better tailored to your brand and user experience.  

If you're interested in trying out Relevance AI and Custom Tool Embeds, you can sign up to get started or book a demo to see it in action.

Custom Task Views

We introduced a new feature to customize agent task views, enabling better review and monitoring of agent activities.

Key Features

• Customizable Task Views: Create tailored views to focus on specific aspects of an Agentic workflow.
• View Filter Settings:
  • Access via setting icon in task view
  • Ability to create multiple custom views
  • Filter by tools and triggers
  • Name and save custom views

Benefits

• Reduces noise in task review process
• Improves client review experience
• Creates customizable command center UI
• Simplifies approval and escalation processes

‍

Example Use Cases

1. Email Communications View
   • Filter for email-related activities (Gmail, Outlook)
   • Quick overview of prospect communications
   • Streamlined review of email threads
2. Research View
   • Isolate research-related activities
   • Easy validation of prospect research
   • Focused view of research reports

‍

‍

New Agents List View

We've added a new list view for Agents.

Key Improvements:

• 📊 Unified View: Manage all agents in one streamlined view
• 🔍 Enhanced Details: Expand each agent to view connected tools and integrations
• 🔄 Smart Sorting: Order by last run, modified date, or completed tasks
• 📈 Performance Metrics: Track agent productivity.

💡 Pro Tip: Use the "Tasks Done" sorting feature to identify your top-performing agents .

‍

‍

.

‍

Our latest release includes an extremely powerful feature for debugging multi-agent systems, that underlines our commitment to being the most advanced agent platform. With Override Mode, you can mock inputs and outputs for all parts of your agent’s system.

‍

Advanced agent debugging with Override Mode

When building advanced multi-agent systems, it’s important that you’re able to test your agents efficiently.

We noticed, when observing our internal agent building squad, that this involves re-running certain tasks over and over as you make tweaks to your agent’s instructions.

This takes up a lot of time and sucks up credits, running through tools that you aren’t even testing. To help with this debugging experience, we’ve built what we call Override Mode!

Override Mode allows you to mock inputs and outputs for any of your tools or subagents. If an output is mocked, the tool or subagent won’t actually run, saving on credits and time!

You can toggle any agent into Override Mode:

‍

‍

You will be asked whether you want to clone the task into Override Mode, or just continue:

‍

‍

Note: the same task can’t exist in both normal and “Override” mode. You need to clone a task into Override Mode if you want to mock its inputs and outputs.

Once you are in Override Mode, you can click your settings cog to start configuring your overrides.

‍

‍

For inputs, we show you a form where you can force inputs to be used by the agent for the tool. This lets you control certain variables in your agents flow, if you are experimenting with something later in its flow.

It also lets you lock in certain testing variables - for example, if you’re testing a “Send email” tool, you may want to always ensure it sends the email to your test email rather than some external email.

For output mocking, you can provide a JSON object. If you mock an output, the tool won’t run and will simply return the mocked output immediately.

You can also set input/output overrides from tools or subagents that have run in your timeline. Click the three dots and set the input or output.

‍

‍

Also note that in Override Mode, you can set different Approval mode settings that will only take effect in Override Mode.

‍

‍

If a tool or subagent has mocked inputs or outputs, you will see this in the sidebar on your task view:

‍

We’ve made a few key updates to our platform in this week’s release, particularly for power users and expert agent builders!

‍

Iterate on your agent’s tools with better logging

‍

When you are working on a tool for your agent, you will often want to test the tool with inputs that your agent provided it.

‍

Previously you could do this one by one, by clicking on the tool execution and then “Test in tool builder”.  However, when wanting to test the tool against a lot of test cases, agent builders found this process extremely time consuming.

‍

We’ve shipped a feature that will make this process much easier! In the “Logs” tab in the Tool Builder, you will now see tool executions from agents.

‍

Click the “Test Input” button and it will prefill your tool with the same inputs that the agent used, making for easy testing!

‍

‍

Today’s release is headlined by some exciting upgrades to the agent building experience!

‍

Agent Builder glow up

‍

We’ve overhauled the user experience for building an agent in Relevance, making it easier to find what you need and understand how to customise it.

Everything you previously had access to is there, but just organised within a new sidebar.

‍

For example, we’ve broken up your resources in to three categories: your tools, subagents and abilities. Abilities are built in agent powers, such as task labelling, message scheduling and escalation.

‍

‍

‍

One of the biggest improvements in experience is a much clearer layout and more breathing room when configuring the tools and subagents you have attached to your agent:

‍

‍

This update is full of fun touches, such as our new agent avatar selector:

‍

‍

See before/after when you edit agent approvals

‍

Now you can see a log of what you changed when an agent asks for approval to run a tool, and you update the proposed inputs.

‍

‍

Note, you can also provide feedback about the agent’s proposed inputs more easily! We are using this data to help fine tune an agent model.

‍

Pause your tasks

‍

We’ve implemented a feature to pause tasks. This means that the task will no longer be able to receive any new messages from yourself, triggers or API.

Note, that this will not stop it finishing what it is currently doing - but gives you a way to stop it from doing anything else moving forward!

‍

‍

‍

‍

New UI for viewing your agent’s tasks

‍

What: We've revamped the task UI to give you an intuitive, clean design for viewing and managing your agent’s tasks.

‍

Why: The UI offers a streamlined layout that reduces information overload and makes it easier to understand what your agents have been working on.

‍

‍

Find anywhere your agent encounters an error

‍

What: We have a new filter type in the Activity Center, where you can filter down to tasks where an error has occurred. This means, at any point, a tool run by the agent or the agent’s LLM errored.

‍

Why: This allows you to identify problem sessions and resolve any issues, or use that as a means of improving your agent.

‍

Enhanced Import and Export for Tools

‍

What: You can now export tools into a .rai file and import them when creating a new tool.

‍

Why: This allows for seamless sharing and backing up of custom tools locally, streamlining collaboration and tool management workflows.

‍

Improved agent task search for faster workflow

‍

What: We've revamped the search engine for agent tasks.

‍

Why: We've implemented a fuzzy search text index on our database. This new system delivers an intuitive and flexible search experience so you can drill down and quickly locate the specific agent tasks you need, streamlining your workflow.

‍

More reliable and flexible task labeling

‍

What: You can now add rich descriptions to the the tags you provide to your agents for labeling tasks. This new feature gives you more flexibility and power in instructing your agents on how to use and interpret each tag. You can even set up rules and prompt for specific behaviors like mutual exclusivity, where, for example, using one tag automatically untags another related tag.

‍

Why: This depth of labeling opens up new possibilities for fine-grained task management.

‍

Project management for the AI workforce with the new Activity Centre

‍

What: We've overhauled the Activity Centre in our platform, turning it into a centralized hub with real-time dashboards and robust filtering capabilities for all important information about your agents and tasks. This powerful command centre provides an unprecedented level of visibility and control over your AI workforce's activities, making Relevance the world’s first project management platform for AI agent teams.

‍

Why: Managing a team of AI agents can be complex, with numerous tasks, projects, and status alerts to track. The new Activity Centre streamlines this process, letting you to monitor progress, identify bottlenecks, and optimize resource allocation for maximum productivity, all from a single, intuitive interface.

*** This feature is available for business and above users.

‍

A new look for the activity page

We are excited to launch a brand new activity page dashboard that gives you visibility into all of the recent work your AI agents are doing. You can view the tasks in progress, pending approvals, and completed work over customizable time ranges - last hour, last week, last 30 days etc. You can also filter and segment the tasks by agent, label, or status to hone in on what's most important. This marks the start of Relevance striving to help you better track, delegate to, and manage your AI workforce.

Key activity page features:

• See all recent tasks from your agents in one place
• Filter by status (in progress, pending approval etc)
• Filter by agent or label
• View aggregated totals of agent work over time
• Track tasks requiring your review and input

‍

A reskinned activity sidebar

In addition to the new page, we've reskinned the activity sidebar. Your notifications and settings are now conveniently accessible here, and we've also added quick access to your most recently used agents, making delegate to them faster than ever.

‍

Feedback for agents

Thumbs up if an agent response makes your day... thumbs down if something misses the mark.

We've added easy reactions so you can let us know how helpful responses have been.

We'll keep track behind the scenes and your feedback will be crucial once the data can be used to improve the underlying agent model.

With your help, our agents will get smarter and will better understand your needs.

‍

Agent teams & sub-agents

Multi-agent systems often require coordinating groups of agents with specialised roles. We're introducing Agent Teams to make this a reality!

Teams allow you to compose individual agents into a group that can coordinate and work with each other on tasks.

For example, you might assemble a team of agents that specialise in research, content writing and editing to collaborate on a blog post.

To unlock this feature, book a demo with us or upgrade to the business plan and start leveraging the full capabilities of an AI workforce.

‍

We have made it easier for users to understand and utilize variables when building or customizing their AI tools. Previously, users would often encounter errors when feeding variables of one type into inputs that required a different type. To address this, we have implemented the following enhancements:

• Clear indication of variables and their types throughout the user interface.
• Highlighting of inputs that require specific variable types.
• Clear error messages with detailed explanations and links to relevant documentation to help users rectify typing mistakes.

Variable menu improvements

The menu now previews the content of all variables, making it easier to work with long-form AI prompts. In response to user requests, the variable menu now dynamically appears underneath the cursor position.

Edit messages in Agent conversations

We are excited to introduce a highly demanded feature for AI agents. Users can now edit previously sent messages within a conversation, and our system will automatically regenerate the rest of the conversation accordingly. This feature greatly simplifies agent usage, allowing for easy debugging, testing, and correction of any mistakes made during conversations.

‍

We've made it even easier to configure AI tools with our latest update. Now, the variable menu has an expanded view that shows variables grouped together by their step. Additionally, we display a sample of the variable's value and its data type, such as string or number.

‍

Long-running tools in shareable links

We've listened to your feedback and made significant improvements to our shareable link/embeddable form feature. Previously, it was limited to tools that ran for 60 seconds or less. However, with our latest update, even tools that run for a longer duration can now be used with the public link.

‍

Reskinned Agents

We're constantly working to enhance your experience with our Agents UI, and we're excited to announce a fresh new look for it to address common issues and improve usability.

Cancel bulk runs

We understand that sometimes you may need to stop long running jobs that are performed across your dataset. That's why we've introduced a new feature that allows you to cancel your bulk tool enrichments in Data tables. With this functionality, you have the power to stop ongoing enrichments, giving you more control over your data processing.

Chat is our AI assistant that works like ChatGPT but with a few key benefits! First, none of the data is used for training and the stored history only exists for your benefit. Secondly, you can activate chains that the assistant can use as tools to augment its capabilities. Let's say you've created a chain that can search through your annual reports and answer a question, well now the AI assistant can use that as a tool if you ask it a question about the annual reports. This is all done automatically for you - just activate the chains you'd like for it to be able to access and away you go. Think of it like Plugins in ChatGPT except you can create your own, for your business needs without code.

Generate automations and AI apps using natural language with our Invent co-pilot. It can help you get started with a simple chain that you can then extend and build into a full-fledged app. Iterate after the first attempt to make it have the right inputs and prompt to meet your needs.

Our first iteration is designed to help you build single-prompt apps. It means that you don't have to copy-paste prompts into ChatGPT each time you want to use them. Instead you can launch an app you can share with your team that has a form to input your prompts.

‍

We've launched a new dashboard for our improved chain building experience. We've also implemented datasets and the ability to vectorize columns. Let us know your feedback!

Build and test your LLM chains in our low-code notebook. Drag and drop blocks from our massive library of transformations. Inspired by data-science Jupyter notebooks, run cells individually to test each step of your chain and iterate. One click deployment to API or a shareable form.

Our SDK is the framework for building LLM powered features and agents. With advanced customization, magical deployment and multi-provider support, Relevance AI makes it easy to integrate large language models into your product.

Check out the documentation to learn more!

We've shipped an end-to-end flow for setting up Ask Relevance to enable conversation customer support in your product, trained on your documentation. When setting up a new dataset, simply select the option for Ask Relevance. Alternatively, run the Enable Ask Relevance workflow on an existing dataset.