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.