Changelog

An image of this changelog

Better typing for inputs and variables

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.

Other improvements

  • Bulk run improvements

Fixes

An image of this changelog

Better variable menu

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.

Screenshot of agent conversation

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.

Screenshot of data table cancel option

Other improvements

  • Smoother animations

Fixes

An image of this changelog

Private chat assistant with access to your chains

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.

Other improvements

  • Onboarding updated to include better role questions
  • Templates can now be searched semantically
  • Added categorisation to templates
  • Added starter videos to chain builder

Fixes

An image of this changelog

Invent apps

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.

Other improvements

  • Support for executing long-running chains without timing out

Fixes

An image of this changelog

New dataset and chain building dashboard

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!

Other improvements

  • Templates for building chains in one click
  • More warnings around inputs in chains
  • Better empty states

Fixes

  • Fix overly strict schema of JSON input in chain
  • Fix loading templates while not in US region
An image of this changelog

The low-code Notebook for building chains

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.

Other improvements

Fixes

An image of this changelog

Our SDK for building LLM features in your product

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!

Other improvements

  • Also shipped some great documentation and examples for the SDK

Fixes

An image of this changelog

Ask Relevance for supporting your customers

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.

Other improvements

  • Persisting state of your dataset sidebar
  • Better UI for creating dataset based on integrations
  • Handle PDFs as part of our Interview AI transcript view
  • New "Support" option for better in-app support from our team

Fixes

  • Fix highlighting for One To Many clustering
  • Fix renaming of columns during upload
  • Fix copy link for shared dashboards
  • Fix "frequency as percentage" toggle in charts
  • Fix step ordering on some complex workflows

The home of the AI workforce

Get started with Relevance AI today