Feedback

Have something to say?

Tell Runbear how they could make the product more useful to you.

Connect Runbear to Google Agent Development Kit (ADK)

Request to integrate Runbear with the Google Agent Development Kit (ADK) using a simple API or webhook-based connection. This would allow Runbear to forward Slack messages to ADK agents and relay responses back, enabling a seamless Slack interface for ADK-powered assistants. The integration should support configurable endpoint URLs, basic authentication (if needed), and payload structures compatible with ADK’s expected format. This lightweight setup would provide real-time agent interaction within Slack without requiring a full SDK integration, making it easy to maintain and extend.

Ethen Amezquita 11 days ago

Persistent Chain-of-Thought (CoT) and Action Logs for Debugging

Currently, during a run, the Chain-of-Thought (CoT) is only visible while the model is thinking but disappears once the run is complete, making it impossible to review or debug the model’s reasoning. I am requesting that CoT be persistently logged and saved per run, along with a full log of all actions taken (tool calls, API requests, etc). This would allow users to inspect exactly how and why a task succeeded or failed, improve prompt tuning, and diagnose failures more effectively. Having a permanent, viewable record of both CoT and actions would significantly improve transparency, debugging, and agent development workflows.

Ethen Amezquita 19 days ago

In Progress

Website as a Knowledge base

Many customers have asked for the ability to use their public-facing documentation and FAQ pages as knowledge sources for their AI agents. In response to this demand, we are working on a feature that allows you to sync a website—including its subpages—so that your AI Agent can access and utilize the content as part of its knowledge base. This will make it easier for teams to keep their agents up to date with the latest product information, policies, and support content without needing to duplicate efforts in multiple systems.

Joel Lim 24 days ago

Completed

Ability to Search Google Drive Files, Navigate and See folder names / path, Filter

Advanced users of assistants end up having a significant number of files and folders shared with their AI assistants. This becomes unwieldy to manage / maintain as assistants and usage matures. Providing the ability to navigate, search/filter, and see folder names / created / updates and file paths for shared files and folders within the google drive integration enables the ability to scale and manage the assistant’s knowledge base. Note that for AI advisory businesses managing client’s AI’s for them would also include the ability to see the Company/Folder path and filter to ensure they can easily manage multiple clients safely without accidentally sharing incorrect files or folders to other clients’ Assistants.

Antoni Tisot 6 months ago

1

Completed

Share entire Google Drive folder with Assistants > Automatically adds files to assistant's knowledge base

Enable the ability to share an entire folder with an assistant. 1. Folder is shared via google drive etc… 2. User selects folder within Runbear Drive integration UI > Folder and all content of folder is then automatically shared with Assistant (including any new files added in future) This enables easier maintenance of the knowledge base by businesses, as once a folder is designated, team members with appropriate permissions can then add new files to these folders that the assistant can access without having to request Runbear Admin to add new files to every assistant. Example: Business defines a google drive folder for ‘Standard Operating Procedures’ for the Training / SOP AI assistant. Any new SOPs that are created and added to the folder are automatically added to the Assistant’s knowledge ensuring the assistant is always up to date on the latest SOPs and reducing the Admin required to manage assistant’s knowledge base.

Antoni Tisot 6 months ago

2

Zendesk Chatbot Integration

Currently, Runbear Zendesk integration supports executing AI on every new inquiry. However, more customization options are needed to utilize AI better. For example, agents want to trigger AI manually by mentioning a chatbot. Requirements Support invoking AI by mentioning it. Support invoking AI that understands conversations on each ticket. Optional Support using Runbear on the sidebar instead of inside the chat panel.

Snow W. Lee (Sungwon) 9 months ago

Other Connections (Box?) for File Search

Google Drive and Confluence are great, but the ability to support other storage solutions would be great. I have no idea how hard it is to make happen, but the ability to connect to Box folders or even OneDrive/Sharepoint folders would be a huge improvement for our ability to easily keep assistants up-to-date on the latest information without adding another step to the 'where do I put announcements and new info’ process.

connormckinnis 9 months ago

1

Scheduled Trigger

We have received requests to support triggering Runbear based on a schedule, rather than directly mentioning @Runbear or using other trigger conditions. This feature will enable users to create new use cases, such as a daily digest bot. Scheduled triggers will provide more flexibility and automation options, allowing you to set up regular updates and reports without manual intervention.

Liam Hwang 10 months ago

1