Scalable Collaboration of Multiple AI Agents in Workspaces

Ever wondered how to make AI agents actually useful in your daily work? While there’s been lots of buzz around AI automation, most solutions still struggle with a fundamental problem: they don’t fit naturally into how we actually work. That’s where SlackAgents comes in.

We present SlackAgents, a multi-agent library for scalable management and collaboration of AI agents on Slack. As an agentic layer developed upon the Slack platform, the framework offers instant AI integration into organizational workflows, enabling continuous improvement through daily use. It also leverages Slack’s extensive features to enable AI-powered automation of real daily tasks. Furthermore, SlackAgents facilitates scalable collaboration, allowing for effective communication and task orchestration. Our solution bridges existing gaps in AI agent management, offering a robust platform for developing, deploying and managing AI agents for workplace environments.

What Makes SlackAgents Different?

Here is a comparison of features supported by SlackAgents library vs existing libraries in terms of Multiple Agents: multi-agent orchestration; Workspace Automation: native Slack workspace feature support and automation; Scalable Collaboration: support for vast number of agents for collaborative task solving; Admin Management: interfaces for human supervisors to monitor and intervene; Market Distribution: instant deployment and distribution to workspaces via the Slack Marketplace.

Our solution is a multi-agent library as an agentic layer leveraging the Slack infrastructure, the most widely used messaging and collaboration platform for corporate workspaces. The marriage of multi-agent framework with Slack can immediately bring the following benefits:

• Scalable Collaboration: multi-agent communication and task orchestration are handled by various types of conversation sessions across threads and channels of the Slack messaging system.
• Slack-Powered Automation: interfaces AI agents to various Slack features and visual components, such as canvas, bookmarks, workflows, notifications, etc., incentivizing developers to build AI agents that can control Slack for automating real daily work and tasks;
• Workspace Integration: enables developers to use every AI agent in the existing workflows, ensuring immediate deployment and continuous improvement through daily interactions. The agent can be easily distributed to the public and other Slack workspaces;

AI for IT Operations

Modern cloud applications typically follow a network topology which consists of multiple interconnected services with complex dependencies. The problem of localizing the root cause of failure during a throttle incident is challenging: a fault in a service will be propagated to all its parent services. Therefore, when an outlier is detected at the organization level, multiple metrics could be detected as abnormal at the same time, and it is difficult to find the culprit.

The Contributing Factor Analysis approach solves the challenge by incorporating causal discovery (CD) and causal inference (CI) into analysis, which treats the failure as an intervention on the root cause nodes of the causal graph or Baysian network. The algorithm recognizes a minimal set of intervention targets in the graph, such that the data during normal periods can be converted into the data during incident periods, by propagating the intervention through the discovered causal graph.

We consider the metrics (e.g., dbCPUtime) of each logRecordType or URI pattern as random variables in the graph. We use time-series causal discovery algorithms to: Detect a minimal set of nodes in the graph, whose trend or values are significantly changed before and after the anomaly is fired, as the root causes of the org anomaly; Quantify the contribution of each root cause by calculating how much the trends or values need to be changed, so that the normal data can be converted into data in incident periods.

Solution

We developed a scalable and efficient causal discovery framework, which is able to handle the large-scale graph and time-series data. The key idea is to decompose the causal attribution problem into a set of smaller subproblems, which can be solved in parallel. We also develop a novel optimization algorithm to further improve the efficiency. Check out our library for more details.