Overview

The new Agents & Assistants feature provides a foundational framework for developers to build customized AI agents within Slack, introducing key events and APIs for interacting with Slack’s new AI container. The AI Agent container enables customers to connect their custom LLMs to meet their organization’s unique needs. Whether it’s automating workflows, answering queries, or providing intelligent insights, this new surface adapts to specific business requirements meeting the needs of mid-market and enterprise customers. Customers can either build their own AI agent or work with Global System Integrators (GSIs) to create enterprise-level AI solutions tailored to their needs.

Key Features

• New entry point: AI Agents are easily accessible from the top of the Slack web client, allowing users to toggle between multiple agents as needed.
• Split-view: Users can interact with the AI Agent in a persistent split-view window, enabling them to multitask while engaging with the agent. The split-view remains open as users navigate across Slack.
• Suggested prompts: AI Agents leverage context to provide dynamic, relevant prompts based on user activity in Slack channels and DMs.
• Loading state: New shimmer UX and typing status indicators help set user expectations, showing when the agent is processing and working on a response.
• Updated App Home: The AI Agent’s landing page now includes a Chat tab for ongoing conversations and a History tab making it easy for users to revisit past interactions, creating a more cohesive user experience. Developers can also customize thread titles to summarize key topics.

Customer Benefits

• Bring Your Own Large Language Model (BYOLLM): Flexibility to use custom LLMs for creating personalized AI Agents.
• Reusable interface: The AI agent container’s intuitive and flexible interface allows seamless integration with custom business workflows and logic.
• Improved UX: A streamlined, multitasking-friendly interface allows users to interact with AI Agents without disrupting their work.
• Centralized conversation management: Users can easily track and reference past AI Agent interactions, ensuring better continuity in ongoing projects and discussions.

Technical Implementation Details

You can find the main developer documentation at https://api.slack.com/docs/apps/ai

App agents and assistants themselves are not an LLM; rather, they give you the tools and interface to best integrate an LLM for use in Slack. Developers who are familiar with creating conversational chatbots in Slack (AI-powered or otherwise) should not have much difficulty taking advantage of the new features that make Slack apps more discoverable, accessible, and message thread-friendly for users. The new surface area is a natural extension of how developers previously integrated bots into Slack, only introducing a few new events, endpoints, and concepts that power the new experience.

The app assistant flow

1. Listen for the assistant_thread_started event and inspect for the context
2. Respond to the assistant_thread_started event with suggested prompts
3. Listen for the message.im event and set a typing status
4. Respond to the message.im event with the desired chat response

Developer Tools with Assistant support

SDKs

• Node Slack SDK
  @slack/web-api version 6.13.0 now includes support for AI Assistants & Agents. Release notes
• Python Slack SDK
  Version 3.33.0 now includes support for assistant.threads.* APIs. Release notes

Bolt Framework

• Python
  Support released in version 1.21.1 (documentation)
• Java
  Support released in version 1.44.0 (documentation)
• JavaScript
  Support released in version 4.0.0 (documentation)

Sample Code

• https://github.com/slack-samples/bolt-python-assistant-template
• https://github.com/slack-samples/bolt-python-ai-chatbot

Helpful Links

• Developer API documentation
• Slack Help Center user documentation
• Slack Marketplace App Category

Demo Video

Watch the demo video to see how the AI Agents feature makes Slack the conversational interface for AI.

Overview

The AI-Optimized Incident Management solution helps organizations streamline the process of incident reporting and resolution using Slack’s Workflow Builder, custom workflow steps, Slack Canvas, and OpenAI’s ChatGPT. By integrating these tools, this solution automates bug creation in Jira Cloud, generates AI-driven incident summaries, and facilitates comprehensive documentation, all within Slack. This enables teams to enhance collaboration, minimize downtime, and standardize their incident management practices. 

Key Features

• Automated Incident Reporting: Quickly report incidents and automatically create Jira issues directly from Slack, reducing manual effort and increasing accuracy.
• Custom Workflow Steps: Design and implement reusable, customized steps tailored to specific incident management workflows, enhancing flexibility.
• AI-Generated Summaries and Root Cause Analysis: Leverage ChatGPT to provide instant, AI-driven insights into incident details and causes, accelerating resolution times.
• Slack Canvas for Documentation: Use Slack Canvas to create structured, easily accessible incident reports, ensuring comprehensive documentation for future reference.

Customer Benefits

• Faster Incident Resolution: Automate repetitive tasks and streamline communication to resolve incidents more quickly.
• Improved Collaboration: Enhance cross-functional collaboration by centralizing incident management within Slack.
• Standardized Documentation: Maintain consistent, comprehensive records that are easily retrievable for audits and reviews.
• Data-Driven Decision-Making: Utilize AI-generated insights to improve decision-making and proactively address issues. 
  

Technical Implementation Details

• Infrastructure: This solution requires an external hosting environment, such as Heroku, to run custom code.
• APIs and Integrations: Requires integration with Jira Cloud and OpenAI API for AI functionalities. Ensure you have the necessary API keys and permissions configured.
• Source Code: The complete source code and setup guide are available on GitHub. [View Source Code on GitHub].

Demo Video

Watch the demo to see how the AI-Optimized Incident Management solution transforms your incident handling processes. 

Overview

The Google Drive Expense Logging solution simplifies the process of submitting and managing business expenses within Slack. By integrating Slack’s Workflow Builder with Google Drive and Google Sheets, this solution allows users to submit expenses, upload receipts, and log details directly within Slack, enhancing efficiency and ensuring accurate expense tracking.

Key Features

• Direct Google Drive Integration: Users can upload receipts and invoices directly to Google Drive from Slack, simplifying expense submission.
• Automated Logging in Google Sheets: Automatically logs expense details into Google Sheets, integrating seamlessly with existing financial workflows.
• Customizable Workflows: Adaptable workflows that can be tailored to the specific needs of your finance team. 
  

Customer Benefits

• Streamlined Expense Submission: Reduce the time and effort required to log expenses, making it easier for employees to comply with expense policies.
• Accurate Record-Keeping: Maintain precise and organized records of all expenses, improving transparency and accountability.
• Integration with Existing Tools: Leverage existing investments in Google Drive and Google Sheets, reducing the need for additional software.

Technical Implementation Details

• Infrastructure: Fully hosted within Slack, requiring no external infrastructure.
• OAuth and API Setup: Requires OAuth setup in Google Cloud for authentication and API access to Google Drive and Sheets.
• Source Code: Available on GitHub for review and customization

Demo Video

Watch the demo to see how the Google Drive Expense Logging solution can improve your expense management process.