Integrate a slack-native AI agent

Unify company knowledge with slack-native AI agents

is a Slack-native AI agent that you use to unify the knowledge in your company. This includes your Slack history, docs, GitHub repositories, Salesforce and so on. You use your to get instant answers for real business, technical, and operations questions in your Slack channels.

can handle concurrent conversations with enterprise-grade reliability. They have the following features:

• Durable and atomic event handling: -backed event claiming ensures exactly-once processing, even under high concurrency and failure conditions
• Bounded concurrency: fixed worker pools prevent resource exhaustion while maintaining predictable performance under load
• Immediate event processing: provide real-time responsiveness. Events are processed within milliseconds of arrival rather than waiting for polling cycles
• Resilient retry logic: automatic retry with visibility thresholds, plus stuck or expired event cleanup
• Horizontal scalability: run multiple instances simultaneously with coordinated work distribution across all instances
• AI-Powered Responses: use the AI model of your choice, you can also integrate with MCP servers
• Extensible architecture: zero code integration for basic agents. For more specialized use cases, easily customize your agent using Jinja templates
• Complete observability: detailed tracing of event flow, worker activity, and database operations with full Logfire instrumentation

This page shows you how to install the , connect to the MCP server, and customize prompts for your specific needs.

Prerequisites

To follow the procedure on this page you need to:

• Create a target .

  This procedure also works for .

• Install the uv package manager
• Get an Anthropic API key
• Optional: get a Logfire token

Create a Slack app

Before installing , you need to create a Slack app that the will connect to. This app provides the security tokens for Slack integration with your :

1. Create a manifest for your Slack App

   1. In a temporary directory, download the Slack manifest template:

      curl -O https://raw.githubusercontent.com/timescale/tiger-agents-for-work/main/slack-manifest.json
      

   2. Edit slack-manifest.json and customize your name and description of your Slack App. For example:

      "display_information": {
        "name": "Tiger Agent",
        "description": "Tiger AI Agent helps you easily access your business information, and tune your Tiger services",
        "background_color": "#000000"
      },
      "features": {
        "bot_user": {
          "display_name": "Tiger Agent",
          "always_online": true
        }
      },
      

   3. Copy the contents of slack-manifest.json to the clipboard:

      cat slack-manifest.json| pbcopy
      

2. Create the Slack app

   1. Go to api.slack.com/apps.
   2. Click Create New App.
   3. Select From a manifest.
   4. Choose your workspace, then click Next.
   5. Paste the contents of slack-manifest.json and click Next.
   6. Click Create.

3. Generate an app-level token

   1. In your app settings, go to Basic Information.
   2. Scroll to App-Level Tokens.
   3. Click Generate Token and Scopes.
   4. Add a Token Name, then click Add Scope, add connections:write then click Generate.
   5. Copy the xapp-* token locally and click Done.

4. Install your app to a Slack workspace

   1. In the sidebar, under Settings, click Install App.
   2. Click Install to <workspace name>, then click Allow.
   3. Copy the xoxb- Bot User OAuth Token locally.

You have created a Slack app and obtained the necessary tokens for integration.

Install and configure your instance

are a production-ready library and CLI written in Python that you use to create Slack-native AI agents. This section shows you how to configure a to connect to your Slack app, and give it access to your data and analytics stored in .

1. Create a project directory

   mkdir my-tiger-agent
   cd my-tiger-agent
   

2. Create a environment with your Slack, AI Assistant, and database configuration

   1. Download .env.sample to a local .env file:
   curl -L -o .env https://raw.githubusercontent.com/timescale/tiger-agent/refs/heads/main/.env.sample
   

   1. In .env, add your Slack tokens and Anthropic API key:
   # Slack tokens (from the Slack app you created)
   SLACK_APP_TOKEN=xapp-your-app-token
   SLACK_BOT_TOKEN=xoxb-your-bot-token
   
   # Anthropic API key
   ANTHROPIC_API_KEY=sk-ant-your-api-key
   
   # Optional: Logfire token for enhanced logging
   LOGFIRE_TOKEN=your-logfire-token
   

   1. Add the connection details for the you are using for this :
   PGHOST=<host>
   PGDATABASE=tsdb
   PGPORT=<port>
   PGUSER=tsdbadmin
   PGPASSWORD=<password>
   

   1. Save and close .env.

3. Add the default prompts to your project

   mkdir prompts
   curl -L -o prompts/system_prompt.md https://raw.githubusercontent.com/timescale/tiger-agent/refs/heads/main/prompts/system_prompt.md
   curl -L -o prompts/user_prompt.md https://raw.githubusercontent.com/timescale/tiger-agent/refs/heads/main/prompts/user_prompt.md
   

4. Install to manage and run your AI-powered Slack bots

   1. Install the using uv.

      uv tool install --from git+https://github.com/timescale/tiger-agents-for-work.git tiger-agent
      

      tiger-agent is installed in ~/.local/bin/tiger-agent. If necessary, add this folder to your PATH.

   2. Verify the installation.

      tiger-agent --help
      

      You see the help output with the available commands and options.

5. Connect your with Slack

   1. Run your :

      tiger-agent run --prompts prompts/  --env .env
      

      If you open the explorer in , you can see the tables used by your .

   2. In Slack, open a public channel app and ask a couple of questions. You see the response in your public channel and log messages in the terminal.

   

Add information from MCP servers to your

To increase the amount of specialized information your AI Assistant can use, you can add MCP servers supplying data your users need. For example, to add the MCP server to your :

1. Copy the example mcp_config.json to your project

   In my-tiger-agent, run the following command:

    curl -L -o mcp_config.json https://raw.githubusercontent.com/timescale/tiger-agent/refs/heads/main/examples/mcp_config.json
   

2. Configure your to connect to the most useful MCP servers for your organization

   For example, to add the documentation MCP server to your , update the docs entry to the following:

   "docs": {
     "tool_prefix": "docs",
     "url": "https://mcp.tigerdata.com/docs",
     "allow_sampling": false
   },
   

   To avoid errors, delete all entries in mcp_config.json with invalid URLs. For example the github entry with http://github-mcp-server/mcp.

3. Restart your

   tiger-agent run --prompts prompts/ --mcp-config mcp_config.json
   

You have configured your to connect to . For more information, see MCP Server Configuration.

Customize prompts for personalization

uses Jinja2 templates for dynamic, context-aware prompt generation. This system allows for sophisticated prompts that adapt to conversation context, user preferences, and event metadata. uses the following templates:

• system_prompt.md: defines the AI Assistant’s role, capabilities, and behavior patterns. This template sets the foundation for the way your will respond and interact.
• user_prompt.md: formats the user’s request with relevant context, providing the AI Assistant with the information necessary to generate an appropriate response.

To change the way your s interact with users in your Slack app:

1. Update the prompt

   For example, in prompts/system_prompt.md, add another item in the Response Protocol section to fine tune the behavior of your s. For example:

   5. Be snarky but vaguely amusing
   

2. Test your configuration

   Run with your custom prompt:

   tiger-agent run --mcp-config mcp_config.json --prompts prompts/
   

For more information, see Prompt tempates.

Advanced configuration options

For additional customization, you can modify the following parameters:

• --model: change AI model (default: anthropic:claude-sonnet-4-20250514)
• --num-workers: adjust concurrent workers (default: 5)
• --max-attempts: set retry attempts per event (default: 3)

Example with custom settings:

tiger-agent run \
  --model claude-3-5-sonnet-latest \
  --mcp-config mcp_config.json \
  --prompts prompts/ \
  --num-workers 10 \
  --max-attempts 5

Your s are now configured with MCP server access and personalized prompts.