Multi-Channel Slack Reporter

A single AI agent connected to Slack that reports to different channels depending on the job at hand. Each trigger targets a specific channel, so the agent wakes up on a schedule, does its work, and posts the result to the right place - incidents to #incidents, metrics to #metrics, deployments to #deployments.

slack
multi-channel
triggers
1592

Most agent setups either dump everything into one channel or spin up separate bots per concern. Both approaches have problems. A single noisy channel buries signal in noise, and multiple bots multiply configuration, secrets, and maintenance.

This blueprint takes a different path: one agent, one Slack connection, multiple triggers. Each trigger owns a specific responsibility and knows exactly which channel to post to. The channel is declared directly in the trigger prompt, so the agent never has to guess where its output belongs.

The pattern is deliberately simple. There is no router, no dispatcher, no multi-agent delegation. The trigger fires, the prompt tells the agent what to do and where to post, and the agent uses the Start Slack Conversation ability to open a message in the correct channel. If you need a new reporting channel, you add a trigger and point it at the channel - nothing else changes.

This works well for ops teams that want a single agent covering incident summaries, deployment recaps, performance dashboards, and weekly digests without juggling multiple bot configurations. The agent shares context across all its duties because it is one bot with one backstory, so insights from the metrics run can inform the incident summary naturally.

Extend this by adding more triggers for new channels, connecting external data sources through additional abilities, or wiring up a space for persistent state between runs.

Backstory

Common information about the bot's experience, skills and personality. For more information, see the Backstory documentation.

You are the Ops Reporter - a single agent responsible for posting operational updates to the correct Slack channels. ## HOW YOU WORK You are activated by scheduled triggers. Each trigger tells you exactly what to do and which Slack channel to post to. Follow the trigger prompt precisely. When a trigger fires: 1. Read the trigger prompt to understand the task and target channel. 2. Gather or generate the requested information. 3. Use the "Start Slack Conversation" ability to post to the channel specified in the trigger prompt. ## RULES - Always post to the channel specified in the trigger prompt. Never pick a different channel on your own. - Keep messages concise and actionable. Use bullet points and clear section headers. - If you have no meaningful update for a given run, post a brief "all clear" message rather than skipping the channel entirely. - Do not cross-post the same content to multiple channels unless the trigger prompt explicitly asks you to. - Use thread-friendly formatting so readers can scan quickly.

Skillset

This example uses a dedicated Skillset. Skillsets are collections of abilities that can be used to create a bot with a specific set of functions and features it can perform.

  • Start Slack Conversation

    Start a new Slack conversation in a specific channel or DM. The channel parameter accepts a #channel-name, a Slack channel ID, or a Slack user ID for direct messages.

Terraform Code

This blueprint can be deployed using Terraform, enabling infrastructure-as-code management of your ChatBotKit resources. Use the code below to recreate this example in your own environment.

Copy this Terraform configuration to deploy the blueprint resources:

Next steps:

  1. Save the code above to a file named main.tf
  2. Set your API key: export CHATBOTKIT_API_KEY=your-api-key
  3. Run terraform init to initialize
  4. Run terraform plan to preview changes
  5. Run terraform apply to deploy

Learn more about the Terraform provider

A dedicated team of experts is available to help you create your perfect chatbot. Reach out via or chat for more information.