Slack Formatter Agent Bubble
AI agent for creating well-formatted Slack messages with adjustable verbosity and technicality
Quick Start
import { SlackFormatterAgentBubble } from '@bubblelab/bubble-core';
import { CredentialType } from '@bubblelab/shared-schemas';
const result = await new SlackFormatterAgentBubble({
message: 'example', // The message or question to send to the AI agent
credentials: {
[CredentialType.OPENAI_CRED]: process.env.OPENAI_CRED as string,
},
}).action();
Operation Details
execute
- Input Schema
- Output Schema
messagestring required- The message or question to send to the AI agent
verbosity'1' | '2' | '3' | '4' | '5'- Response verbosity level (1-5): 1=concise bullet points, 5=comprehensive explanations
technicality'1' | '2' | '3' | '4' | '5'- Technical complexity level (1-5): 1=plain English, 5=expert terminology
includeBlockKitboolean- Include Slack Block Kit JSON for rich formatting
includeQueryboolean- Include the query that was executed in the response
includeExplanationboolean- Include explanation of what the query does and why it was chosen
modelobject- AI model configuration including provider, temperature, and tokens
toolsobject[]- Array of tool bubbles the AI agent can use
maxIterationsnumber- Maximum number of iterations for the agent workflow
credentialsRecord<CredentialType,string>- Object mapping credential types to values (injected at runtime)
additionalContextstring- Additional context about how to answer the question
responsestring required- The AI agents formatted response in Slack markdown
blocksobject[]- Slack Block Kit formatted blocks for rich message display
metadataobject required- Metadata about the formatting
toolCallsobject[]- Array of tool calls made during the conversation
iterationsnumber required- Number of back-and-forth iterations in the agent workflow
errorstring required- Error message of the run, undefined if successful
successboolean required- Whether the agent execution completed successfully