lindy-core-workflow-a

name	lindy-core-workflow-a
description	Build and configure multi-step Lindy AI agent workflows. Use when creating agents with triggers, actions, conditions, knowledge bases, or agent steps. Trigger with phrases like "create lindy agent", "build lindy agent", "lindy agent workflow", "configure lindy agent", "lindy workflow".
allowed-tools	Read, Write, Edit, Bash(curl:*)
version	1.15.0
license	MIT
author	Jeremy Longshore <[e-mail]>
tags	["saas","lindy","workflow"]
compatibility	Designed for Claude Code

Lindy Core Workflow A: Agent Creation

Overview

Complete workflow for creating, configuring, and testing Lindy AI agents. Agents consist of four components: Prompt (behavioral instructions), Model (AI engine), Skills (available actions), and Exit Conditions (completion criteria).

Prerequisites

• Lindy account at
• Use case defined (support bot, email triage, data processor, etc.)
• Required integrations identified (Slack, Gmail, Sheets, etc.)

Instructions

Step 1: Define Agent Specification

Before building, document:

• Purpose: What the agent does (one sentence)
• Trigger: What wakes it up (webhook, email, schedule, chat, etc.)
• Actions: What it does (send email, update sheet, post to Slack, etc.)
• Model: GPT-4 (smart, expensive), Claude Sonnet (balanced), Gemini Flash (fast, cheap)

Step 2: Create the Agent

Option A — Natural Language (recommended):

1. Click New Agent at

2. Describe your agent in plain English:

   When a customer emails [e-mail], classify the email as
   billing/technical/general, draft a response using our knowledge base,
   and post the classification to #support-triage in Slack
   

3. Agent Builder auto-generates trigger + action nodes

Option B — Manual Build:

1. Click New Agent > Start from scratch
2. Add trigger: Click "+" > Select trigger type
3. Add actions: Click "+" > Search for action
4. Connect nodes by dragging arrows between steps

Step 3: Configure the Prompt

Open Settings > Prompt. Structure it with clear sections:

## Identity
You are a customer support classifier and responder for [Company].

## Instructions
1. Read the incoming email carefully
2. Classify into: billing, technical, or general
3. Search the knowledge base for relevant answers
4. Draft a professional response using the KB results
5. If no KB match found, escalate to human

## Constraints
- Never promise refunds or credits without human approval
- Keep responses under 200 words
- Always include ticket reference number

Prompt best practices (from Lindy docs):