AI & PromptingBeginner 1 to 2 hours

Build a Lead Categorization & Auto-Responder Workflow

Map a workflow logic and write prompts to automate email lead categorization and replies.

The Scenario

A boutique real estate agency receives hundreds of web inquiries daily. Agents spend hours manual-sorting them. The agency manager wants an automated workflow that reads an inquiry, categorizes it by intent (buying, renting, selling), and drafts a contextual email response.

The Brief

Design a step-by-step logic map for a workflow (e.g. using Zapier or Make.com) that triggers on a new form submission. Outline how the payload is structured, the exact system prompt sent to the LLM for categorization and drafting, and the schema output of the LLM.

Deliverables

  • Graphical or markdown flowchart illustrating the workflow steps.
  • The detailed LLM prompt used to categorize the lead and draft the response (with variables like {{lead_message}} and {{property_type}}).
  • The input/output JSON payload structure mapping fields between the form, the LLM step, and the email sender.
  • One safeguard implementation to prevent sending inappropriate AI-generated responses to clients.

Submission Guidance

Deliver your solution in clean Markdown. Present the prompts clearly with variable placeholders, and describe the input/output schemas as structured JSON blocks.

Submit Your Work

Your submission is graded against the rubric on the right. If you pass, you get a public Badge URL you can share on LinkedIn. There is no draft save, so work offline first and paste your finished response here.

This appears on your public Badge.

We'll email you the permanent link to your Badge so you never lose it. Not shown publicly.

0/20000 charactersMarkdown supported

One per line or comma separated. Up to 5 links.

Loading security check...

By submitting, you agree your submission text, name, and evaluation will appear on a public Badge URL.