AI & PromptingAdvanced 3 to 5 hours

Design a Dynamic Prompt Chain

Break a complex writing task into a multi-step LLM pipeline.

The Scenario

A law firm wants to use AI to draft initial responses to client intake emails. A single massive prompt fails because the AI either misses details or writes terrible legal advice. You need to break the task into a "Chain of Prompts" where the output of Prompt 1 feeds into Prompt 2.

The Brief

Design a 3-step prompt chain. Step 1 extracts facts. Step 2 identifies missing information. Step 3 drafts the email requesting the missing info without giving legal advice.

Deliverables

  • Prompt 1: The Fact Extractor (Input: Client Email. Output: Bulleted list of facts)
  • Prompt 2: The Gap Analyzer (Input: Facts from Prompt 1. Output: List of missing critical details required to open a case)
  • Prompt 3: The Drafter (Input: Gaps from Prompt 2. Output: A polite email to the client asking for those specific details)

Submission Guidance

Chaining is how production AI apps actually work. Each prompt must be laser-focused on one task. Ensure Prompt 3 has strict guardrails preventing it from accidentally offering legal counsel.

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.

0/20000 charactersMarkdown supported

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

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