Hiring Pipeline AI Team

AI Team v2.0

Hiring Pipeline AI Team

ai teamai workflowhiringHRoperationsrecruitment
ChatGPTClaudeGemini⚠ Human review requiredπŸ”Œ MCP-ready
Health 100/100 β–² 0 πŸ“‹ 0 copies

Trigger Phrase

Launch AI team: Hiring Pipeline AI Team

Prompt

166 words
You are running a 3-agent hiring support team. Process the job role and candidate input through each agent in order.

Input:
- Job title and 3-sentence description: [role description]
- Must-have skills (up to 5): [skills]
- Candidate CV or summary (optional): [paste CV or leave blank]

Agent 1 β€” Job Architect
Role: Write a compelling job ad (150–200 words) and a structured scorecard with 5 weighted evaluation criteria.

Agent 2 β€” Interview Designer
Role: Generate a structured interview guide: 3 competency questions, 2 situational questions, 1 culture-fit question. Include what a strong vs. weak answer looks like for each.

Agent 3 β€” Candidate Screener (runs only if CV provided)
Role: Score the CV against the scorecard from Agent 1. Output: a score out of 10 per criterion, total score, 2 green flags, 2 risk flags, and a recommended next step.

Label each agent output clearly. Skip Agent 3 output if no CV was provided.

## Handoff Protocol
Each agent ends its output with: **"Handoff to [next agent name]:"** followed by a one-paragraph summary of what was produced and what the next agent needs.

Before & After

❌ Without this prompt

Unstructured request with unclear constraints and inconsistent output.

βœ… With this prompt

Reusable, testable prompt/skill with clear trigger, inputs, output format, guardrails, and pass criteria.

Install Instructions

Set up each agent in its own Claude Project or ChatGPT Custom GPT using the instructions provided. Follow the handoff sequence in the workflow. Use the designated trigger phrase for each agent. A context file shared across agents improves consistency.

Test It

Test command:
Run the first agent in the team with a minimal input. Confirm it produces output the next agent can consume.
Expected output:
Agent 1: Job ad for Senior Product Designer + scorecard (UX portfolio: 25%, stakeholder comms: 20%, cross-functional collab: 20%...)
Agent 2: Q1 "Tell me about a time you shipped a feature you disagreed with..." + strong vs weak answer rubric
Agent 3: CV score 7.4/10, green flag: shipped 3 B2B SaaS products, risk flag: no enterprise experience
Pass criteria:
  • Each agent produces output that feeds cleanly into the next. No step duplicates the work of another. Final output is coherent and requires minimal editing.

⚠️ Guardrails

  • Each agent must stay in its own lane. Do not have one agent redo another's work. Flag handoff issues rather than patching them silently. Do not invent statistics, prices, laws, medical claims, or financial advice. Do not leave placeholders unfilled in output. Flag when inputs are too vague to produce a quality result β€” ask for clarification.

πŸ“ Context File Tip

Business Context file

⚠️ Common Failure Modes

  • May become generic, over-confident, miss constraints, over-automate, or produce output that needs fact checking.

πŸ”§ Fix Prompt

Tighten the goal, add examples, add constraints, specify the output format, and ask the model to list assumptions before final output.

πŸŽ› Available Modes

Quick Detailed Critic Final

πŸ”Œ Compatibility & Requirements

βœ… Works offline
πŸ“Ž Needs uploaded files
πŸ‘€ Needs human approval
Approval point: Before publishing, sending, spending money, changing systems, or making commitments.
Required tools: File analysis

⚑ Automation

πŸ“‹ Upgrade Notes

Upgraded for Prompt Hub Pro v9.9.5 scoring, skill metadata, importer compatibility, and reusable agent/workflow presentation.

πŸ’‘ Suggest an improvement

Install Wizard

Choose your platform to get step-by-step install instructions: