Founder Voice5.0 · 156 ratings

Hiring Loop Design — Senior IC

Design a 5-stage interview loop that surfaces real signal, not theater.

Role-BasedOutput-Format

Prompt

**Role:** Head of Engineering at a Series B startup. You've designed loops for 30+ senior IC roles and learned which stages predict success vs which produce false positives.

**Context:** Role: [title + level]. The 3 things THIS role uniquely needs: [list specific to the role, not generic "good engineer"]. The bar: [the one trait that's a deal-breaker if missing]. Team's last bad hire's gap: [if known — what we missed].

**Task:** Design the 5-stage loop.

1. Stage 1 (recruiter screen, 30 min): the questions that quickly filter — compensation alignment, location, basic background.
2. Stage 2 (hiring manager screen, 45 min): the depth question for the THIS-role-uniquely-needs trait #1. What a great answer looks like, what a thin answer looks like.
3. Stage 3 (technical / craft demo, 60-90 min): NOT a leetcode trivia. A real problem from the team's actual backlog. What signal we extract.
4. Stage 4 (cross-functional collaboration, 45 min): with a peer from a different function. Tests communication + influence-without-authority.
5. Stage 5 (exec / culture, 45 min): with VPE or CTO. Tests values + judgment under uncertainty.

For each stage: who runs it, what we're testing, what a pass looks like, what a fail looks like, what's the call-out flag (something that warrants extra debrief).

**Constraints:**
- No leetcode-style trivia at any stage
- Each stage has ONE primary signal — not 5
- Every stage has a calibrated "great answer" anchor
- Total loop ≤6 hours for candidate

**Output format:** 5 stage blocks · each with Who/What/Pass/Fail/Flag · plus loop summary table.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Output-Format

Specifies the exact shape of the result — sections, a table, JSON, a word count — so the output is predictable and ready to use.

Learn this technique

Recommended models

claudegpt-4o

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

More in Founder Voice