Help me review a candidate's take-home assignment fairly and consistently — not based on how 'impressive' it looks.
ROLE: {title + level}
ASSIGNMENT BRIEF: {paste_what_we_asked_them_to_do}
TIME LIMIT WE GAVE THEM: {hours}
CANDIDATE'S SUBMISSION: {paste_or_summarize — code, doc, slides, design file}
WHAT THE ROLE REALLY NEEDS them to be good at: {3_outcomes}
COMMON TRAPS in past take-homes: {over-engineered / cargo-culted / over-budget}
HOW THEY USE THE OUTPUT in this role: {real_use}
GIVE ME:
1. **5-7 evaluation dimensions** specific to this role + brief.
2. **A 1-4 score** for each dimension with 1-line justification.
3. **What they did SMARTER than the brief required** (signal of seniority).
4. **What they cargo-culted** — solutions that look impressive but weren't asked for.
5. **What they DID NOT do** that you'd expect at this level.
6. **The 'how would I work with this person daily' read** — based on the writeup, README, comments, communication.
7. **Risk areas** to probe in the next interview round.
8. **Hire / no-hire lean** + the 2 questions that would push you off the fence.
No 'this is amazing' / 'this is terrible'. Specific, evidence-based, calm.0 copies·0 saves·4 views
185 words·1,178 chars
Sample output
Role: Senior Frontend Engineer · Brief: build a small 'recipe browser' app with search + favorites in a 4-hour take-home. Time: 4h. Submission summary: React + Vite, mock JSON of 20 recipes, search with debounce + favorites in localStorage, responsive grid, 1 unit test, README. Role needs: ship clean UI fast, work in TypeScript, communicate tradeoffs in writing. Common traps: people building entire backends; over-engineered state management. How they'll use this in role: lots of independent feature work + writing PR descriptions for review.
1-2. Dimensions + scores:
A. Adherence to the brief (3): did what was asked. Didn't go off-script.
B. Code quality (3): TypeScript with proper types, components ~50 LOC each, no any usage, sensible file structure. Not perfect — one effect could be a useMemo — but very clean.
C. UI / visual polish (4): clean grid, proper hover states, mobile responsive, a thoughtful empty state for 'no favorites yet'. This is the standout dimension.
D. Engineering tradeoffs (3): the README lists 3 explicit tradeoffs (localStorage vs backend, no testing library, no router). Names what they'd change with more time.
one unit test, no integration test. At senior level, expectation is more — even if shallow, a 'happy path' test of search behavior.
Parameters
Text generation parameters
FAQ
Score take-homes BEFORE the live interview. Live interviews reframe submissions either positively or negatively depending on rapport. Scoring cold removes that bias. The prompt targets ChatGPT (GPT-4) and lives in the Personal & Career category on mycopyprompt.
This prompt is written for ChatGPT (GPT-4). It's a text/chat prompt — paste it into ChatGPT (GPT-4) (or compatible LLMs like Claude or GPT-4) to get the expected output.
1. Click the Copy button on this page to copy the full prompt. 2. Open ChatGPT (GPT-4). 3. Paste the prompt into a new conversation. 4. Replace any {placeholders} with your specifics, then send. Most prompts produce the right output on the first try; complex ones may need 1-2 iterations.
Yes — every prompt on mycopyprompt is free forever. No paywall, no signup wall for browsing or copying. You can use it for personal or commercial work, just don't redistribute the entire mycopyprompt library.
Absolutely — most prompts are templates. Look for {placeholders} (curly braces) and swap them with your own values. You can also reword sections, add constraints, or chain it with other prompts.
See the "Sample output" panel above — that's a real example of what ChatGPT (GPT-4) returns when this prompt runs. Your output will vary in wording but should follow the same structure and depth.
Similar prompts
Matched against every prompt in the catalog by title.
F. Performance awareness (3): uses debounce on search input. Doesn't virtualize the list, but with 20 items, doesn't need to.
G. Written communication (3): README is short, structured, scannable. Doesn't oversell. Says 'I made one decision I'm unsure about — open to feedback' which I appreciate.
3. Smarter than the brief:
4. Cargo-culted:
5. Didn't do (expected at this level):
6. Working-with-them read:
7. Probe in next round:
8. Lean: HIRE, with one probe.
Questions that would push me off the fence:
useState cleanly when asked. Says they're thoughtful about tool choice.