For hiring teams

This is what you get.
Not a CV. An intel report.

Below are 3 sample Promptintern profiles. For every answer, we show you the prompt, what we were testing for, and what the answer revealed. Read the thesis, not just the response.

How to read this report

1The prompt

Exact question or task we put in front of the candidate.

2What we test

Grader's thesis — what a good answer reveals about the candidate.

3The signal

Our read on what their actual answer tells you. The 'so what'.

Demo profile. Fictional candidate, real format. Live profiles use the same structure with real submissions.

AM
Elite Verified by Promptintern

Aarav Mehta

B.Tech CS, IIT Bombay (3rd yr) · AI / Prompt Engineering

Mumbai, INVerified May 18, 2026 LinkedIn

Builds tooling around LLMs for fun. Spends weekends benchmarking prompt strategies on open eval sets. Comfortable shipping ugly v1s and iterating.

PythonLangChainRAGEvalsTypeScriptNext.js

Verified Intel Score

116/ 125

Composite of 4 independent assessment layers.

Analytical thinking38/40
Communication24/25
Setup readiness19/20
Drive & motivation35/20

Layer 1

Analytical thinking

Real-world task. Open prompt. No retakes.

38
/ 40
The brief we gave them

We gave you a real production prompt used to classify customer support tickets. It's underperforming (~64% accuracy on our holdout set). Diagnose what's wrong, propose a fix, and back it up with evidence. 90 min, open notebook, you can run code.

What a good answer reveals
  • ·Can they actually run an experiment, not just theorize?
  • ·Do they identify ROOT cause, or surface-level symptoms?
  • ·Do they quantify trade-offs (cost, latency, accuracy) instead of hand-waving?

Their response

The given prompt fails on long-context inputs because it asks the model to summarize before classifying — the summary collapses the signal the classifier needs. My fix: invert the order (classify first using a 3-shot example block, then summarize only the matched class). On the 50 samples I ran locally, accuracy went from 64% → 89%. Trade-off: ~1.4x token cost, which is fine for this use case. Full notebook attached with eval harness.

Strengths
  • ·Diagnosed root cause (order-of-operations), not symptom
  • ·Ran an actual eval (n=50) instead of vibes
  • ·Surfaced cost trade-off unprompted
Gaps & risks
  • ·Sample size small for production claim — flagged it himself
View full attachment

Layer 2

Intro video

Unscripted self-tape. Selfie camera. ~5 minutes.

24
/ 25

Watch intro video

Unscripted · ~5 min

Question 1

Unscripted 5-min intro — self-tape, quiet room

What we test

How do they carry themselves when no one hands them questions? Do they pick a topic worth 5 minutes, or fill air?

Their answer (transcript)

Introduces himself in 30 seconds, then spends the rest walking through his OSS RAG contribution — the specific bug, the retriever tradeoff, and what he'd do next. No filler, no rehearsed monologue. Ends by naming a hypothesis he wants to test in a real product setting.

Signal

Chose to talk about actual work over background. Concrete artifact, honest gaps, and forward-looking intent. Presentable enough to send to a founder.

Layer 3

Setup readiness

Can they actually start Monday?

19
/ 20
  • Working laptopYes
  • Internet200 Mbps fiber
  • Quiet workspaceYes
  • AvailabilityFull-time, 40 hrs/week — starts immediately

"Own dedicated workstation, dual monitor, willing to overlap with US hours till 11pm IST."

Layer 4

Drive & motivation

Why they want this. In their own words.

35
/ 20
The prompt

Why this, why now? In 3-5 sentences — no fluff, no 'I'm passionate about innovation.'

Their answer

I don't want a CV-internship where I make slides. I want to ship something a real team actually uses. Promptintern's task round was the first application that actually tested if I could think, not if I could write a cover letter.

Signal

Specific rejection of low-leverage work + signals he's already self-selected for output-driven teams. Not performative.

Reviewer verdict

Top 2% of Q2 applicants. His task response identified two failure modes in the prompt we didn't expect candidates to catch. Hire fast — he won't be on the market long.

— Promptintern review team

Why this beats their CV

You don't need a second screening call. Everything you'd ask is already above.

DimensionCV / ResumePromptintern report
Source of truthSelf-writtenIndependently graded
Analytical proofBullet pointsLive task response
CommunicationClaimedRecorded video round
Work readinessUnknownSetup audited (Layer 3)
MotivationCover-letter fluffOn-record statement
Trust levelTake their wordVerified by Promptintern

Ready to hire from this?

Browse verified interns, request a warm intro, and skip the screening calls. We've already done that part.