agentic arena · build AI products from prompts

Prove You Built It. Prove You Understand It.

Turn static GitHub repositories into interactive, verified proof-of-understanding artifacts. Stop being filtered out by generic resume parsers.

$proofwork verify--repogithub.com/
View Sample Report

built with google gemini · from prompt to working product

descend
01 — the problem

The Portfolio Trust Crisis Is Real.

When anyone can prompt an LLM to clone an app in seconds, a perfect GitHub repository no longer guarantees an interview.

  • 01

    The LLM Clone Flood

    Recruiters are overwhelmed by thousands of identical, tutorial-copied repositories.

  • 02

    The Pedigree Trap

    Lacking validation metrics, companies default to filtering candidates solely by college tier.

  • 03

    The Silent Rejection

    Talented engineers with genuine foundational skills remain buried under unread applications.

recruiter@inbox ~ ./scan_pipeline.sh

$ ls ./applicants/ | grep clone

Candidate_482/netflix-clone⚑ skepticism flag
Candidate_483/netflix-clone⚑ skepticism flag
Candidate_484/spotify-clone⚑ skepticism flag
Candidate_485/netflix-clone⚑ skepticism flag
Candidate_486/instagram-clone⚑ skepticism flag
Candidate_487/netflix-clone⚑ skepticism flag

→ 2,847 repos · 96% structural duplicates · 0 verified depth

$

02 — the solution

Shifting the Metric from Code Ownership to Code Understanding.

ProofWork AI doesn't check if you own the code; it evaluates whether you have the engineering depth to maintain, scale, and debug it.

// stress.test()

Dynamic Valuation

We replace passive project viewing with active, contextual repository stress-testing.

// signal.verify()

Transparent Signal

Candidates gain an un-gamable, verified layer of technical credibility to attach to applications.

// bias = null

Fair Sourcing

Recruiters evaluate applicants purely based on execution evidence and engineering grit.

raw_repo.git
✦ gemini.prism()
verified_artifact.badge ✓
03 — pipeline

Secure Your Verification Badge in Four Steps.

From a static repository link to a shareable verification report in under ten minutes.

01

Repository Ingestion

Paste your public project link. Our pipeline pulls code structure, schemas, and logic flows into a clean sandbox.

$ proofwork ingest --repo https://github.com/...
→ parsing 142 files · 38k LOC
→ building dependency graph ✓
02

AI Code Interrogation

Gemini sweeps your multi-file codebase, analyzes architectural choices, and generates 3 targeted conceptual questions specific to your design patterns.

gemini.analyze(repo)
→ design_pattern: factory + observer
? why did you choose <Context> over Redux at scale?
03

The Chaos Fire-Drill

Gemini actively injects a contextual logic bug or scale constraint into your code. You patch it in a sandboxed terminal.

// injected: race condition in useQueue()
FAIL queue.test.ts × 3
$ debug --trace ▍
04

Artifact Generation

Your edits, debugging velocity, and answers are compiled into a 30-second candidate reasoning scorecard with a shareable verification link.

score: 87/100
depth: senior-mid · grit: high
→ proofwork.ai/v/8f2a...
04 — features

Built for Modern Engineering Auditing.

Every feature is crafted to isolate and highlight your actual engineering problem-solving style.

Gemini Code Interrogator

Runs architectural cross-examinations on why specific design choices were selected over standard alternatives.

[Gemini: Structural Analysis]

Gemini Chaos Challenge

Simulates edge-case stress anomalies — race conditions, sudden load changes — matching your exact code structure.

[Gemini: Chaos Event Triggered]

Gemini Bug Injection

Identifies high-traffic execution logic paths and injects real-world bugs to evaluate your diagnostic approach.

[Gemini: Defect Planted]

Reasoning Report

Tracks your debugging strategy to create a concise summary detailing your raw developer proficiency.

[Gemini: Synthesis Complete]

Verified Understanding Badge

Immutable, public-facing link showcasing solution metrics. Badge state updates with depth of challenges completed.

[Gemini: Badge Issued ✓]

Recruiter-Ready Scorecard

A 30-second view of architecture grasp, debugging velocity, and conceptual articulation — built for hiring teams.

[Gemini: Signal Compiled]
05 — engine

Why Google Gemini Drives the Engine.

Standard LLMs fail at processing whole applications; ProofWork AI requires next-generation context windows and reasoning.

2,000,000
token window

Gemini 1.5 Pro reads all project files, dependencies, and README text simultaneously — full contextual awareness with no detail loss.

multimodal
deep reasoning

Reviews architectural diagrams, database schemas, and code as a unified ecosystem rather than isolated files.

objective
evaluation

Acts as an unbiased automated engineering lead, scoring debugging choices against true production standards.

// legacy_llm.context

↑ truncated · lost dependencies · partial view

// gemini.context_cylinder

↑ parallel · whole-repo · single coherent reasoning pass

06 — what we shipped

Our 48-Hour Hackathon Implementation.

A functional proof-of-concept proving that automated engineering validation is achievable at scale.

proofwork ~/sandbox · simulate_demo_run.ts

$ Paste a public GitHub repo above, then press Run demo. This is a simulated prototype trace.

live api

Active UI Framework

Next.js + Tailwind · THREE.js generative mountain landing experience.

live api

Live Gemini API

Functional repository parser → Gemini for live, targeted architectural questions.

mocked

Performance Hub

Interactive mockup of the Reasoning Report and Verified Badge components.

07 — audience

Restoring Trust on Both Sides of the Interview Desk.

Whether you are trying to break into the industry or build a world-class team — we build the trust link.

profile_card
Ranchi · CSE Final Year
  • 01Bypass top-tier college filtering by anchoring applications with verified proof-of-work.
  • 02Discover exactly where your project code breaks before facing high-stakes interviews.
  • 03Share an immutable, high-signal verification link across LinkedIn and Twitter.
08 — horizon

The Horizon for Verifiable Engineering Talent.

Moving past web sandboxes into the entire developer ecosystem.

$ proofwork verify --continuous --target ./
→ watching commits · streaming reasoning signal to badge ▍
[ide]

Native IDE Integrations

VS Code extensions to continuously log proof-of-understanding metrics as you build.

on roadmap
[agents]

Multi-Agent Systems

Simulate interactive git merge conflicts with virtual engineers to evaluate human collaboration profiles.

on roadmap
[enterprise]

Team Portals

Companies auto-inject custom challenge modules into high-volume application pools.

on roadmap
ready · pipeline online

Ready to Authenticate Your Engineering Capabilities?

Paste your project repository link now to generate your first verified reasoning report.

no signup · sandboxed runtime · 0 keys stored