[ Tryout Project · photo-intelligence-fullstack-demo ]

Photo Intelligence Full-Stack Demo

Build an upload-to-analysis demo for property photos with an API, classifier, validation report, and polished output review UI.

Large1 to 2 focused weeks$500 bounty on approval

Submit by email Open project repo

Problem

The ideal full-stack version of the photo intelligence project proves more than classification: upload UX, API design, file handling, processing state, validation, and output review all matter.

A strong demo should let a reviewer upload property photos, run analysis, inspect grouped/labelled output, and trust the validator report.

Scope

Build a frontend upload and review workspace.
Build backend endpoints for session creation, photo upload, analysis, and result retrieval.
Store uploaded images locally or behind an object-storage-compatible abstraction.
Run a heuristic, open-source model, hosted VLM, or hybrid photo classification pipeline.
Return schema-valid JSON plus validator success/failure and warnings.
Render gallery, per-photo labels, spaces, listing hero, validation report, and raw JSON/download.

Acceptance criteria

Meet every line below and the submission is approved. The $500 bounty is paid, regardless of any internship decision.

Runs from a clean checkout with documented setup commands.
Lets a reviewer upload multiple images and run local analysis.
Preserves every uploaded photo ID exactly once in the output.
Matches the public Polaris Image 2 contract and shows validator status in the UI.
Includes at least one automated validator or API-contract test.
Includes a writeup covering architecture, API design, model/data choices, deployment plan, limitations, and next steps.

Writeup

The artifact is half. The writeup is the other half. Show us how you think.

Explain the frontend/backend boundary and API design.
Describe file storage and processing-state choices.
Explain model or heuristic choices, cost, latency, and validation.
Document deployment tradeoffs and next production steps.

Assets

Full-stack project brief and mock result
Public-safe full-stack brief with suggested API shape, mock result, plus-point criteria, and submission instructions.

How to submit

Code submissions: fork the tryouts mono-repo, build inside projects/photo-intelligence-fullstack-demo/submissions/<your-handle>/, and open a PR with your code plus a WRITEUP.md.
Non-code submissions (design, ops, data): email talent@getcovent.com with subject Internship Tryout: photo-intelligence-fullstack-demo: <Your Name>. Attach a link to the artifact (repo, live URL, Figma, Notion, video, deck) plus your writeup.
Review: founders read every submission. We respond within 7 days.

Bounty rules

Every project has clear acceptance criteria. Meet the bar, get paid.
Uncapped: multiple people can solve the same project and each is paid.
The bounty is independent of any internship offer.
We respond within 7 days.
Payment via Wise (international) or ACH (US) after a W-9 or W-8BEN.
One bounty per person per project.

Covent is an equal opportunity employer. We hire on merit and fit, not background.

Problem

The ideal full-stack version of the photo intelligence project proves more than classification: upload UX, API design, file handling, processing state, validation, and output review all matter.

A strong demo should let a reviewer upload property photos, run analysis, inspect grouped/labelled output, and trust the validator report.

Scope

Build a frontend upload and review workspace.

Build backend endpoints for session creation, photo upload, analysis, and result retrieval.

Store uploaded images locally or behind an object-storage-compatible abstraction.

Run a heuristic, open-source model, hosted VLM, or hybrid photo classification pipeline.

Return schema-valid JSON plus validator success/failure and warnings.

Render gallery, per-photo labels, spaces, listing hero, validation report, and raw JSON/download.

Acceptance criteria

Meet every line below and the submission is approved. The $500 bounty is paid, regardless of any internship decision.

Runs from a clean checkout with documented setup commands.

Lets a reviewer upload multiple images and run local analysis.

Preserves every uploaded photo ID exactly once in the output.

Matches the public Polaris Image 2 contract and shows validator status in the UI.

Includes at least one automated validator or API-contract test.

Includes a writeup covering architecture, API design, model/data choices, deployment plan, limitations, and next steps.

Writeup

The artifact is half. The writeup is the other half. Show us how you think.

Explain the frontend/backend boundary and API design.

Describe file storage and processing-state choices.

Explain model or heuristic choices, cost, latency, and validation.

Document deployment tradeoffs and next production steps.

How to submit

Code submissions: fork the tryouts mono-repo, build inside projects/photo-intelligence-fullstack-demo/submissions/<your-handle>/, and open a PR with your code plus a WRITEUP.md.

Non-code submissions (design, ops, data): email talent@getcovent.com with subject Internship Tryout: photo-intelligence-fullstack-demo: <Your Name>. Attach a link to the artifact (repo, live URL, Figma, Notion, video, deck) plus your writeup.

Review: founders read every submission. We respond within 7 days.

Bounty rules

Every project has clear acceptance criteria. Meet the bar, get paid.

Uncapped: multiple people can solve the same project and each is paid.

The bounty is independent of any internship offer.

We respond within 7 days.

Payment via Wise (international) or ACH (US) after a W-9 or W-8BEN.

One bounty per person per project.