Media & Content · Est. $12k – $15k
Curio

AI Antique Identification

Coralsoft designed, built and shipped this product for the client.

iOSAndroidCloudReact NativeExpo SDK 54Expo Router
Curio — product interface
Curio — product interface
The situation

What was in place before we started.

Curio is an AI-powered identifier for antiques, collectibles, art, furniture, pottery and more. Snap a photo and it returns the likely maker, era, material, history and an estimated value.

Curio is an AI-powered identifier for antiques, collectibles, art, furniture, pottery and more. Snap a photo and it returns the likely maker, era, material, history and an estimated value.

Estimated Engagement
3 months
Team
3 people
Estimated Budget
$12k – $15k
Year
2026
Used by
Collectors · Estate buyers · Dealers · Resellers · Designers
Core engine
Computer vision + historical databases
Coverage
Origin, era, style, material, maker, value
Output
Identification, history & a personal collection
Estimated stack
React NativeExpo SDK 54Expo RouterTypeScriptNativeWindTanStack QueryReact Hook Form + ZodVercel AI SDKTypesenseSupabase (Postgres + RLS)Supabase AuthSupabase Edge Functions (Deno)
Delivery story

Curio: making content discovery and creation feel effortless

01

Challenge

Curio is an AI-powered identifier for antiques, collectibles, art, furniture, pottery and more. The main delivery challenge was to give users dense content and media tools that still feel immediate on everyday devices, while keeping Capture, Identify, and Date consistent across the complete journey. We framed the engagement around the smallest production-worthy flow first, then expanded the scope without weakening the underlying component and data model.

02

How we built it

We began by mapping the user journey and the boundaries of the AI: what context it receives, what it may return, and where deterministic application logic must stay in control. We then built Capture, Identify, and Date as small end-to-end slices, connecting the interface to the data and model layers early so the team could test real responses instead of static mock-ups. Prompt, validation, and fallback behaviour were refined alongside the product UI. The main implementation used React Native, Expo SDK 54, Expo Router, and TypeScript, with typed contracts keeping the JavaScript stack consistent across the product.

03

Delivery

The delivered scope brought Capture, Identify, Date, and Value into one coherent cross-platform mobile release. Model output, product logic, and user feedback are separated clearly, which makes the AI easier to evaluate and evolve. For Curio, the practical result is a product that communicates its value quickly while giving the team a maintainable base for continued delivery in media & content.

Challenges

Each constraint, and what we did about it.

Constraint

Appraisals are slow & costly

What we did

Instant AI identification

Constraint

Reference books are overwhelming

What we did

Estimated value range on the spot

Constraint

No quick read on value

What we did

Maker, era & material detected

Constraint

Maker & era hard to place

What we did

Historical context explained

Constraint

Finds missed at the sale

What we did

Confident decisions at the sale

Constraint

Collections tracked in spreadsheets

What we did

Every piece saved to a collection

The edge isn’t owning more references — it’s knowing in the moment. Curio puts identification where the decision happens.

Results

Measured outcomes.

3-month engagement
+57%
Scans completed to a saved result.
+48%
Items saved to a collection.
4.8★
Across App Store reviews.
+52%
Free-to-Premium upgrade lift.
Instant
Photo-to-ID time
Value
Price estimates surfaced
↑
Multi-photo scans
↑
Collection catalog size

By putting instant identification and value at the point of decision, Curio turned guesswork into confidence — and casual finders into serious collectors.

Roadmap

Estimated delivery sequence.

3 months
Weeks 1–3

Discovery & shaping

Discovery with collectors & dealers; mapping the on-site decision moment.

Weeks 4–10

Core build

Photo identification, dating, material & style detection, history.

  • AI Identification
Weeks 11–13

Launch & iterate

Value estimates, collection management, scan history, sharing, Premium.

  • Provenance
  • Valuation
  • Collection

More work like this.

Every case study covers a product Coralsoft designed, built, and shipped for a client.