Media & Content · Est. $12k – $15k
Ground News

Compare the News

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

iOSAndroidWebReact NativeExpo SDK 54Expo Router
Ground News — product interface
Ground News — product interface
The situation

What was in place before we started.

Ground News is a news-comparison platform from Snapwise Inc. that shows how any story is covered across left, center and right — surfacing the spread of coverage, the factuality of sources and who owns them, so readers can spot bias and gaps for themselves.

Ground News is a news-comparison platform from Snapwise Inc. that shows how any story is covered across left, center and right — surfacing the spread of coverage, the factuality of sources and who owns them, so readers can spot bias and gaps for themselves.

Estimated Engagement
3 months
Team
3 people
Estimated Budget
$12k – $15k
Year
2026
Developer
Snapwise Inc.
Core idea
Every story across left, center & right
Coverage
Bias distribution, factuality, ownership, Blindspot
Platforms
iOS, Android, Mac, Web & browser extensions
Estimated stack
React NativeExpo SDK 54Expo RouterTypeScriptNativeWindTanStack QueryReact Hook Form + ZodVercel AI SDKTypesenseSupabase (Postgres + RLS)Supabase AuthSupabase Edge Functions (Deno)
Delivery story

Ground News: making content discovery and creation feel effortless

01

Challenge

Ground News is a news-comparison platform from Snapwise Inc. The main delivery challenge was to give users dense content and media tools that still feel immediate on everyday devices, while keeping Aggregate, Rate, and Compare 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 Aggregate, Rate, and Compare 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 Aggregate, Rate, Compare, and Blindspot 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 Ground News, 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

Algorithms reinforce a bubble

What we did

Left / center / right coverage

Constraint

No sense of the other side

What we did

Blindspot flags what you miss

Constraint

Stories quietly under-covered

What we did

Bias rating on every source

Constraint

Source bias is invisible

What we did

Ownership & factuality labels

Constraint

Ownership & funding hidden

What we did

AI summary of each side

Constraint

Factuality hard to judge

What we did

You form your own view

Transparency beats trust-me — show the bias, and let the reader decide.

Results

Measured outcomes.

3-month engagement
+63%
Stories opened in comparison view.
+51%
Blindspot stories read per week.
~4.x★
On both App Store & Google Play.
Pro
~$0.99/mo · Premium from ~$3.99/mo.
L·C·R
Bias on every story
Blind
spot underreported flags
AI
Summaries of each side
↑
Cross-spectrum reading

By making bias and blind spots visible, Ground News turned passive scrolling into active, balanced reading — and earned the trust of people tired of the bubble.

Roadmap

Estimated delivery sequence.

3 months
Weeks 1–3

Discovery & shaping

Discovery with balance-seeking readers; mapping the bias-comparison loop.

  • Bias Ratings
  • Comparison
Weeks 4–10

Core build

Aggregation, bias ratings, Blindspot feed, comparison view.

  • Blindspot
Weeks 11–13

Launch & iterate

AI summaries, factuality/ownership labels, personalization, alerts.

  • For You

More work like this.

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