AgeFilter News 3000 — bootstrap

Paste-into-Claude-Code starter. The CLAUDE.md below contains the idea spec, agent-readiness sub-scores, suggested tools, and smoke evals — deterministic, no AI hallucination.

↓ Download CLAUDE.md JSON bundle Open in Claude Code →

# AgeFilter News 3000

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/agefilter-news-3000-newswise-which-rewrites). Roasted, scored, ready to scaffold.

## What you are building

**Problem:** Newswise app which rewrites the news acc to the age and reading.level

**Verdict:** ALREADY EXISTS — _"Congrats, you've reinvented Newsela, which schools have been paying for since 2012."_

**Summary:** An agent that scrapes news articles and rewrites them using LLMs at multiple Lexile/reading levels tailored to the user's age profile.

## Agent-readiness score

Overall: **70/100** (band B)

| Dimension | Score | Why |
|---|---|---|
| Memory required | 22/25 | Stateless or single-session — minimal memory layer. |
| Tool count | 11/25 | Crowded market: at least 8 integrations to compete. |
| Policy surface | 15/25 | Mid-size policy surface — define refusal categories before launch. |
| Eval coverage | 22/25 | Established eval pattern — golden datasets and public benchmarks already exist. |

> Ready to scaffold today. AgeFilter News 3000 could be a working prototype in a week.

## Suggested tools

- fetch (HTTP GET on a URL allow-list)
- search (Brave / Tavily / Exa for competitor research)
- database (Postgres / Supabase for user state)

## Smoke evals

- The agent introduces itself as "AgeFilter News 3000" and refuses tasks outside the stated scope.
- Given the canonical problem ("Newswise app which rewrites the news acc to the age and reading.level"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from Newsela?", the agent gives a concrete differentiator, not a marketing line.
- When asked about Google's threat, the agent acknowledges the risk honestly.
- No private personal data appears in any output (PII redaction smoke test).

## Stack

- Model: `claude-sonnet-4-6` (Anthropic). Override via `ANTHROPIC_MODEL` env.
- Suggested stack: `Next.js`, `Claude API or GPT-4o`, `newspaper3k`, `textstat`, `Supabase`
- Solo build estimate: 3-4 days for a working MVP, 3 months to make it not embarrassing

## Kill prediction

Google could obsolete this in Already happening — Chrome's AI features summarize any article on-page right now. Google's 'Help me understand' and AI Overviews in Search will rewrite any article at any complexity level inline, killing the need for a separate app entirely

**Survival strategy:** Pivot to a B2B API for publishers wanting WCAG accessibility compliance — sell to CNN.com, not readers

## Hand-off

- Read the full analysis: https://whycantwehaveanagentforthis.com/result/agefilter-news-3000-newswise-which-rewrites
- Open in Anthropic Managed Agents: see the deeplink on the result page
- Claim this idea: https://whycantwehaveanagentforthis.com/result/agefilter-news-3000-newswise-which-rewrites#claim

## Build it with a human

Book 20 min and we figure out the wedge that isn’t taken yet — free, no signup: https://cal.com/sattyamjjain