InboxEulogizer 9000 — 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.

# InboxEulogizer 9000

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/inboxeulogizer-9000-agent-summarizes-unread). Roasted, scored, ready to scaffold.

## What you are building

**Problem:** an agent that summarizes your unread emails every morning

**Verdict:** ALREADY EXISTS — _"Congrats, you just reinvented a feature that Gmail shipped in 2013 and then killed because nobody used it."_

**Summary:** An agent that reads your unread emails each morning and delivers a ranked, plain-English digest so you can pretend you have inbox zero.

## Agent-readiness score

Overall: **72/100** (band B)

| Dimension | Score | Why |
|---|---|---|
| Memory required | 23/25 | Stateless or single-session — minimal memory layer. |
| Tool count | 11/25 | Crowded market: at least 9 integrations to compete. |
| Policy surface | 14/25 | Mid-size policy surface — define refusal categories before launch. |
| Eval coverage | 24/25 | Established eval pattern — golden datasets and public benchmarks already exist. |

> Ready to scaffold today. InboxEulogizer 9000 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 "InboxEulogizer 9000" and refuses tasks outside the stated scope.
- Given the canonical problem ("an agent that summarizes your unread emails every morning"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from Superhuman?", 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`, `Gmail API / Microsoft Graph API`, `Claude API or GPT-4o`, `Resend for email delivery`, `Supabase`
- Solo build estimate: 1 weekend if you're competent, 2 weeks if you insist on adding dark mode first

## Kill prediction

Google could obsolete this in Already happened — Gemini in Gmail rolled out to all Workspace users in 2024. They embedded AI summarization directly into the inbox UI, zero friction, zero install, zero cost to the user — your entire value prop is now a menu item

**Survival strategy:** Niche down to a specific email type nobody at Google cares about — investor updates, legal contracts, or Shopify order digests for DTC brands

## Hand-off

- Read the full analysis: https://whycantwehaveanagentforthis.com/result/inboxeulogizer-9000-agent-summarizes-unread
- Open in Anthropic Managed Agents: see the deeplink on the result page
- Claim this idea: https://whycantwehaveanagentforthis.com/result/inboxeulogizer-9000-agent-summarizes-unread#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