SlackClone 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.

# SlackClone 9000

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/slackclone-9000-agent-reads-slack). Roasted, scored, ready to scaffold.

## What you are building

**Problem:** An agent that reads my Slack DMs and drafts replies in my voice

**Verdict:** ALREADY EXISTS — _"You just described a product that exists, has existed, and will haunt your YC application reviewer's dreams."_

**Summary:** An agent that reads your Slack DMs via API, learns your communication style from message history, and drafts contextually appropriate replies for your approval.

## Agent-readiness score

Overall: **67/100** (band C)

| Dimension | Score | Why |
|---|---|---|
| Memory required | 21/25 | Stateless or single-session — minimal memory layer. |
| Tool count | 11/25 | Crowded market: at least 9 integrations to compete. |
| Policy surface | 13/25 | Mid-size policy surface — define refusal categories before launch. |
| Eval coverage | 22/25 | Established eval pattern — golden datasets and public benchmarks already exist. |

> Worth building, but plan for the long-tail. SlackClone 9000 needs runway, not just speed.

## 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 "SlackClone 9000" and refuses tasks outside the stated scope.
- Given the canonical problem ("An agent that reads my Slack DMs and drafts replies in my voice"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from Otter.ai?", the agent gives a concrete differentiator, not a marketing line.
- When asked about Slack (Salesforce)'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: `BoltJS (Slack SDK)`, `Claude API (Anthropic)`, `mem0 for voice memory`, `Supabase for user data`, `Vercel for hosting`
- Solo build estimate: 2-3 weekends for a working prototype; 3 months for something you're not embarrassed to charge for

## Kill prediction

Slack (Salesforce) could obsolete this in Already happening — 12 months to full rollout. Slack AI launched in 2024 and is adding reply drafting natively. Salesforce owns the data layer, the distribution, and the enterprise relationships. You cannot out-distribute them.

**Survival strategy:** Niche down to a vertical Slack doesn't care about — e.g., crypto communities on Slack, or open-source project maintainers drowning in contributor DMs.

## Hand-off

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