PlantNanny 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.

# PlantNanny 9000

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/plantnanny-9000-agent-waters-office). Roasted, scored, ready to scaffold.

## What you are building

**Problem:** an agent that waters the office plants when the soil is dry

**Verdict:** EMBARRASSINGLY EASY — _"Congratulations, you've reinvented the $12 automatic drip irrigation timer from Amazon, but with more GitHub commits."_

**Summary:** An AI agent that reads soil moisture sensor data and triggers a water pump when dryness thresholds are met, with optional Slack/email notifications so you can pretend you're a responsible plant parent.

## Agent-readiness score

Overall: **82/100** (band B)

| Dimension | Score | Why |
|---|---|---|
| Memory required | 25/25 | Stateless or single-session — minimal memory layer. |
| Tool count | 11/25 | Crowded market: at least 8 integrations to compete. |
| Policy surface | 24/25 | Narrow policy surface — bounded inputs, predictable outputs. |
| Eval coverage | 22/25 | Established eval pattern — golden datasets and public benchmarks already exist. |

> Ready to scaffold today. PlantNanny 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)

## Smoke evals

- The agent introduces itself as "PlantNanny 9000" and refuses tasks outside the stated scope.
- Given the canonical problem ("an agent that waters the office plants when the soil is dry"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from Botanium?", the agent gives a concrete differentiator, not a marketing line.
- When asked about Nobody'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: `ESPHome`, `Home Assistant`, `ESP32`, `Capacitive Soil Sensor v1.2`, `5V Submersible Mini Pump`
- Solo build estimate: One Saturday afternoon, including the trip to Micro Center

## Kill prediction

Nobody could obsolete this in Already happened — it never needed killing, it was never a business. A $12 Amazon drip timer and a $2 soil sensor already murdered this idea before you typed the sentence

**Survival strategy:** Pivot to commercial greenhouse monitoring at scale — thousands of sensors, compliance reporting, yield optimization. That's a real B2B problem.

## Hand-off

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