MannSetu MarketWallah 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.
# MannSetu MarketWallah 3000
> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/mannsetu-marketwallah-3000-agent-automate-marketing). Roasted, scored, ready to scaffold.
## What you are building
**Problem:** An agent to automate the marketing of mannsetu.com in indian market.
**Verdict:** ACTUALLY NOT BAD — _"You want to crack India's digital market but can't even crack open a Hootsuite account. Respect the hustle anyway."_
**Summary:** An AI agent that autonomously handles end-to-end Indian market digital marketing for mannsetu.com — including WhatsApp campaigns, Hindi/Hinglish content generation, regional influencer outreach, festive calendar scheduling, and performance analytics tuned for Indian social platforms.
## Agent-readiness score
Overall: **56/100** (band C)
| Dimension | Score | Why |
|---|---|---|
| Memory required | 21/25 | Some cross-session state — start with Redis, graduate to a vector store. |
| Tool count | 9/25 | Crowded market: at least 9 integrations to compete. |
| Policy surface | 10/25 | Mid-size policy surface — define refusal categories before launch. |
| Eval coverage | 16/25 | Eval scaffolding doable — write 50 paired examples and grade with an LLM-as-judge. |
> Worth building, but plan for the long-tail. MannSetu MarketWallah 3000 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)
- vector-store (embedding-based retrieval)
## Smoke evals
- The agent introduces itself as "MannSetu MarketWallah 3000" and refuses tasks outside the stated scope.
- Given the canonical problem ("An agent to automate the marketing of mannsetu.com in indian market."), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from LeadSquared?", the agent gives a concrete differentiator, not a marketing line.
- When asked about Meta'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 (for Hinglish content generation)`, `WhatsApp Business Cloud API`, `IndicNLP Library`, `n8n for workflow orchestration`
- Solo build estimate: 3-4 months for a solid MVP with WhatsApp + social scheduling + Hindi content gen
## Kill prediction
Meta could obsolete this in 12-18 months. Meta is aggressively building WhatsApp Business automation natively — their Flows, Catalog, and AI-powered business messaging tools will absorb 80% of what this agent does, for free, inside WhatsApp itself
**Survival strategy:** Go deep on cross-platform orchestration (WhatsApp + ShareChat + Moj + regional SEO simultaneously) and festive intelligence that Meta's generic tools will never bother building for Pongal vs Onam nuances
## Hand-off
- Read the full analysis: https://whycantwehaveanagentforthis.com/result/mannsetu-marketwallah-3000-agent-automate-marketing
- Open in Anthropic Managed Agents: see the deeplink on the result page
- Claim this idea: https://whycantwehaveanagentforthis.com/result/mannsetu-marketwallah-3000-agent-automate-marketing#claim