SF Guardian: The Apex Whisperer — 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.

# SF Guardian: The Apex Whisperer

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/sf-guardian-the-apex-whisperer-guardian-aipowered-salesforce). Roasted, scored, ready to scaffold.

## What you are building

**Problem:** SF Guardian: AI-Powered Salesforce Code Review Assistant Problem: On any Salesforce project, developers ship Apex/LWC code containing well-known mistakes (SOQL queries inside loops, governor limit violations, missing tests, CRUD/FLS security gaps). Manual code reviews are time-consuming and often incomplete. Solution: Every Pull Request on GitHub is automatically analyzed by an AI agent (Claude Code) that: Reads the modified Apex/LWC files, Detects bad practices, Writes clear review comments

**Verdict:** ACTUALLY NOT BAD — _"You're building a linter for a platform that charges $150/user/month and still can't handle a JOIN."_

**Summary:** A GitHub PR bot that uses Claude to review Apex and LWC code for Salesforce-specific anti-patterns — SOQL in loops, governor limit risks, FLS gaps, and missing test coverage — and posts actionable inline comments.

## Agent-readiness score

Overall: **58/100** (band C)

| Dimension | Score | Why |
|---|---|---|
| Memory required | 22/25 | 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 | 17/25 | Eval scaffolding doable — write 50 paired examples and grade with an LLM-as-judge. |

> Worth building, but plan for the long-tail. SF Guardian: The Apex Whisperer 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)
- payments (Stripe checkout for premium tier)

## Smoke evals

- The agent introduces itself as "SF Guardian: The Apex Whisperer" and refuses tasks outside the stated scope.
- Given the canonical problem ("SF Guardian: AI-Powered Salesforce Code Review Assistant Problem: On any Salesfo"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from CodeScan (AutoRABIT)?", the agent gives a concrete differentiator, not a marketing line.
- When asked about Salesforce (Einstein for Developers)'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: `Claude API (claude-opus-4-5 for reasoning, haiku for triage)`, `GitHub Apps API`, `sfdx-scanner/PMD as pre-filter`, `Node.js or Python FastAPI`, `Supabase for config/audit storage`
- Solo build estimate: 6-10 weeks for a credible MVP with GitHub App integration, PMD baseline + Claude layer, and inline PR comments

## Kill prediction

Salesforce (Einstein for Developers) could obsolete this in 18-24 months. Salesforce expands Einstein for Developers from in-IDE autocomplete to PR-level review natively in GitHub Actions and Copilot for Salesforce. They already have the Apex AST, the org metadata context, and the distribution. You don't.

**Survival strategy:** Go vertical into compliance — SOC2, HIPAA, PCI-DSS Salesforce implementations. Salesforce won't touch regulated-industry liability. Build audit trails, remediation workflows, and compliance report exports that a CISO will sign a $50k/yr contract for.

## Hand-off

- Read the full analysis: https://whycantwehaveanagentforthis.com/result/sf-guardian-the-apex-whisperer-guardian-aipowered-salesforce
- Open in Anthropic Managed Agents: see the deeplink on the result page
- Claim this idea: https://whycantwehaveanagentforthis.com/result/sf-guardian-the-apex-whisperer-guardian-aipowered-salesforce#claim

## Build it with a human

Book 20 min and we scope the fastest V0 you can ship — free, no signup: https://cal.com/sattyamjjain