1d • General discussion
AI Developer Accelerator — Coaching Call - May 12th
AI Developer Accelerator — Coaching Call - May 12
Meeting Purpose
Key Takeaways
- Hybrid AI Workflows: Combining Claude Code for primary development with Codex for adversarial validation (e.g., security red-teaming) is a powerful pattern to counter model biases and improve code quality.
- AI-Driven Infrastructure: AI can automate complex infrastructure tasks, like generating Disaster Recovery (DR) plans. The ideal customer is a high-growth startup needing enterprise-grade resilience, not a large enterprise.
- User-Driven Development: A custom feedback widget enables users to narrate issues directly, capturing screen recordings and network logs. This provides high-fidelity input for AI agents to generate targeted fixes.
- AI for Process Automation: AI can automate repetitive tasks by generating deterministic scripts (e.g., Google App Scripts) that run efficiently without repeated token consumption.
Topics
AI-Assisted Development Workflows
- Hybrid Workflow (Claude Code + Codex): Rationale: Mitigates model biases by using two distinct models. Process: Claude Code generates specs, plans, and code. Codex performs adversarial validation and security red-teaming. Codex's analysis reports feed back into Claude Code for fixes.
- Superpower Plugin: A recommended plugin for Claude Code that automates the SDLC (spec, plan, implement). It spawns sub-agents with fresh context windows to manage token limits and improve focus.
- Skill Management: Recommendation: Build skills using Claude Code's skill creator skill, rather than downloading them. Rationale: Avoids supply chain security risks (e.g., prompt injection, poison pills).
- UI Testing with Playwright: The Playwright MCP (Connector) allows Claude Code to execute UI tests on a local browser. Benefit: Enables automated, visual validation of UI output, which AI agents cannot perform directly.
Project Demos & Feedback
- Elena's Multi-Cloud DR System: Function: An agentic system (on AWS Bedrock) that analyzes existing cloud infrastructure (AWS) and generates a DR plan for a target cloud (GCP). Process: Discovery: Analyzes infrastructure, code, and docs. Criticality Assessment: Assigns a tier based on user input (e.g., revenue, PCI DSS). Strategy Generation: Proposes DR options (e.g., warm standby, active-active). Plan Generation: Creates a detailed DR plan (MD/PDF) mapping services. Market Feedback: Ideal Customer: High-growth startups needing enterprise-grade resilience. Rationale: Large enterprises often prefer expensive consultants (e.g., Deloitte), while startups lack the in-house expertise. Agent Design: Structure agents by context (single goal), not by human-like task division.
- Ty's isotope Testing Package: Function: A package to improve testing visibility by logging UI and database state changes. Process: Runs tests and logs database changes (e.g., in Supabase). Captures UI screenshots at each step. Benefit: Provides a complete, step-by-step audit trail to easily identify bugs.
- Morgan's Digital Signage Project: Goal: An AI-powered digital signage system that turns "garbage in" (e.g., a photo of a poster) into "beauty out" (a polished, animated slide). Key Learning: Ask AI to generate code that creates artifacts, not the artifacts themselves. Example: AI-generated JavaScript for a perfect circle vs. an AI-generated image of an amoeba-like shape. Hardware Note: Only older Amazon Fire Stick HD models support sideloading apps. Newer 4K models require an official Amazon App Store submission.
AI for Business Process Improvement
- Elijah's Client Challenge: Documenting and improving processes for a 250-employee construction company.
- Recommended Approach: Find Champions: Identify employees with deep process knowledge who can articulate pain points. Amplify, Don't Fix: AI applied to a broken process will only expose its flaws faster. Process improvement must precede or accompany AI implementation. Use Deterministic Scripts: For repetitive tasks, have AI generate a one-time script (e.g., Google App Script) that runs efficiently without repeated token calls. Consider a Custom ERP: Ty built a custom ERP to replace Odoo, saving ~$100k/year in subscriptions. Method: A gradual, modular replacement using a "user-driven development" feedback loop. Benefit: A custom system perfectly tailored to business needs, avoiding unused features and high SaaS costs.
Next Steps
- Patrick: Finalize packaging for the "community brain" project. Share links to security skill repositories.
- Ty: Share instructions for mapping Claude Code to DeepSeek 4.
- Morgan: Evaluate Codex for its built-in DALL-E 3 image generation.
- Elena: Refine the DR system's target customer profile (high-growth startups). Install the Superpower plugin in Claude Code.
- Elijah: Connect with Ty to discuss the custom ERP build process.
Action Items
- Prepare Open WebUI instance for Patrick's Community Brain drop-in - WATCH (5 secs)
- Post Claude Code→DeepSeek 4 proxy instructions in community - WATCH (5 secs)
- Update DR POC: refine cost estimates, add DR testing, split agents by context - WATCH (5 secs)
- Evaluate Claude Agent SDK for marketing campaign automation - WATCH (5 secs)
- Install Superpower in Claude Code; run /insights; use Skill Creator to build skills - WATCH (5 secs)
- Post security skills links in community - WATCH (5 secs)
0
0 comments
AI Developer Accelerator — Coaching Call - May 12th
skool.com/ai-developer-accelerator
Master AI & software development to build apps and unlock new income streams. Transform ideas into profits. 💡➕🤖➕👨💻🟰💰
Leaderboard (30-day)
1
+11
2
+5
3
+3
4
+3
5
+1
Powered by