THE GUTS
My approach to building intelligent systems — combining AI-first thinking with production-grade engineering
Working Philosophy
The principles that guide my development process
AI-First Thinking
Start with the intelligence layer. Route tasks to the right model based on complexity, latency, and cost. Use local inference for sensitive data, cloud for scale.
Iterate in Production
Ship fast, measure everything. Real user feedback beats perfect planning. Deploy daily with automated rollback. Monitor latency, error rates, and user satisfaction in real-time.
Build to Scale
Start with serverless, add infrastructure when needed. Design for horizontal scaling from day one. Use managed services until you need control, then self-host strategically.
Automate Everything
If I do it twice, I automate it. Workflows for deployment, testing, monitoring, and data processing. Let AI handle the repetitive, keep humans in the loop for judgment.
Reasoning Engines
The LLMs I route to based on task requirements
GPT-4o
My go-to for multi-step workflows, code generation, and strategic planning. Strong tool-use capabilities and reliable structured output.
Claude 3.5 Sonnet
Best for long-context analysis, detailed reasoning, and instruction following. Superior safety and nuanced understanding of complex documents.
GPT-4o-mini
Cost-optimized for classification, summarization, and routine automation. 15x cheaper than GPT-4o with ~300ms latency.
Llama 3.1 70B + QLoRA
Local inference for sensitive data. Custom fine-tuned models utilizing QLoRA adapters for domain-specific security intelligence and OSINT data processing. Zero external API calls, complete privacy control.
ElevenLabs + Whisper
Real-time voice interactions with Whisper STT, LLM reasoning, and ElevenLabs TTS. WebRTC streaming for sub-second responses.
Development Stack
Daily tools and frameworks I work with
Warp Terminal
GPU-accelerated terminal with AI command generation, workflow blocks, and collaborative sessions. My command center for everything.
React + Vite
Modern React with Vite for instant HMR. Tailwind for rapid UI development. Component-driven architecture with TypeScript for type safety.
Vercel Edge Functions
Serverless functions at the edge. <50ms cold starts, automatic scaling, deployed across 30+ regions. Perfect for API endpoints.
Supabase
Managed Postgres with automatic API generation, row-level security, and real-time subscriptions. Edge functions for serverless compute.
Weaviate + Advanced RAG
Vector database and retrieval orchestration. Implementing lexical-vector hybrid search, cross-encoder rerankers, and custom chunking strategies to minimize LLM hallucinations.
Docker Swarm
Container orchestration for microservices. Service discovery, load balancing, rolling updates, and automatic failover across 6 nodes.
Google Cloud Platform
Deploying scalable AI applications and microservices. Utilizing Vertex AI for enterprise model deployment, testing, and managed dataset orchestration.
Agent Test Harnesses
Custom evaluation harnesses for testing agent behavior, reliability, and security vulnerability discovery. Automating prompt injection tests and tracing latency profiles.
Automation & Integration
How I connect systems and automate workflows
Temporal.io
Resilient, code-defined orchestration with event-driven state tracking. Implements auto-retry mechanisms, complex sagas, and asynchronous callbacks with strong consistency guarantees.
Zapier Premium
Enterprise SaaS integration for CRM, email, calendar, and business tools. Multi-step automation with conditional logic.
MCP Server & Middleware
Standardized middleware for LLM-to-system communication. Custom JSON-RPC tool endpoints, prompt registries, and context-injection hooks for autonomous agents.
LangGraph & CrewAI
Orchestrating autonomous agents with state preservation, custom tool bindings, conditional routing, and human-in-the-loop checkpoints.
Quality Standards
The benchmarks I target for production systems