Work
CHP Report Automation
PI law firms need traffic collision reports. This system handles the whole process: monitors email intake, identifies missing data, calls CHP offices with voice AI, and automates the government portal. I wrote every spec. Agents wrote every line of code.
0 firms · 0 users · 0+ requests
Runs on: Next.js · Convex · Playwright · VAPI · Twilio
→ Read case study
Knowledge Extraction Engine
Takes expert knowledge out of someone's head and turns it into structured rules a machine can use. AI runs the interviews, I designed the extraction pipeline and review workflow. 279 rules extracted so far.
0 rules · 0% coverage · 0 categories
Runs on: Next.js · Convex · Claude API
→ Read case study
Multi-Agent Case Analysis
Multiple AI agents analyze different parts of a legal case at the same time. Results get aggregated and ranked by severity. I wrote the routing logic and aggregation specs. In detailed design phase.
0x throughput · HIPAA-compliant · hybrid cloud+edge
Runs on: Next.js · Convex · Claude API · Filevine API
Always-On Agent System
My daily operating system. One coordinator agent on a Mac Mini M4 delegates to specialists for coding, research, and analysis. Runs 24/7 across Discord, Telegram, WhatsApp, and iMessage.
Runs daily · multi-channel · persistent memory
Runs on: Mac Mini M4 · Multi-Provider AI
→ Read case study
What I Actually Do
Orchestration
- Claude Code
- Codex CLI
- Cursor
- Multi-Agent Systems
- Agent-to-Agent Coordination
- Model Routing & Selection
System Design
- PRDs & Technical Specs
- Architecture Planning
- CLAUDE.md / AGENTS.md Files
- Phase-by-Phase Execution
- Agent Task Decomposition
AI Operations
- Prompt Engineering
- Context Window Management
- Agent QA & Review
- Cost Optimization
- Multi-Provider Strategy
Domain Expertise
- PI Workflow Automation
- CHP & Government Systems
- API Integration (REST, Webhooks)
- HIPAA & Legal Compliance
Infrastructure
- Vercel / Fly.io Deployment
- Dedicated Hardware (Mac Mini M4)
- Cron Automation
- Multi-Channel Messaging
- Git & Version Control
Industries
Personal Injury Law
Thousands of decisions per week, buried in paperwork. I design AI systems that track cases, hit deadlines, and flag problems. I've built production tools for real PI firms handling real cases.
Operations & Field Sales
Reps in the field, leads going cold, managers drowning in data. I build the intelligence layer that keeps your pipeline moving. Same process: specs, agent execution, human review.
Admissions Consulting
Hundreds of students, dozens of deadlines, zero margin for error. I design systems that keep track of everything so consultants can focus on the students.
How I Work
From understanding your problem to shipping production software.
Understand
I learn your business. The decisions, the exceptions, the edge cases that only your best people know.
Spec
Detailed specs that coding agents can execute. PRDs, data models, constraints, phase-by-phase prompts.
Build
Agents write the code. I review every output and iterate until it works the way it should.
Review
QA, testing, polish. Nothing ships until it handles the edge cases your business actually hits.
Ship
Production deployment with documentation. I stick around to make sure it holds up.
I was in the first 1% of ChatGPT users. When the APIs opened up, I started building. When coding agents got good, I went all in. Three years of daily use across every major model and tool that's come out since.
I don't write code. I write specs and direct AI coding agents to build production software. Claude Code, Codex, Cursor. I have live apps serving real users right now. Every line was written by an agent I directed.
Most people are still figuring out how to prompt ChatGPT. I run multi-agent systems on dedicated hardware, route tasks to different models based on cost and complexity, and ship production code daily. That gap is where Manager Matt operates.
— Matt Sanchez, Founder