Site launch
Launched codavidgarcia.com. My personal site showcasing the intersection of technical leadership and AI engineering.
I like designing systems where LLMs actually help people get work done. RAG pipelines, multi-agent workflows, tools that integrate into existing processes.
Bridging the gap between "here's what we want" and "here's what we shipped." Keeping projects moving, teams aligned, and stakeholders informed.
Building AI-first products from scratch: HugeContext, Docsalia, Claritude. All in production, all solving real problems I encountered.
Finding workflows that feel painful and automating them away. Whether that's dev tooling, data pipelines, or team coordination.
End-to-end: concept → architecture → code → production
Evidence-Gated Multi-Agent Code Generation Under Repository Constraints
Modern LLM coding assistants are excellent at finishing requests, but real engineering failures happen when a “finished” change quietly violates a repository’s constraints: module boundaries, security posture, test contracts, and operational assumptions. This working draft proposes a governance-first architecture that makes repository fitness the stopping condition. It combines local grounding (HugeContext), an Agent–Auditor loop (HugeCode), and a deterministic Gatekeeper that enforces fitness functions via static analysis, tests, and policy checks.
Launched codavidgarcia.com. My personal site showcasing the intersection of technical leadership and AI engineering.
After months of development and testing, HugeContext is now production-ready. 17x smaller than competitors while delivering better retrieval quality.
Made significant progress on the RAG evaluation framework paper. Case studies from enterprise deployments are coming together.
If you're working on something interesting and think I might be helpful, I'd love to hear from you.