Retrieval is the secret-sauce surface: getting RAG right
Your consultant's body of work is the retrieval corpus. Embeddings, chunking, hybrid search, the prompt template that pulls in the right context, this is the surface that earns the bill.
Builds platforms and writes about them. Virtualization era to AI era — vRA, NSX, OneFuse, then Privian, now Helix (a publication where AI agents draft under review). Orlando.
Your consultant's body of work is the retrieval corpus. Embeddings, chunking, hybrid search, the prompt template that pulls in the right context, this is the surface that earns the bill.
One Postgres for both your relational data and your embeddings. Secrets in Secrets Manager. Encryption on by default. The MVP-grade data layer that doesn't need a forklift later.
The cheapest day-one decision is also the most expensive one to defer: auth, tenant scoping, and row-level security wired in before you have a single customer.
mflux, ollama/mlx-lm, fine-tuning, whisper, a batch runner, what runs on the desk, and the math on why it pays for itself in months.
Christmas 1991, ninth grade. I came out of the bathroom, looked across the hall into the family room, and there it was, a 386 DX40 my parents had hidden, waiting for Christmas morning. Three decades on, the instincts that machine drilled into me are the ones I'm reaching for in the AI age.
API Gateway, Lambda, Cognito, RDS+pgvector, Bedrock, S3, EventBridge, SQS, CloudFront, CloudWatch. The smallest cloud shape that actually ships.
Customer-facing belongs in the cloud. Training, batch, and eval belong on the desk. Here's why running both costs less and works better.
Captured judgment is not a model and it's not a knowledge base. It's the small set of things the consultant has personally learned from being wrong.
Most AI MVPs over-build the model and under-build the product loop. Here's the question that fixes that, and the eighteen pieces that follow it.
Mid-2026 honest read on personal AI assistants. What actually works, what's still vapor, and where Apple, Google, Anthropic, and OpenAI land on the consumer question. The gap between the demos and the daily-driver experience is still wide, but not as wide as it was.
The platform owns the foundation decisions. The product owns the business decisions. Most of the tug-of-war I've watched between platform and product teams comes down to no one having drawn that line in writing. DaC draws it, by making the decision surface itself the contract between them.
What the experiment is asking, the failures already encountered, and the failure shapes still on the watch list.