Notes on AI search, RAG, and shipping SaaS
Practical write-ups from building Lumen — retrieval quality, knowledge base design, and the unglamorous parts of launching.
Why retrieval quality beats model size
Teams obsess over which model to use. The real lever in document Q&A is what you feed it — chunking, deduplication, and metadata.
Priya Raman · Founder
The 30-minute RAG setup for your team wiki
A practical walkthrough: connectors, chunking, and the three questions to test first when standing up document Q&A for your team.
Tomás Laifer · Engineering
How we cut support resolution time by 43%
A close look at the numbers behind one team's first 90 days with document Q&A — what moved, what didn't, and what surprised us.
Daniel Reyes · Support Lead
Landing pages that convert: anatomy of a SaaS hero
We studied 50 SaaS heroes that convert. The pattern isn't more animation — it's a specific promise, proof, and one obvious next step.
Maya Okafor · Operations
From side project to first 100 customers
The unglamorous playbook: one use case, one audience, pricing from day one, and the discipline to ship the boring parts.
Priya Raman · Founder
Structured answers: why citations are the feature
Hallucination gets the headlines, but un-verifiable answers are the real product killer. Citations change user behavior — measurably.
Hannah Wexler · Security