New — every answer now cites its sources
Blog

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.

RAG
6 min read

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

Tutorial
8 min read

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

Case study
5 min read

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

Marketing
7 min read

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

Launching
6 min read

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

AI search
5 min read

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