Design6 min read
Citations that actually work: designing trust into AI answers
A confident wrong answer costs more than no answer at all. Here is the citation UX we landed on after watching 40 support agents use Lumen.
Priya Raman · Feb 18, 2026
Writing
Notes on retrieval, knowledge and shipping
What we learn building Lumen: chunking strategies, citation UX, knowledge-base rollouts and the occasional launch retrospective.
RAG8 min read
Chunking is 80% of your RAG quality
Model choice gets the attention. Chunk boundaries decide whether retrieval finds the right paragraph. A practical guide with the settings we ship.
Yuki Tanaka · Feb 4, 2026
Knowledge7 min read
How to build an internal knowledge base people actually use
Most wikis die within six months. The fix is not more documentation — it is reducing the cost of retrieval to almost zero.
Marta Kowalski · Jan 22, 2026
AI search5 min read
AI search vs keyword search: when each one wins
Semantic search is not a strict upgrade. Hybrid retrieval beats both, and the reason is more interesting than the benchmark.
Yuki Tanaka · Jan 9, 2026
Design6 min read
Landing pages that convert for AI products
AI landing pages all look identical because they all describe the model instead of the job. Six changes that move signups.
Sofia Marín · Dec 15, 2025
Building9 min read
What we learned launching a SaaS in public
Ninety days, one paid pilot, and a lot of things that did not work. An honest retrospective with the numbers included.
Sofia Marín · Nov 30, 2025
Stop searching. Start asking.
Connect one folder and ask your first question in under five minutes. Free forever for solo use, no credit card, no sales call.
We'll only email you about your account. Unsubscribe in one click — see our privacy policy.