CoreWise Academy

Building with AI · Layer IV / Broad

Build a knowledge base your team can ask

Retrieval augmented generation in plain terms: put the relevant facts in front of the question. How to feed the chat, docs, and code your team already uses into a knowledge base anyone can ask, and why weighting beats volume.

Nº 023 · Vol. I·7 min read· Updated July 2026

“the whole company’s answers, one question away”

The hype version of a company knowledge base is a glowing 3D brain floating on screen. The useful version has no picture at all. It is a system that reads everywhere your team already writes, the chat threads, the wiki, the code, and lets anyone ask a plain question and get an answer drawn from all of it. Nick Saraev walked through one that a chip company, Cerebras, runs internally and wrote up in detail, fielding about 15,000 questions a day.

01Put the answer up front

Retrieval augmented generation is just fetching the facts, and the whole game is finding the right facts to put there, and a knowledge base is the machine that finds them. This is the automatic version of what you do by hand when you Brief the model like a brilliant new hire.

02Gather what your team knows

A knowledge base is only as good as what you feed it, so feed it where the knowledge already lives. Slack messages, the wiki of checklists and onboarding pages, the code and its history, and any database of numbers you track.

03Store more than the raw text

Label each item. A chat thread does not go in as a wall of text: a model reads it first and attaches who spoke, when, what they were asking, and how it resolved, etc.

Those labels let the knowledge base weight what it finds. A founder’s message from a minute ago should count for more than a junior’s note from three years back, and a question about last week’s seminar should surface last week’s, not all of them equally. Weighting by recency and source is the difference.

04Match on words and on meaning

When a question comes in, the knowledge base has to find the right saved item, and matching on meaning alone is not enough. Cerebras tried that first and it fell short, so it now runs two kinds of match together.

Exact word matching catches an error string, a host name, or a flag someone pasted in, where the precise characters are the whole point. Let the newer answer win a tie, and each one covers the other’s blind spot.

“how effectively can you retrieve the highest quality ones, the most relevant ones”

Nick Saraev, “Cerebras Just Killed Second Brains” · 22:05

05Build it with a coding agent

Coding agents can build the ingestion pipelines, the plumbing that pulls data in, for Slack, email, GitHub, etc.

You supply the understanding of how the data should flow; the agent supplies the wiring.

A knowledge base is the team-sized version of what one agent gets when you Give your agent a memory.

“a system that allows us to store information before the question”

Nick Saraev, “Cerebras Just Killed Second Brains” · 4:37

Further reading

FAQ

In one sentence, what does retrieval add to a model's answer?

It places the relevant facts directly in front of the question, so the model answers from those facts instead of guessing across everything it half remembers.

Why weight recent, trusted items above the rest?

A knowledge base that skips this treats every document the same, so a three year old note can outrank a founder's message from a minute ago. Weighting by recency and source pushes the answer toward what is current and trustworthy.

What matters more than the number of documents you store?

How well the knowledge base retrieves the few most relevant ones. Nick kept about 640 documents and a large company keeps hundreds of thousands, yet the better system is the one that pulls the highest quality match, not the biggest pile.

Sources
  1. Nick Saraev · “Cerebras Just Killed Second Brains”
    cited at 2:07 · 4:37 · 7:55 · 9:55 · 12:00 · 14:51 · 20:03 · 22:05