Meeting Intel How it works
How it works: two phases
All OpenAI does is turn text into numbers, or write text. The matching happens in our own database.

When you upload a meeting  (happens once)

Transcript

→

Split into chunks

~200 words each (a few speaker turns).

→
OpenAI

Turn each chunk into numbers

1536 numbers = a “meaning fingerprint”.

→
Our database

Store chunks + numbers

Also, once: OpenAI reads the whole transcript → the meeting’s Decisions & Action items.

When you ask a question  (every time)

Your question

→
OpenAI

Turn it into numbers

→
Our database

Find the 6 closest chunks

Nearest “meaning fingerprints”.

→
OpenAI

Write the answer

From those chunks, with citations.

Embedding = turning words into numbers that capture meaning. At question time our database — not OpenAI — compares the numbers to find the best matches.