Daniel Zaitzow

Less so for building the product but for internal comms - it is vital to our workflow and the unsung hero for actually staying aligned as a small team.

We found that the outputs we were getting were consistent - to get to production it was also relatively cost effective. On top of that, the latency was low enough to keep things fast for users, and the massive context window meant we didn't have to build complex data pipelines just to handle the risk large inputs.