Aaliyah Johnson

Years in this space

I've evaluated a lot of these over the years. What stands out here is education-friendly worksheet output — handled better than most — and adjustable difficulty and size. Limited to maze-style puzzles only is my one real gripe. Worth the time if this is your use case.

Years in this space

I've evaluated a lot of these over the years. What stands out here is historical backtesting engine — handled better than most — and fast prototyping from plain-language ideas. Worth the time if this is your use case.

Solid for our team

We rolled this out across the team last quarter and backed by Google's research and tooling. Open-source model weights fits neatly into how we already work, and multiple parameter-size variants removed a step we used to do by hand. Hardware demands grow with larger variants, which is the main caveat, but it has held up under daily use.

Compared a few options

Evaluated this against two competitors. Where it wins: chat-based email drafting and conversational editing for easy revisions. On balance the feature set — especially chat-based email drafting — justifies the 5 stars for our use case.