getEvalsUseful evals for real-world tasks.
A Puma experiment. Measure AI on work that matters to you — privately, on your device — not someone else's leaderboard.
Private by design
Public benches show how models behave in the wild. Private evals tell you whether your prompts, tools, and agents hold up on the tasks you actually run. Your gold answers stay on your device.
Cases you keep
Capture the tickets, documents, and workflows your system must handle. Nothing is uploaded. You are not training the industry on your test set.
Graders you control
Score with exact match, contains, regex, JSON field checks, and keyword lists. Start simple, then tighten the rubric as the work gets clearer.
Runs that stay local
Paste model outputs, label the system under test, and keep a history of pass rates as prompts and models change — all in this browser.
Two paths. One purpose.
getEvals sits next to Puma Browser and the PumaAI lab. Same purpose: AI that stays in your hands.
01 / Company
Puma.tech
AI, on your terms. A more personal browser, and research toward a future where AI stays in your hands.
02 / Research
PumaAI
A small lab studying private local inference, observable agent harnesses, and memory store.
03 / Product
Puma Browser
Local and cloud AI, right in your browser. Private by design. iOS and Android.