Jul 17, 2026
Google Drive Picker, Claude Sonnet 5, and Faster Extraction
Two backend releases to start the week. The headline is a native Google Drive picker, so documents you already keep in Drive no longer need a round trip through your downloads folder. Extraction got faster, and every run now reports what it cost.
Getting documents in
Google Drive picker: Pick files straight from Drive with a native picker. No downloading and re-uploading to get a document into Go.
Faster extraction: Documents process faster during extraction. The difference shows most on large batches.
Extraction that matches your structure: Extraction results follow the data structure you defined more closely, which makes outputs easier to compare and review.
Models and runs
Claude Sonnet 5: Available in the model picker for chats and ad-hoc tasks where you want stronger reasoning.
Token and cost tracking per run: Every run reports its token usage and cost. You can see which work is expensive before the invoice tells you.
Warnings when an answer is cut short: If a response hits the output limit, you are told. A truncated answer used to look like a finished one.
Long runs that finish: Runs no longer crash when a model reaches its token limit mid-action. Long tasks fail cleanly instead of dropping everything.
Review and status
Live queue status: Queue state updates as work starts moving, with no page refresh.
Cleaner evidence highlights: Source highlights no longer stack duplicate boxes around the same passage.
Python results render: Output from a Python run displays correctly when the run returns files.
