Jul 21, 2026

GPT-5.6, Questions Inside Cases, and a Favorites Sidebar

Five releases over the weekend and Monday. The one worth reading twice: a case can now stop and ask you a question mid-run rather than guessing at the answer.

Models

  • GPT-5.6: Pick GPT-5.6 from the model picker when you set up a chat or a task. Prompt caching works correctly with it, so responses come back without the loading stalls the first builds had.

Cases and workflows

  • Questions inside cases: A case can pause and ask you for input before it continues. Required questions stay in front of you until they are answered, so a run does not proceed on a guess.

  • Field recovery: A project with recalculation switched off can recover fields that never finished computing. No manual repair, no blank column.

  • Folder sync controls: Turn sync on or off for one folder at a time instead of all or nothing.

  • Required integrations, connected in place: When a workflow needs an integration you have not connected yet, you can connect it without leaving what you were doing.

Evidence and citations

  • More accurate citations: Citations match the source text more precisely, including text inside web pages. The stray anchor text, extra blank lines, and misplaced highlights are gone.

  • Citations in generated artifacts: A generated page carries its citations in the content, so you can check a figure without reopening the source pile.

Reporting and scripts

  • Favorites sidebar: Favorites live in the sidebar, persist across sessions, and can be added from context menus. There is a documented API for them too.

  • Python scripts that take input: A Python run can accept input while it runs, so scripts that prompt for a value or read pasted data work as written.

  • Workspace usage reports: Token usage reports name the workspace on every row. Admins stop stitching per-workspace exports together.

Precision AI for Institutional Workflows

Build once.
Deploy across teams.
Improve over time.

Precision AI for Institutional Workflows

Build once.
Deploy across teams.
Improve over time.

Precision AI for Institutional Workflows

Build once.
Deploy across teams.
Improve over time.