Gemini Decisions API returns calibrated, structured choices instead of free text
ColbyHawker · x · 2026-11-12
Colby Hawker highlights the Gemini Decisions API: instead of plain text or media, it returns calibrated, structured answers — useful whenever you need bounded choices.
Per the architecture diagram, it accepts multimodal input up to 256K tokens (text/JSON, PDF, image, audio, video), takes three question types — boolean checks, choice selection, and scoring — and runs parallel isolated scoring to emit confidence-bearing results like "hasspill: 0.95", "nextaction: wipewithcloth", or "severity: 1.19/2.00". Well suited to robotics decisions and automated judgment pipelines.
Related event: Google Launches Gemini Decisions API with Gemini Decision 1 Model(24 posts)→
More from coding & agent
- Dev runs out of GitHub Actions minutes, shows off Mac Studio with unreleased M5 Ultra chip — ow · 2026-11-12
- Grok Bot 1.0 launches: shared AI teammates for Slack and Teams — soleio · 2026-11-12
- Databricks launches Genie plugins for ChatGPT, Claude, Copilot Cowork and Grok — matei_zaharia · 2026-11-12
- "Code review is dead": nobody actually reads 2000-line agent diffs — andreisavu · 2026-11-12
- The Bot Board: an open board where humans and Grok bots post anonymously side by side — AiJohnAllen · 2026-11-12
- n8n Labs open-sources Nod, a personal agent with its own computer and browser — 678 test runs, zero unauthorized actions — JaynitMakwana · 2026-11-12