BuildRiot
Sign in

AISource: Google

Google opens Agricultural Understanding public preview with per-project approval

Google expanded Agricultural Understanding access to developers, startups and researchers. Its agricultural APIs offer field maps and historical crop predictions, but each Cloud project needs approval and provisioned quota.

By News DeskPublished here (UTC)1 min read
Google logo
Cover: BuildRiot

Google expanded Agricultural Understanding into public preview for developers, startups and researchers on October 15, 2026. Developers must create a Google Cloud project, request allowlisting and await email confirmation of quota provisioning. They can then enable the API and create an API key. Approval applies separately to each project, and Google recommends restricting the key to this API. Sources: Google, Google for Developers

Google documents field-map outputs and historical crop predictions with confidence scores. These outputs could support field-map overlays and interfaces displaying historical crop predictions. Sources: Google for Developers

Google says Amnex integrated the APIs into Gujarat's Krushi Pragati platform. Google also says OpenAgriNet, seeded and led by EkStep Foundation, uses the APIs for an administrator dashboard and is exploring a broader agricultural application. Soil-health, pest, weather and multilingual advice belong to the surrounding applications; the documented API outputs are field maps and crop predictions. Sources: Google, Google for Developers

Why it matters

Developers can build field-map interfaces and interfaces displaying historical crop predictions with confidence scores. Access still depends on project approval.

Attribution

Sources

  1. 1GoogleFrom lab to impact: Advancing AI for real-world progress in IndiaSource published (UTC)
  2. 2The WeekGoogle expands AI Initiatives across India, from agriculture and education to MSMEsSource published (UTC)
  3. 3Google for DevelopersAPI overview
  4. 4Google DeepMindAgricultural Understanding Platform
  5. 5Google for DevelopersResponse format
  6. 6Google for DevelopersUnderstanding the data

Read the original source for full details and context.

Report a problem

Links, dates or what you expected. Do not include passwords or private data.

More on AI

All AI stories

AI

Vercel reports production sandbox host-memory leakage

Vercel reported production host-memory leakage and host code execution from the same flaw on researcher-owned test machines. The findings put host patching, network policies and snapshot ownership under scrutiny for teams running untrusted agent code.

Vercel

AI

Google adds QueryData preview to Firestore with MongoDB compatibility

Google announced QueryData support for Firestore with MongoDB compatibility on October 12, 2026. Google says the feature lets developers build data agents that query database content through conversational language. Its documentation says QueryData translates natural-language questions into MongoDB-compatible Query Language (MQL) queries, using developer-supplied context sets with database-specific information. The feature is in preview, with potentially limited support.

Firebase