<?xml version="1.0" encoding="UTF-8"?><ns2:project xmlns:ns1="http://gtr.rcuk.ac.uk/gtr/api" xmlns:ns2="http://gtr.rcuk.ac.uk/gtr/api/project" xmlns:ns3="http://gtr.rcuk.ac.uk/gtr/api/fund" xmlns:ns4="http://gtr.rcuk.ac.uk/gtr/api/person" xmlns:ns5="http://gtr.rcuk.ac.uk/gtr/api/project/outcome" xmlns:ns6="http://gtr.rcuk.ac.uk/gtr/api/organisation" ns1:created="2026-06-03T15:52:43Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/FA812FE9-2ED3-4484-B3F1-37EB37A6540D" ns1:id="FA812FE9-2ED3-4484-B3F1-37EB37A6540D"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/EE792257-28A7-4152-BE38-FF956565AA13" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/525E4E55-97BD-4947-B163-10661CC97855" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/525E4E55-97BD-4947-B163-10661CC97855" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2025-02-28T00:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/C6E9CA76-AB49-4128-BFB1-E54838887B09" ns1:rel="FUND" ns1:start="2024-03-01T00:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">10105139</ns2:identifier></ns2:identifiers><ns2:title>DEEPSEEK 2.0: Harnessing AI For Data-Driven Agricultural Decision Making</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Collaborative R&amp;D</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>The goal of the DEEPSEEK project is to leverage the latest AI technologies for the benefit of the agricultural sector in the UK.

This industrial research project will use AI to help agricultural businesses de-risk their biggest decisions. It will unlock the latest agricultural research data, generating real-time, actionable insights for critical, time-sensitive decisions through natural language search.

Existing AI platforms have limited use in UK agriculture as they lack contextual understanding, are prone to generating misinformation and lack the accurate citations needed for specialist applications.

The InnovateUK grant funding will support the R&amp;amp;D costs needed to build and fine-tune the datasets, solution architecture, vector search algorithms and user interface needed to implement an intelligent agricultural database for a group of early adopter agricultural businesses in UK.

Following deployment and testing with early adopters, the tool could be scaled up to incorporate additional data sources and made available directly to end-users through a licensable web portal.</ns2:abstractText></ns2:project>