LiveMarket prices
Wheat flour (packaged)58—Ginger (imported)167—Ginger (local)154—Aman rice (medium)56—Aman rice (coarse)48—Aman rice (fine)72—Iodised salt (packaged)32—Green chilli218—Broiler chicken162—Mutton900—Sugar (local)132—Chickpeas (whole)85—Farm eggs (red)47—Onion (local)60—Boro rice (medium)55—Boro rice (coarse)47—Boro rice (fine)66—Beef729—Mung dal122—Garlic (imported)192—Garlic (local)173—Soybean oil163—
Updated 22 October 2026
Dhaka30°Clear skyHumidity 58%Wind 8 km/h

AI agent filed a Staffordshire farmer's SFI application in an hour, before funds ran out

Clive Bailye's AI farming agent, Giles, watched the government site, filled in his Sustainable Farming Incentive form when the window opened and had it ready to review by 10.30am; the pot closed at 3.48pm.

AI agent filed a Staffordshire farmer's SFI application in an hour, before funds ran out
Agrotech

An AI farming agent filled in and readied a Sustainable Farming Incentive (SFI) application worth hundreds of thousands of pounds for Staffordshire arable farmer Clive Bailye while he was in London, letting him submit it hours before the funding ran out, Farmers Weekly reports.

Bailye had used the agent, called Giles, to plan which SFI26 options suited his land two or three weeks before Window 2 opened on 22 September. On the day, the system monitored the government website, began filling in the application when the window opened at 10am and messaged him at about 10.30am that it was ready to review. He checked and cleared it on his phone, and it was in at 11.09am; the funding pot was exhausted at 3.48pm. "I'm blown away by it," he said.

Giles has analysed more than 20 years of yield maps and soil tests from TWB Farms near Lichfield, suggested growing spelt and found a microbrewery four miles away looking for growers, and sourced quotes for 10,000 litres of red diesel. Rather than one AI model, it picks the most cost-effective tool for each task from several large language models, builds a private "farm memory" from records and questions, and uses a second AI system to check its work, with final decisions left to the farmer. Each farm's data is kept separate and is not sold or shared with buyers or suppliers, the developers say.

Simon Haley, an independent adviser at SRH Agribusiness and a member of the CAAV's AI working group, called such tools "genuinely exciting and potentially valuable" but said farmers must take data governance and privacy more seriously. AI will take on more of advisers' administrative work, he said, but good professional judgement becomes more important, not less. The developer building the system says the idea came from Bailye himself.

Giles is being taken to market by Agigence, which has initial grant funding from Defra's Adopt innovation fund to let trial farmers use it free from November through most of 2027, with a public beta for a few hundred UK farmers, starting with arable, planned for early 2027.

Photo: Roger Kidd / Wikimedia Commons (CC BY-SA 2.0)

Source: Farmers Weekly

Farmers WeeklySource

Agrotech

Related stories

Comments

(0)