Products & Tools

CSU Extension Specialist Brings AI Chatbot to Colorado Farmers

Xue "Alice" Dong built a Python chatbot grounded in Extension publications to help Colorado ranchers run agritourism businesses, taught 200+ entrepreneurs, and was named a 2026 GenAI for Good finalist.

Community-Focused Academic Brings AI Tools to Colorado Farmers
Community-Focused Academic Brings AI Tools to Colorado Farmers12019 / pixabay
By James Calloway7 min read

Why it matters

  • Xue "Alice" Dong built the AI-Powered Agritourism Chatbot in Python using retrieval-augmented generation over curated Extension publications.
  • Her AgriPivot AI Agent was a finalist in the 2026 GenAI for Good Challenge, selected from 318 teams across 79 countries.
  • She has taught her AI workshop 20 times to more than 200 entrepreneurs from 32 Colorado counties; 90 percent reported trying a new AI task.
  • She has secured seven competitive grants totaling more than US $250,000, including USDA NIFA funding.
  • The chatbot runs in a web browser rather than as a phone app because many farmers she serves don't own a smartphone.

A Colorado State University Extension specialist has built a chatbot that answers farmers' questions about starting agritourism businesses, using retrieval-augmented generation over trusted Extension publications rather than an unconstrained language model. Xue "Alice" Dong's project was named a finalist in the 2026 GenAI for Good Challenge, selected from 318 teams across 79 countries, and her AI workshops have reached more than 200 entrepreneurs from 32 Colorado counties.

The stakes are straightforward. Many farmers and ranchers in eastern Colorado are curious about artificial intelligence, but they have no local technically trained person to show them how to use it. Dong has made that her job — and a test of whether generative AI can be made useful to populations the technology industry rarely designs for.

Who is Xue "Alice" Dong?

Dong is an IEEE senior member and an extension regional specialist with the Colorado State University Extension, CSU's outreach arm. She works in Logan County and serves a 10-county farming area in Colorado's northeast corner. Her role is to turn university research into practical help for the people who live there.

"We [extension specialists] act as a bridge," she says. "We bridge our campus to the rural communities we serve."

That bridging function matters here. Many of the farmers and ranchers she serves are older and have no technical training. Often their children and grandchildren have left the farm for city jobs or are simply not around to teach them new tools. Without intervention, Dong argues, the benefits of AI could pass them by.

Her credentials stack up quickly. In 2026 she was named a finalist in the GenAI for Good Challenge — organized by IEEE Humanitarian Technologies and the U.N.'s International Telecommunication Union — for her AgriPivot AI Agent. She also won the 2026 Award for Innovation from the National Extension Technology Community (NETC), plus both the 2025 national and Western regional Educational Technology Awards from the National Association of Community Development Extension Professionals (NACDEP). She has secured seven competitive grants totaling more than US $250,000 as principal investigator or co-principal investigator, including funding supported by the Department of Agriculture's National Institute of Food and Agriculture.

The takeaway: this is not a hobbyist project but a federally backed extension program with peer-reviewed output behind it.

What does the chatbot actually do?

In 2025, Dong earned a third master's degree, in artificial intelligence and machine learning, from CSU Global. She immediately applied those skills to agritourism — farms opening their property to visitors for fun, education, or shopping, such as pick-your-own fruit orchards, growing lessons, and sales of handmade products.

She built the AI-Powered Agritourism Chatbot (AgriTourismAI.com) in Python. The interface resembles ChatGPT's, but the mechanics differ. Under the hood it uses retrieval-augmented generation (RAG), a technique where the AI looks up information in a curated set of trusted documents before answering. Dong curated that collection from Extension publications, so answers rest on authoritative sources and are, in principle, less likely to be fabricated.

The design choices reveal a close reading of her audience. The bot runs in a web browser rather than as a phone app. Many farmers she works with don't own a smartphone, Dong says, but nearly all have a computer, tablet, or other web-capable device. No download required.

Typical questions include how to attract visitors and how to write a business plan. A farmer considering a corn maze can ask how to price admission, what insurance to carry, and which permits to get. The bot also advises on managing risk. What the source does not say: any measured effect on farm revenue. Dong documented one deployment — Prairie Ridge Buffalo Ranch in eastern Colorado — in a peer-reviewed 2025 case study, "Revolutionizing Agritourism with AI and Machine Learning," published in CABI Tourism Cases. Surveys and interviews with other users showed they found the bot easy to use, learn from, and act on, she says; full results are still being prepared for publication. Presented at NeurIPS 2025, the code is openly available on GitHub so other Extension offices can adapt it.

In plain words: the bot is grounded, browser-based, and open-source — three deliberate constraints, with adoption evidence still in progress.

How she teaches AI beyond the chatbot

Dong's concern is not only whether people use AI but how. In 2026, she and Paul Hill of Utah State University Extension published "From Access to Governance: Generative AI Literacy for Extension Professionals and Small Businesses, and a Governance-Aware Design Framework" in the journal AI. The paper offers a framework for responsible generative AI adoption.

She also teaches hands-on workshops on ChatGPT, Claude, and Gemini — 20 sessions so far, reaching more than 200 entrepreneurs and business owners from 32 Colorado counties. In follow-up surveys, 90 percent of participants reported trying at least one new AI task in their business. Venues include a community center run by the Logan County Economic Development Corp. in Sterling, co-hosted sessions with the Rural Community Assistance Corp., Colorado Startup Week, and Boulder Startup Week, plus webinars for people who can't travel.

Her work extends past agriculture. In 2026 she contributed an AI assistant to Project Pythia, an open-science program funded by the U.S. National Science Foundation and led by the National Center for Atmospheric Research. The assistant converts raw airport weather report data into plain-language guidance for farmers and other non-technical users — and flags missing data rather than guessing, a small design decision that speaks to her grounding-first philosophy.

How did she get here?

Dong was born in Beijing; both her parents are doctors. As a child she drew inventive things, sketching solutions to problems before building them. "I've always had a passion to create something tangible that can solve problems in the real world," she says. She credits no single mentor — all her teachers, she says, laid the groundwork.

She earned two bachelor's degrees at Inner Mongolia Normal University in Hohhot in 2013, one in geographical science and one in education, then a master's in curriculum and instruction from Beijing Normal University in 2016. That year she moved to the United States, earning a master's in environmental biology from SUNY's College of Environmental Science and Forestry in Syracuse in 2020.

She then worked as education and outreach coordinator at Paul Smith's College in New York, managing national watershed projects and invasive-species prevention, writing grants, and building educational sites including Maintain the Chain for the Fulton Chain of Lakes in the Adirondacks. In 2022 she joined Stewards of the Coast and Redwoods in Guerneville, Calif., as program manager, working with California State Parks on Sonoma County's coast and the Russian River area. She left in 2023 for the CSU Extension.

The Cooperative Extension System she joined is a nationwide network run by land-grant universities — schools founded with federal grants to teach practical subjects. It is overseen federally by USDA's National Institute of Food and Agriculture, managed statewide through land-grant universities, and delivered locally across more than 3,000 counties. Dong lives and works in Sterling, a small rural town, but many people she helps live one to four hours' drive away, so most work happens by email, phone, and virtual meetings.

"We need to translate that research into something more practical, and easier to use, that farmers and ranchers can understand immediately," she says.

What comes next?

Dong joined IEEE in 2025 and was quickly elevated to senior member. Her professional home is the IEEE Society on Social Implications of Technology; she serves as vice treasurer of the IEEE Denver Section's Young Professionals group. She presented "Entrepreneur AI Agent: Empowering Small Businesses and Bridging the Digital Divide through Context-Aware Generative AI" at the 2026 IEEE Global Humanitarian Technology Conference and attended the IEEE World Forum on Public Safety Technology in Boulder, Colo., in September 2026.

Her advice to students considering the field: pick a specialty based on passion — livestock, natural resources, food systems, or 4-H — because extension work offers a third path beyond academia and industry. "You apply advanced skills directly to the communities that need them," she says.

Her assessment of her audience remains the same. The people of eastern Colorado are curious about new technology, she says, but they can't make the leap alone. "They really need this kind of a bridge."

Source: spectrum.ieee.org

Share this article:

More from James Calloway

James Calloway

Show full bio

News editor covering people, launches and day-to-day practice in artificial intelligence and machine learning at AI In Context.

791 articles

Related articles

  1. 67.8% of Workers Now Use AI Weekly — But 56.4% Get No Time to Learn It
  2. OpenAI expands ChatGPT Edu across four Australian universities
  3. OpenAI Signs Memorandum of Understanding With U.S. DOE
  4. OpenAI commits to 10 million AI certifications by 2030 with Walmart
  5. AI CEOs Keep Pitching a Future Nobody Asked For

« Previous articleNext article »