Kisan e-Mitra is a voice-based AI-enabled chatbot developed to assist farmers with responses to their queries regarding the Pradhan Mantri Kisan Samman Nidhi (PM-KISAN) scheme, one of India's largest social assistance programmes, which provides income support of INR 6,000 per year to over 90 million farming families across India. The chatbot was launched on 21 September 2023 by the Union Minister of State for Agriculture and Farmers Welfare, Shri Kailash Choudhary, and is described as the first AI chatbot integrated with a major flagship scheme of the Government of India.
The primary purpose of Kisan e-Mitra is to provide farmers with timely and accurate information about their PM-KISAN application status, payment details, ineligibility status, and any updates or modifications to the scheme. It functions as a comprehensive grievance redressal tool, offering farmers a one-stop solution for resolving queries that were previously handled through manual processes. Users can interact with the chatbot through three input methods: text input, voice input in their preferred language, and selection from a list of frequently asked questions. The system processes 49 distinct query categories using predefined response templates that are tailored with beneficiary-specific data to generate personalised replies relevant to each farmer's individual circumstances.
The technical architecture of Kisan e-Mitra employs natural language processing to interpret the intent of farmer queries and retrieve relevant information from the PM-KISAN scheme database. Following a significant enhancement in February 2024 led by Wadhwani AI, the system was upgraded to incorporate a Large Language Model for generating responses, improving the quality and accuracy of its outputs. Multilingual support is provided through integration with Bhashini, the National Language Translation Mission, which uses the IndicTrans2 model for translation capabilities. This integration enables the chatbot to accept audio and text queries in the user's preferred language and to provide responses in the local language in both text and audio formats. During Phase I, the chatbot was launched in five languages: English, Hindi, Tamil, Bengali, and Odia. It was subsequently expanded to 11 languages, adding Malayalam, Gujarati, Punjabi, Telugu, Marathi, and Kannada, with plans to eventually support all 22 official Indian languages.
The development and enhancement of Kisan e-Mitra has involved multiple institutional partners. The initial development was supported by EkStep Foundation and Bhashini, operating under the Department of Agriculture and Farmers Welfare (DA&FW). Following the February 2024 enhancement, Wadhwani AI played a central role in developing the upgraded AI and ML capabilities, with support from Google.org, the National Informatics Centre (NIC), and Samagra Governance. The chatbot is accessible through the PM-KISAN official website and the PM-KISAN mobile application, which also features face authentication-based e-KYC technology.
In terms of scale and usage, Kisan e-Mitra has demonstrated substantial uptake since its launch. Following the February 2024 enhancement, the system answered 2.69 million queries in just 186 days, representing a 668 percent increase compared to manual grievance redressal processes. Government reporting as of April 2025 indicated the chatbot was handling over 20,000 farmer queries daily and had answered more than 92 lakh (9.2 million) queries in total. By July 2025, this figure had risen to over 95 lakh (9.5 million) queries resolved. The Wadhwani AI impact dashboard reports over 5 million grievances resolved, more than 290,000 unique farmers served, and over 400,000 farmers enrolled, with geographic coverage spanning 28 states and 8 Union Territories, and the service operates on a 24/7 basis.
The system operates as an informational and grievance support tool rather than a decision-making system. It does not make automated eligibility or payment decisions; its function is limited to providing information lookup and query resolution based on existing scheme records. The decision criticality is therefore assessed as low, as incorrect or incomplete responses would delay information access but would not directly affect benefit eligibility or payment amounts. No primary source has been identified describing escalation pathways to human agents or specific human oversight protocols governing the chatbot's operations.
From a risk perspective, the primary concerns relate to the accuracy and reliability of the chatbot's responses, particularly given its reliance on NLP and LLM components that could generate incorrect or misleading information. Transparency to users regarding the AI-generated nature of responses and the limitations of the system is a further consideration. Accessibility remains a concern given that language coverage, while expanding, does not yet encompass all 22 official Indian languages, potentially excluding farmers who speak less widely supported languages. The chatbot's dependence on the Bhashini translation infrastructure and the IndicTrans2 model introduces an upstream dependency on the quality and availability of these services. No public documentation has been identified regarding formal risk assessments, data protection impact assessments, bias audits, or independent evaluations of the system's performance or accuracy across different language and demographic groups.