Create a short video to deliver news reports through an AI generated news anchor/reporter. This bot is designed to understand and respond in Hindi only.

This bot is designed to ask to help students fill out scholarship applications from their school records and identity documents. It asks for their ID documents, schoolmarks and then visually understands the data inside in them and then builds to build a profile of the user. It's a great example of using GPT4-Turbo in conjunction with advanced OCR to recognize text (which GPTV doesn't do well), combined with audio speech recognition in a WhatsApp bot using 11labs

Aimed at Indian farmers and Extension Agents, this copilot uses a collection of documents and transcripts of 100s of videos representing best practices from the Indian Ministry of Agriculture and Digital Green's video transcripts & FAQs to answer common questions from Indian farmers. We load these documents + transcripts into a vector database and with each question, we search the DB and add the results to create an answer to the farmer's questions. Additionally, the copilot features WhatsApp follow-up and location buttons plus agentic web search to get local weather and prices. It also leverages ISDA's Africa soil API to look up soil information based on the user's location.

Click here to read the case study.

ClassMate is an AI Teaching Assistant trained on Teach For India's rich pedagogy-related artifacts to support teaching Fellows working in under-resourced classrooms across India. Click here to read the case study.

Compares a set of the latest sovereign and private models for their responses being similar to our golden QnA of common small shareholder farmer questions and answers (in English) from ClearGlobal and Opportunity Intl. What makes a good golden eval QnA? Click here to read the case study.

Evaluate AI-generated images for cultural bias at scale. Upload a CSV dataset, run image tests in parallel and use the Culture Image Bias Evaluator to generate individual verdicts and an aggregate bias score. Compare prompts, models and settings for responsible AI testing.