Over the last year or so, the data science team at IDinsight has been busy building AI products like Ask-A-Question and Ask-A-Metric. A few months back, I was on a panel on GenAI for Social Impact and was asked if they should be investing in AI or not. I talked about how AI is a tool and we want to be problem driven. I talked about thinking about your use case and finding the tool that fits it best instead of starting with the AI hammer and looking for a nail.
With all the hoopla around AI of late, these are questions on the minds of almost all social sector organizations. Below is how I see it. I’d love to hear your thoughts.
We’ve spent the last 8 months or so building Ask-a-Question, an AI question-answering service for direct-to-citizen helplines. We decided not to create yet-another-RAG solution. Ethan Mollick summarizes our concerns well. In short, the tech for a cheap, scalable, and guaranteed error-free AI is not there - the kind that you’d want to roll out to citizens in high risk and high trust use-cases like health. Instead, we wanted to lean on our experience building a question-answering for MomConnect to build something that is (a) trustworthy; and (b) provides actionable insights to support continuous learning and improvement.
We have fine-tuned the Gemma-2 2-billion parameter instruction model on a custom dataset in order to detect whether user messages pertain to urgent or non-urgent maternal healthcare issues. Our model demonstrates superior performance compared to GPT-3.5-Turbo in accurately distinguishing between urgent and non-urgent messages. Both the dataset and the model have been made publicly available to support further research and development in this critical area.1
TL;DR: We are comparing Ask-a-Metric (AAM) and vanna.ai performance, on metrics that we find ourselves regularly testing for AAM use-cases. We find that Ask-a-Metric performs on-par with vanna.ai for straightforward queries, but struggles with more complex queries. Vanna.ai also struggles with complex queries and lacks guardrails, but has a greater range of features than AAM.1
Ask-a-Metric is a WhatsApp-based AI data analyst that uses LLMs to answer SQL database queries, facilitating data access for decision-making in the development sector (GitHub). Initially, we used a simple pipeline for rapid feedback but faced challenges in accuracy and building it for scale. We tested an agentic approach with CrewAI, improving accuracy but ending up with high costs and slow response speeds. We used these results to develop a pseudo-agent pipeline that combines the best of both approaches, reducing costs and response times while maintaining accuracy.1
It’s the GenAI age. Every person and their grandpa is creating AI chatbots based on RAG. For farmers, for mothers, for teachers, for bureaucrats. Hey, we’re doing it too!
But here’s a hot take: you don’t need a RAG AI chatbot. Definitely not at the start. Probably not ever.
