I built an AI-powered research intelligence platform that helps analysts and business teams query complex datasets through a single conversational interface.
๐๐ก๐ ๐๐ซ๐จ๐๐ฅ๐๐ฆ
Research teams often work across disconnected databases, reports, spreadsheets, dashboards, and documents. This slows analysis, makes cross-source searching difficult, and can reduce trust in AI-generated answers.
๐๐ก๐ ๐๐จ๐ฅ๐ฎ๐ญ๐ข๐จ๐ง
The platform combines RAG, AI agents, natural-language-to-SQL, structured and unstructured retrieval, source attribution, confidence scoring, and evaluation pipelines.
Users can ask a business question in natural language, and the system decides whether to search documents, query databases, run SQL, or combine multiple sources before returning an evidence-backed answer.
๐๐๐๐ฎ๐ซ๐๐๐ฒ & ๐๐ซ๐จ๐๐ฎ๐๐ญ ๐๐ฑ๐ฉ๐๐ซ๐ข๐๐ง๐๐
The system evaluates answer correctness, retrieval quality, SQL accuracy, source relevance, hallucination risk, and response performance. Low-confidence results are captured for review and continuous improvement.
The frontend is built with React + TypeScript and includes AI chat, dataset exploration, source references, analytics, evaluation dashboards, and real-time updates.
Impressive work. Bringing RAG, natural-language-to-SQL, source attribution, confidence scoring, and evaluation into one research platform solves a very real problem for data-heavy teams. The focus on accuracy and evidence-backed answers makes this especially valuable.
The A mark built on a diagonal grid, with the ramp stepping up on the right, is simple and holds up on the black AdRamp card. My challenge: the palette shows green and salmon swatches next to the black, but every application tile is black, white or grey. If the accent colours...
Three new portfolio templates out ๐ฅ
Gist: one switch folds every case study down to its key sentences.
Plakat: type at poster scale, and one button inverts the whole site.
Tinta: hover a project and the page takes its colours.
HTML, React and Framer.