AI Lab / Work

Work & Case Studies

Every project in one scroll: what it is, the numbers that matter and the stack behind it. Open any case study for the full problem → solution → future scope write-up, linked to every page that documents the same project.

RAG · Conversational AI · Document Generation

Meeting Intelligence Chatbot

A web chat assistant that syncs meeting transcripts from a shared Google Drive folder, answers questions about them with hybrid-search RAG, and drafts delivery documents (Executive Summary, HLRD, User Stories, Timeline Matrix) through multi-stage LLM pipelines. It is a live project, deployed through a GitHub Actions workflow.

4 delivery documents drafted from meeting talk3 document-generation modes (fast, two-stage, chained)5 role-based personas guiding users44 automated test functions
PythonFastAPIPydanticFAISSSentence-TransformersBM25 (custom, pure Python)PyTorch (CPU)Google Drive APIPyPDF2python-docxopenpyxlpython-pptxpandasReact 18TypeScriptViteTailwind CSSreact-markdownjsPDFhtml2canvaspytestGitHub ActionsPM2Nginx
Read the case study
Multi-Agent Orchestration · Agentic Workflow

AI Executive Command Center

A multi-agent orchestration system that works as a small brand's virtual executive team: one conversational orchestrator routes every request to six specialist agents, who produce campaign strategy, launch and event plans, roadmaps and print-ready apparel artwork. A full executive-team run takes about 60–90 seconds and $0.10–0.30.

~60–90 seconds per full 7-round strategy run~$0.10–0.30 per full run (10–12 LLM calls)1 orchestrator + 6 specialist agents138 test files
Next.js 14 (App Router)React 18TypeScriptNode 20SQLite (better-sqlite3, WAL)ZodMCP TypeScript SDKjose (JWT)sharpdocxpdfkitVitestGitHub ActionsServer-Sent Events
Read the case study