Back to projects

GenAI · Engineering case study

AI Agent Platform

Client: Pollstar

Intelligent, tool-connected agents for the music industry. Built for multi-step execution and production observability.

LangGraphAzureFastAPIRAGReactTailwind CSSshadcn
Illustrative architecture
ClientAPI · App ServiceAgent · LangGraphModels & toolsData & retrievalAZURECONNECTED SERVICESvector searchstatetracesReact appChat interfaceFastAPIAzure App ServiceLangGraph agentSingle LangChain agentMemory · checkpointsRAG retrieverDocument readingGPT-5.4Azure AI FoundryGPT-5.4 miniAzure AI FoundryFunction AppAgent toolsCosmos DBChats · agent stateFAISS indexDocument vectorsLangSmith · LangfuseTraces · prompts · costMusic APIs.NET product backend

01

The problem & context

Pollstar, a live-entertainment industry publication, connecting language models with internal and external music APIs through a web app and agent.

02

Architecture

A React chat interface calls FastAPI on Azure App Service, which runs a single LangChain and LangGraph agent with memory and checkpointing. The agent reasons with GPT-5.4 and GPT-5.4 mini through Azure AI Foundry, calls tools hosted on an Azure Function App that consume the existing .NET music APIs, and uses retrieval-augmented generation over a FAISS index to read documents. Azure Cosmos DB holds conversations, agent state, and metadata, while LangSmith and Langfuse support tracing, evaluation, prompt monitoring, and cost tracking.

Illustrative system view, not a production screenshot.

03

Implementation & my contribution

  • Built the web interface with React, Tailwind CSS, and shadcn.
  • Developed backend APIs and agent workflows using LangChain and LangGraph.
  • Integrated Azure AI Foundry models and Azure Cosmos DB for conversations, agent state, and metadata.
  • Implemented memory, checkpointing, multi-step execution, structured outputs, retries, and validation.
  • Used LangSmith for tracing and evaluation and Langfuse for prompt monitoring and cost tracking.
04

Outcome

Delivered tool-connected agent workflows with observable execution; optimized API performance, token usage, and response latency.

Testimonials

Voices from collaboration.