Prashanth AI
Technology

A stack chosen for production, not demos

Every tool here earns its place by how it performs under real usage — not by how it looks in a slide deck.

Languages

  • Python
  • TypeScript
  • Dart

Frameworks

  • FastAPI
  • Next.js
  • Flutter
  • React

AI & LLM

  • OpenAI
  • Anthropic
  • Google Gemini
  • LangChain
  • LlamaIndex

Databases

  • PostgreSQL
  • pgvector
  • Redis

Vector Databases

  • Qdrant
  • Pinecone

Cloud & DevOps

  • AWS
  • Azure
  • Docker
  • GitHub Actions
Engineering principles

How we choose and use this stack

Model-agnostic by design

We architect around OpenAI, Anthropic, Google Gemini, and other providers interchangeably — your system isn't locked to one vendor's roadmap.

Retrieval before generation

Answers are grounded in retrieved context first. The LLM's job is to reason over what was retrieved, not invent from memory.

Observable in production

Every pipeline ships with logging and evaluation hooks, so accuracy can be measured and improved after launch, not just at demo time.