TuringTalks

Learn to build and deploy LLMs to production. 2-3 articles a week. 100% free.

Latest Posts

Agents 101 — Build and Deploy AI Agents to Production using LangChain

Nov 24, 2025

•

15 min read

Agents 101 — Build and Deploy AI Agents to Production using LangChain

Learn how Langchain turns a simple prompt into a fully functional AI agent that can think, act and remember.

Manish Shivanandhan

Build, Manage, and Ship Python Projects the Easy Way using Poetry

Nov 20, 2025

•

9 min read

Build, Manage, and Ship Python Projects the Easy Way using Poetry

A guide to understanding Python Poetry, how it works, and how to use it in your next Python project.

Manish Shivanandhan

How to Compress Your Prompts and Reduce LLM Costs

Nov 15, 2025

•

8 min read

How to Compress Your Prompts and Reduce LLM Costs

Microsoft just solved the hidden cost problem in AI with LLMLingua, making large language models faster, cheaper, and smarter.

Manish Shivanandhan

How to Add Real-Time Web Search to Your LLM Using Tavily

Nov 12, 2025

•

7 min read

How to Add Real-Time Web Search to Your LLM Using Tavily

Learn how to connect Tavily Search so your AI can fetch real-time facts instead of guessing.

Manish Shivanandhan

How to Keep LLM Outputs Predictable Using Pydantic Validation

Nov 10, 2025

•

6 min read

How to Keep LLM Outputs Predictable Using Pydantic Validation

Tired of LLMs breaking your JSON or skipping fields? Learn how Pydantic can turn messy AI outputs into clean, predictable data every single time.

Manish Shivanandhan

Cut AI Costs Without Losing Capability: The Rise of Small LLMs

Nov 8, 2025

•

7 min read

Cut AI Costs Without Losing Capability: The Rise of Small LLMs

Learn how small language models are helping teams cut AI costs, run locally, and deliver fast, private, and scalable intelligence without relying on the cloud.

Manish Shivanandhan