Medium

Lina Faik

Pinned

Lina Faik

·

Oct 5, 2025

Why I Started The AI Practitioner

… And Why You Should Subscribe

Why I Started The AI Practitioner

Lina Faik

·

2d ago

Inside GEPA: Evolving LLM Agent Prompts with Reflective Feedback

From Execution Traces to Better Prompts: A Practical Walkthrough

Inside GEPA: Evolving LLM Agent Prompts with Reflective Feedback

Lina Faik

·

Nov 3

TextGrad in Practice: Optimizing LLM Agent Prompts with Textual Gradients

How Textual Gradients Turn Banking Classification Errors into Measured Prompt Updates

TextGrad in Practice: Optimizing LLM Agent Prompts with Textual Gradients

Lina Faik

·

Oct 28

Continuously Optimizing AI Agent Prompts in Production

How TextGrad, GEPA, and ACE Turn Production Failures into Safer, Measurable Prompt Updates

Continuously Optimizing AI Agent Prompts in Production

Lina Faik

·

Oct 16

From Prompt Engineering to Harness Engineering: Where the Real Leverage Moved

Concepts & Practical Strategies for Engineering and Evaluating the Harness Around an LLM

From Prompt Engineering to Harness Engineering: Where the Real Leverage Moved

Lina Faik

·

Sep 30

GraphRAG in Production: From Indexing to Deployment

A Practical Comparison of LightRAG and Microsoft GraphRAG Across Indexing, Retrieval, Cost, and Latency

GraphRAG in Production: From Indexing to Deployment

Lina Faik

·

Sep 23

GraphRAG vs. Vector RAG: Better Retrieval or Expensive Overengineering?

Navigating the Graph RAG Landscape: How It Works, What It Costs, and Where It Shines

GraphRAG vs. Vector RAG: Better Retrieval or Expensive Overengineering?

Lina Faik

·

Sep 9

Inside TabFM: How In-Context Learning Enables Prediction on Unseen Tables

This article is also available as a podcast! If you’re on the go or just want to absorb the content in audio format, you can listen to the…

Inside TabFM: How In-Context Learning Enables Prediction on Unseen Tables

Lina Faik

·

Sep 2

LLM Cost Prediction: From Single Prompts to Agentic Systems

A Deep Dive Into Output-Length Forecasting, Agent Budgets, and Python Tooling

LLM Cost Prediction: From Single Prompts to Agentic Systems

Lina Faik

·

Jul 30

Evaluating Google ADK Agents: From Execution Traces to Regression Tests (Part 4)

A Practical Guide to Eval Sets, Eval Configs, Trajectory Metrics, and Rubric-Based Scoring

Evaluating Google ADK Agents: From Execution Traces to Regression Tests (Part 4)

Lina Faik

Lina Faik

Lead AI Scientist bringing AI research to real-world impact across industries. Independent consultant. Subscribe to: aipractitioner.substack.com

Help

Status

About

Careers

Press

Blog

Store

Privacy

Rules

Terms

Text to speech