The AI Practitioner Podcast

by Lina Faik
  • 0.0 (0)
  • Technology
  • Monthly

Real-world AI, explained simply — with code, use cases, and zero fluff. aipractitioner.substack.com

  1. 3d ago

    PODCAST — Inside GEPA: Evolving LLM Agent Prompts with Reflective Feedback

    Prefer reading instead? The full article is available here. The podcast is also available on Spotify and Apple Podcasts. Subscribe to keep up with the latest drops. What if AI agents could continuously improve their prompts as new challenges emerge in production? Even well-designed prompts can lose effectiveness as user needs evolve, new edge cases arise, and unexpected failures occur. Yet manually evaluating and refining prompts on an ongoing basis quickly becomes difficult to scale. In the previous episode, TextGrad introduced automated prompt optimization through textual gradients, using natural-language feedback to iteratively improve instructions. GEPA (Genetic-Pareto) takes a different approach: it combines reflection with evolutionary search to explore multiple prompt candidates and preserve promising alternatives through Pareto-based selection. In this episode, the focus is on how GEPA works, what a real banking intent classification experiment reveals about its effectiveness, and the trade-offs between accuracy, exploration, and prompt complexity. You’ll learn: * How does GEPA optimize prompts? The roles of reflection, mutation, and Pareto-based selection. * How can GEPA be implemented? Defining an agent, building feedback, and running evolutionary search. * How should the results be evaluated? What changes in the instructions, whether performance improves, and which trade-offs emerge. 👉 Enjoyed this episode? Subscribe to The AI Practitioner to get future articles and podcasts delivered straight to your inbox: aipractitioner.substack.com Get full access to The AI Practitioner at aipractitioner.substack.com/subscribe

    PODCAST — Inside GEPA: Evolving LLM Agent Prompts with Reflective Feedback

  2. Nov 3

    PODCAST — TextGrad in Practice: Optimizing LLM Agent Prompts with Textual Gradients

    Prefer reading instead? The full article is available here. The podcast is also available on Spotify and Apple Podcasts. Subscribe to keep up with the latest drops. What if AI agents could improve their own prompts instead of relying on manual updates? In production, data evolves, models change, and new failures emerge. Keeping prompts effective requires continuous evaluation and refinement, but manually managing this process quickly becomes difficult to scale. TextGrad offers a different approach: it uses natural-language feedback, called textual gradients, to identify errors and automatically update prompts without modifying the underlying model. In this episode, the focus is on how TextGrad works, what a real banking classification experiment reveals about its effectiveness, and the challenges of evaluating prompt improvements when no correct answer exists. You’ll learn: * How can AI agents optimize their own prompts? Exploring how TextGrad turns errors into textual gradients and uses them to automatically update instructions. * Does automated prompt optimization actually improve performance? Examining experimental results, why some updates introduce regressions, and the trade-offs between accuracy, cost, and prompt complexity. * What happens when there is no correct answer? Understanding how LLM judges can guide optimization for open-ended tasks, why their feedback can be misleading, and what reliable evaluation requires. 👉 Enjoyed this episode? Subscribe to The AI Practitioner to get future articles and podcasts delivered straight to your inbox: aipractitioner.substack.com Get full access to The AI Practitioner at aipractitioner.substack.com/subscribe

    PODCAST — TextGrad in Practice: Optimizing LLM Agent Prompts with Textual Gradients

  3. Oct 28

    PODCAST — Continuously Optimizing AI Agent Prompts in Production

    Prefer reading instead? The full article is available here. The podcast is also available on Spotify and Apple Podcasts. Subscribe to keep up with the latest drops. What if the key to better AI agents isn’t writing better prompts, but making prompts continuously improve? Even carefully designed prompts can fall short in production. Continuous prompt optimization uses real-world execution data, failures, and feedback to refine agent behavior over time, without changing the underlying model. In this episode, the focus is on how continuous prompt optimization works, why static prompts are no longer enough, and how automated feedback loops can improve agent reliability in production. You’ll learn: * Why optimizing text requires a different kind of gradient: How natural-language feedback can play a role similar to numerical gradients in neural network training. * How TextGrad and GEPA optimize prompts offline: How they turn failures into systematic prompt improvements, and the trade-offs between their approaches. * How ACE enables continuous improvement in production: Why repeatedly rewriting prompts can gradually erase useful knowledge, and how incremental updates help preserve it. 👉 Enjoyed this episode? Subscribe to The AI Practitioner to get future articles and podcasts delivered straight to your inbox: aipractitioner.substack.com Get full access to The AI Practitioner at aipractitioner.substack.com/subscribe

    PODCAST — Continuously Optimizing AI Agent Prompts in Production

  4. Oct 16

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

    Prefer reading instead? The full article is available here. The podcast is also available on Spotify and Apple Podcasts. Subscribe to keep up with the latest drops. What if improving an AI agent’s performance had less to do with choosing a better model and more to do with the system built around it? In one experiment, LangChain improved its coding agent’s benchmark score from 52.8% to 66.5% without changing the underlying model. The difference came from harness engineering: the tools, context management, execution logic, and feedback mechanisms that turn an LLM into a reliable agent. In this episode, the focus is on why harness engineering is gaining attention, how it works, and why it changes the way agent performance should be evaluated. You’ll learn: * Why are better prompts no longer enough? Understanding the challenges of long-running agents, from context degradation and lost progress to unreliable tool use and verification. * What actually makes an agent harness? Exploring the components behind autonomous agents, the approaches used by OpenAI and Anthropic, and the emerging engineering patterns. * Can the same model deliver radically different results? Examining real benchmark experiments, the impact of harness design, and why leaderboard scores may reveal less about model capabilities than they appear to. 👉 Enjoyed this episode? Subscribe to The AI Practitioner to get future articles and podcasts delivered straight to your inbox: aipractitioner.substack.com Get full access to The AI Practitioner at aipractitioner.substack.com/subscribe

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

  5. Sep 23

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

    Prefer reading instead? The full article is available here. The podcast is also available on Spotify and Apple Podcasts. Subscribe to keep up with the latest drops. Standard RAG works well when the answer is contained in one place. But when a question requires connecting facts across several documents, vector retrieval can start to struggle. GraphRAG adds explicit structure around entities and their relationships, making multi-hop retrieval easier, but also more complex and expensive. In this episode, the focus is on how GraphRAG works, how the main approaches differ, and whether the added complexity is actually worth it. You’ll learn: * Why does vector retrieval struggle with multi-hop questions? Exploring why semantic similarity alone is often not enough when an answer requires connecting several entities and facts across documents. * How do the main GraphRAG architectures differ? Breaking down community-based approaches like Microsoft GraphRAG, entity-relation systems like LightRAG, PageRank-based retrieval such as HippoRAG, and recursive summarization with RAPTOR. * Is GraphRAG actually worth the additional cost? Looking at benchmark results, retrieval quality, token usage, latency, and practical implementations of NaiveRAG, LightRAG, and Microsoft GraphRAG. 👉 Enjoyed this episode? Subscribe to The AI Practitioner to get future articles and podcasts delivered straight to your inbox: aipractitioner.substack.com Get full access to The AI Practitioner at aipractitioner.substack.com/subscribe

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

  6. Sep 9

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

    Prefer reading instead? The full article is available here. The podcast is also available on Spotify and Apple Podcasts. Subscribe to keep up with the latest drops. Most tabular machine learning workflows start the same way: clean the data, engineer features, tune hyperparameters, and train a new model from scratch. Google Research’s TabFM proposes a very different approach: treat the dataset itself as context and make predictions in a single forward pass, without task-specific training. In this episode, the focus is on how zero-shot foundation models for tabular data actually work, why tables require a different architecture from text, and how TabFM compares with the models that came before it. You’ll learn: * Why is in-context learning harder for tabular data? Exploring how permutation invariance across rows and columns makes standard sequence modeling a poor fit for tables. * How do TabPFN, TabICL, and TabFM solve the problem differently? Breaking down three architectural approaches to the same challenge and the key ideas that distinguish them. * How do you run these models in practice? Using TabFM, TabPFN, and TabICL on real tabular datasets and looking at the kind of predictive performance you can expect from them. 👉 Enjoyed this episode? Subscribe to The AI Practitioner to get future articles and podcasts delivered straight to your inbox: aipractitioner.substack.com Get full access to The AI Practitioner at aipractitioner.substack.com/subscribe

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

  7. Sep 2

    PODCAST — LLM Cost Prediction: From Single Prompts to Agentic Systems

    Prefer reading instead? The full article is available here. The podcast is also available on Spotify and Apple Podcasts. Subscribe to keep up with the latest drops. LLM costs are easy to calculate after execution, but estimating them before a prompt or agent actually runs is a much harder problem. In this episode, the focus is on predicting LLM and agent costs before execution, from estimating output length for a single model call to reasoning about the much more variable execution paths of AI agents. You’ll learn: * What can be predicted from a prompt before execution? Exploring how token consumption, output length, and model cost can be estimated before sending a request to an LLM. * Can an agent’s cost be estimated before execution? Understanding the additional uncertainty introduced by multiple model calls, tool calls, retries, reasoning steps, and variable execution trajectories. * What Python tooling is available today? Reviewing practical libraries and approaches for estimating and calculating LLM and agent costs, including LiteLLM, genai-prices, tokencost, and tiktoken. 👉 Enjoyed this episode? Subscribe to The AI Practitioner to get future articles and podcasts delivered straight to your inbox: aipractitioner.substack.com Get full access to The AI Practitioner at aipractitioner.substack.com/subscribe

    PODCAST — LLM Cost Prediction: From Single Prompts to Agentic Systems

  8. Jul 30

    PODCAST — Evaluating Google ADK Agents: From Execution Traces to Regression Tests

    Prefer reading instead? The full article is available here. The podcast is also available on Spotify and Apple Podcasts. Subscribe to keep up with the latest drops. Building agents that take real-world actions is impressive, but ensuring they continue to behave correctly as they evolve is a much harder challenge. Manual reviews of execution traces and subjective “vibe checks” quickly become a development bottleneck. In this fourth episode of the Google ADK series, the focus moves from deployment to evaluation and quality assurance. You’ll learn: * What should be evaluated in an agent system? Distinguishing final-response quality from tool use, execution trajectories, state handling, and end-to-end task success. * How Google ADK represents evaluations. Understanding eval sets, evaluation cases, invocations, evaluation configs, and the metrics that operate on them. * How to create, run, and inspect ADK evaluations. Recording evaluation cases, configuring metrics, executing evals from the CLI or Python, and interpreting the resulting scores and reports. 👉 Enjoyed this episode? Subscribe to The AI Practitioner to get future articles and podcasts delivered straight to your inbox: aipractitioner.substack.com Get full access to The AI Practitioner at aipractitioner.substack.com/subscribe

    PODCAST — Evaluating Google ADK Agents: From Execution Traces to Regression Tests
See All (24)

About

Real-world AI, explained simply — with code, use cases, and zero fluff. aipractitioner.substack.com

Information

You Might Also Like