Show Notes
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. Skills have become a core building block for AI agents, packaging expertise and workflows into reusable instructions. But despite their growing importance, most teams still create them through trial and error: write a skill, test it, revise it, and hope it performs better. In this episode, we explore SkillOpt, a framework that treats skills not as static prompts but as trainable artifacts. Instead of manually rewriting instructions, SkillOpt uses evaluation, feedback, and optimization loops to systematically improve a skill over time. You’ll learn: * How SkillOpt reframes prompt engineering as skill training: why skills can be treated as trainable external state and how optimization happens without changing model weights. * What the experiments reveal about skill optimization: where the largest gains appear, why skill transfer works across models, and the practical limits of optimizing instructions instead of model parameters. * How to apply SkillOpt yourself: reproducing the workflow on SearchQA, training skills on your own datasets, and evaluating whether optimization delivers measurable improvements over baseline prompting. By the end, you’ll understand when skill optimization is worth the additional compute, where it outperforms traditional prompt engineering, and why training instructions may become as important as training models in future agent systems. If you’d rather read than listen, the full article (with diagrams, code examples, and implementation details) is available on Substack: 👉 Enjoyed this episode? Subscribe to The AI Practitioner to get future articles and podcasts delivered straight to your inbox.
Get full access to The AI Practitioner at aipractitioner.substack.com/subscribe
More from The AI Practitioner Podcast
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
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
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
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
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