In this article, you will learn what prompt injection and tool misuse are in the context of agentic AI systems, and which defense strategies experts recommend to mitigate them.
Author Archive | Iván Palomares Carrascosa
Scikit-Ollama for Scikit-LLM/Ollama Integration
In this article, you will learn how scikit-ollama bridges the scikit-learn interface with locally running Ollama models to perform zero-shot text classification; no cloud API required.
Context Window Management for Long-Running Agents: Strategies and Tradeoffs
Managing context windows in the long run requires specific strategies. This article presents five of them, together with their inevitable tradeoffs.
Context Windows Are Not Memory: What AI Agent Developers Need to Understand
In this article, you will learn why a large context window is not the same thing as agent memory, and how techniques like retrieval, compression, and summarization fit together in an agent’s cognitive stack.
Clustering Unstructured Text with LLM Embeddings and HDBSCAN
In this article, you will learn how to build a text clustering pipeline by combining large language model embeddings with HDBSCAN, a density-based clustering algorithm, to automatically discover topics in unlabeled text data.
Building an End-to-End Sentiment Analysis Pipeline with Scikit-LLM
In this article, you will learn how to build an end-to-end sentiment analysis pipeline using Scikit-LLM and open-source large language models served through the Groq API.
Multi-Label Text Classification with Scikit-LLM
Learn how to load, adapt, and leverage a pre-trained LLM for a multi-label classification task where a piece of text can be assigned one or multiple categories.
Using Scikit-LLM with Open-Source LLMs
Learn how to leverage Python’s novel Scikit-LLM library to utilized cutting-edge LLMs similar to classical machine learning workflows: all for free.
Scikit-LLM vs. Traditional Text Classifiers: When Should You Use an LLM?
From classic techniques to state-of-the-art: implementing a benchmarking between three distinct approaches for text classification.
Building a Context Pruning Pipeline for Long-Running Agents
This article shows the basic principles to implement a context pruning pipeline for long-running agents, based on conversational continuity and semantic relevance.
