The Glass Box: Why Your Chatbot Needs More Than Just Black-Box Testing
Chatbot applications, especially those built on Retrieval-Augmented Generation (RAG) pipelines, are not like traditional software. Their behavior is non-linear, emergent, and highly sensitive…
Production LLM: Chatbot Tracing and Automated Testing
In this article, we will build and improve an HR Assistant RAG-based application. The application itself is quite simple, but it would help us explore extremely important concepts when it…
Production LLM: Legal Chatbot with Knowledge Graphs and LangGraph
In the legal world, professionals are often overwhelmed by a sea of documents. From multi-hundred-page contracts to dense regulatory frameworks, the ability to find specific, accurate…
Production LLM: Insights from BI Dashboards with an AI Agent
Business Intelligence (BI) dashboards are invaluable tools, offering visual summaries of complex data, tracking key performance indicators (KPIs), and helping organizations make data-driven…
Production LLM: Improving Agent Quality Through Self-Reflection.
Artificial Intelligence (AI) agents are becoming increasingly capable, automating tasks, answering questions, and even generating content. However, like any complex system, they aren’t…
Production LLM: Automated Code Review and Documentation – Part 2.
In our previous article, we looked at a supervisor-based architecture where a manager agent coordinated specialized agents for code review and documentation. Today’s solution takes this…
Production LLM: automated code review and documentation – Part 1.
In this article, we’ll explore how AI Agents can automate some everyday tasks in software development. Large Language Models (LLMs) are not just good at writing code—they can also help take…
Production LLM: Agent with memory and tools
In one of the previous articles, we created a RAG agent that used tools to yield pretty interesting results (Production LLM: Agent with tools). It could solve multiple tasks quite well:…
Production ML: Data Engineering Pipeline – E-commerce Example. Part 2.
In the previous article (Production ML: Data Engineering Pipeline – E-commerce Example. Part 1.), we’ve designed a solution to help us migrate our company data from the old Customer Data…