LLM engineering goes beyond bigger context windows. Learn how context management, reasoning, tools, and agentic systems make AI workflows more reliable.
Generative AI 🦾 |
In this section, we bring together every article on this site that deals with generative AI. Unlike the other sections, this isn’t a category of its own but a cross-cutting view: the articles below also live under The Fundamentals, Technologies & Tools, Real-World Practices or Trends & Insights.
They fall roughly along three lines:
- 🔬 Some look inside the model itself, at what transformers, pretraining and fine-tuning actually do.
- 🔧 Others deal with the engineering layer around it, which is where most of the real work happens: context, RAG, tool calling, agents, evaluation.
- 🏭 And the rest deal with what changes once these systems face real users, from serving and cost to governance and the AI Act.
The order isn’t accidental. Most projects fail somewhere in the second and third groups, long after the model has stopped being the interesting part.
