According to the traditional economic theory, markets are fully efficient and humans operate in them in a rational way. In the late 70s Daniel Kahneman and Amos Tversky started disproving this efficient markets hypothesis, contrasting the consistently logical Homo Economicus (Econ) they depicted, with the more realistic Human who takes decisions based on his questionable points of view. Doing so they gave birth to the study of the psychological factors involved in the making of these decisions, called Behavioral Economics.

The same flawed reasoning also impacts other fields like software engineering: we cannot behave as cold Econ when spending or investing our money, or as rational Engeen when coding. We are humans and this inevitably influences our choices.

The anchoring effect and the availability bias affect how we benchmark and evaluate the performances of our programs. The pro-innovation and bandwagon biases drive our technical decisions, making us to blindly follow hypes and gurus. The not-invented-here syndrome pushes us to create homemade tools instead of using de-facto standards. The framing effect makes us solving the same problem in different ways, depending on how it is presented.

During this talk we will go through these and other heuristics and shortcuts used by our brain, as found by behavioral economists in almost 50 years of research, and examine them in the context of software engineering, discussing their consequences on the quality of our work.

Developing AI applications today goes beyond simple single-model interactions. We're seeing a shift towards agentic AI systems, where multiple specialized agents work together, each capable of independent reasoning. The real challenge for an AI architect lies in orchestrating these agents to collaborate effectively towards a common goal.

Given the diverse and complex tasks these systems handle, a "one-size-fits-all" approach to coordination just doesn't work. We'll explore the spectrum of agentic patterns, from reliable but rigid workflows to highly flexible, autonomous agent orchestration using LLMs, and everything in between.

Beyond just sequencing agents, effective communication is vital. Agents need a shared space to exchange results and enrich each other's contexts.

This talk will cover:

• The pros and cons of various agentic patterns.
• Practical demonstrations of how to combine these patterns using LangChain4j and its Quarkus extension.
• How to leverage the provided infrastructure for agent collaboration.
• The flexibility to implement and seamlessly integrate your own custom agentic patterns.