<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Open Source | Giulia Solinas</title><link>https://giuliasolinas.github.io/tags/open-source/</link><atom:link href="https://giuliasolinas.github.io/tags/open-source/index.xml" rel="self" type="application/rss+xml"/><description>Open Source</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Fri, 27 Mar 2026 00:00:00 +0000</lastBuildDate><image><url>https://giuliasolinas.github.io/media/icon_hu_982c5d63a71b2961.png</url><title>Open Source</title><link>https://giuliasolinas.github.io/tags/open-source/</link></image><item><title>Agentic AI</title><link>https://giuliasolinas.github.io/projects/agentic_ai/</link><pubDate>Fri, 27 Mar 2026 00:00:00 +0000</pubDate><guid>https://giuliasolinas.github.io/projects/agentic_ai/</guid><description>&lt;h1 id="agentic-ai"&gt;Agentic AI&lt;/h1&gt;
&lt;p&gt;&lt;strong&gt;Building Smarter Teams, One Agent at a Time&lt;/strong&gt;&lt;/p&gt;
&lt;p&gt;I specialize in designing and deploying autonomous agent ecosystems that turn complex workflows into seamless, self‑organizing teams. Using &lt;strong&gt;IBM watsonx Orchestrate&lt;/strong&gt;, I assembled a sandbox crew of business analysts who collaborate in real‑time to surface users stories, automate the identification of process requirements, and accelerate decision-making.&lt;/p&gt;
&lt;p&gt;&lt;em&gt;What makes me excited about this project: high degree of specialization, modularity, possibility to scale in tasks, smaller models for each specialized agents, ReAcT capabiliites, orchestration by design.&lt;/em&gt;&lt;/p&gt;
&lt;p&gt;At the same time, I explored the &lt;strong&gt;Google SDK for Agent Building&lt;/strong&gt; and crafted a sandbox project—a virtual podcast crew that researches, scripts, and narrates fintech news on‑the‑fly. The agents coordinate research, fact‑checking, and voice synthesis, delivering a polished, up‑to‑date podcast episode without human intervention.&lt;/p&gt;
&lt;p&gt;&lt;em&gt;What I learned from this project: each agent is supported by a different foundation model like LLM for text creation, multi-modal models for information parsing (including imaging and IDP capabilities), and text-to-speech, each packed in diffrent agents as modular components.&lt;/em&gt;&lt;/p&gt;
&lt;p&gt;Together, these experiences showcase my ability to:&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;&lt;strong&gt;Design modular agent architectures&lt;/strong&gt; that integrate with existing data and NLP pipelines.&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;Orchestrate multi‑agent collaboration&lt;/strong&gt; through clear role‑based interactions.&lt;/li&gt;
&lt;/ul&gt;
&lt;blockquote class="border-l-4 border-neutral-300 dark:border-neutral-600 pl-4 italic text-neutral-600 dark:text-neutral-400 my-6"&gt;
&lt;p&gt;[NOTE!]
My next chapter here in this area is AgentOps.&lt;/p&gt;
&lt;/blockquote&gt;
&lt;p&gt;Do you want to co-develop with me? Just reach out.&lt;/p&gt;
&lt;hr&gt;</description></item></channel></rss>