@@ -86,17 +86,24 @@
             <li>
               <a href="#Pubs">Publications and Blogs</a>
             </li>
-              <a href="#Open Source Projects">Open Source Projects</a>
+              <a href="#Open Source Projects">Open Source Projects</a> <a href="https://github.com/adrida" target="_blank" style="display:inline-block;position:relative;top:3px;margin-left:4px;border-bottom:none !important;"><img src="https://img.shields.io/github/stars/adrida?style=social" alt="Stars" style="height:20px;"></a>
             </li>
 
           </ul>
           </a>
-          <div class="fh5co-nav-call-to-action js-fh5co-nav-call-to-action">
-            <a href="https://scholar.google.com/citations?user=Ia8Rku4AAAAJ&hl" ><img width="30" src="images/googlescholar.png" > </a>
-            <a href="https://adam-rida.medium.com/" ><img width="30" src="images/medium.png" > </a>
-            <a href="https://github.com/adrida" ><img width="30" src="images/github.png" > </a>
-            <a href="https://huggingface.co/Adr740" ><img width="30" src="images/hf.png" > </a>
-            
+          <style>
+            .social-icons { display: flex; align-items: center; gap: 16px; }
+            .social-icons a { display: inline-flex; align-items: center; text-decoration: none; }
+            .social-icons a svg { width: 20px; height: 20px; display: block; opacity: 0.7; transition: opacity 0.2s; }
+            .social-icons a:hover svg { opacity: 1; }
+          </style>
+          <div class="fh5co-nav-call-to-action js-fh5co-nav-call-to-action social-icons">
+            <a href="https://x.com/_adamr_1" target="_blank" title="X"><svg viewBox="0 0 24 24" fill="#000000"><path d="M18.901 1.153h3.68l-8.04 9.19L24 22.846h-7.406l-5.8-7.584-6.638 7.584H.474l8.6-9.83L0 1.154h7.594l5.243 6.932ZM17.61 20.644h2.039L6.486 3.24H4.298Z"/></svg></a>
+            <a href="https://github.com/adrida" target="_blank" title="GitHub"><svg viewBox="0 0 24 24" fill="#181717"><path d="M12 .297c-6.63 0-12 5.373-12 12 0 5.303 3.438 9.8 8.205 11.385.6.113.82-.258.82-.577 0-.285-.01-1.04-.015-2.04-3.338.724-4.042-1.61-4.042-1.61C4.422 18.07 3.633 17.7 3.633 17.7c-1.087-.744.084-.729.084-.729 1.205.084 1.838 1.236 1.838 1.236 1.07 1.835 2.809 1.305 3.495.998.108-.776.417-1.305.76-1.605-2.665-.3-5.466-1.332-5.466-5.93 0-1.31.465-2.38 1.235-3.22-.135-.303-.54-1.523.105-3.176 0 0 1.005-.322 3.3 1.23.96-.267 1.98-.399 3-.405 1.02.006 2.04.138 3 .405 2.28-1.552 3.285-1.23 3.285-1.23.645 1.653.24 2.873.12 3.176.765.84 1.23 1.91 1.23 3.22 0 4.61-2.805 5.625-5.475 5.92.42.36.81 1.096.81 2.22 0 1.606-.015 2.896-.015 3.286 0 .315.21.69.825.57C20.565 22.092 24 17.592 24 12.297c0-6.627-5.373-12-12-12"/></svg></a>
+            <a href="https://scholar.google.com/citations?user=Ia8Rku4AAAAJ&hl" target="_blank" title="Google Scholar"><svg viewBox="0 0 24 24" fill="#4285F4"><path d="M5.242 13.769 0 9.5 12 0l12 9.5-5.242 4.269C17.548 11.249 14.978 9.5 12 9.5c-2.977 0-5.548 1.748-6.758 4.269ZM12 10a7 7 0 1 0 0 14 7 7 0 0 0 0-14Z"/></svg></a>
+            <a href="https://adam-rida.medium.com/" target="_blank" title="Medium"><svg viewBox="0 0 24 24" fill="#000000"><path d="M13.54 12a6.8 6.8 0 0 1-6.77 6.82A6.8 6.8 0 0 1 0 12a6.8 6.8 0 0 1 6.77-6.82A6.8 6.8 0 0 1 13.54 12ZM20.96 12c0 3.54-1.51 6.42-3.38 6.42-1.87 0-3.39-2.88-3.39-6.42s1.52-6.42 3.39-6.42 3.38 2.88 3.38 6.42ZM24 12c0 3.17-.53 5.75-1.19 5.75-.66 0-1.19-2.58-1.19-5.75s.53-5.75 1.19-5.75C23.47 6.25 24 8.83 24 12Z"/></svg></a>
+            <a href="https://huggingface.co/Adr740" target="_blank" title="Hugging Face" style="font-size:19px;line-height:1;">&#x1F917;</a>
+            <a href="https://www.linkedin.com/in/adam-rida-581296142/" target="_blank" title="LinkedIn"><svg viewBox="0 0 24 24" fill="#0A66C2"><path d="M20.447 20.452h-3.554v-5.569c0-1.328-.027-3.037-1.852-3.037-1.853 0-2.136 1.445-2.136 2.939v5.667H9.351V9h3.414v1.561h.046c.477-.9 1.637-1.85 3.37-1.85 3.601 0 4.267 2.37 4.267 5.455v6.286ZM5.337 7.433a2.062 2.062 0 0 1-2.063-2.065 2.064 2.064 0 1 1 2.063 2.065Zm1.782 13.019H3.555V9h3.564v11.452ZM22.225 0H1.771C.792 0 0 .774 0 1.729v20.542C0 23.227.792 24 1.771 24h20.451C23.2 24 24 23.227 24 22.271V1.729C24 .774 23.2 0 22.222 0h.003Z"/></svg></a>
           </div>
             </a>
         </nav>
@@ -114,34 +121,34 @@
         <div class="row">
             <img width="200" src="images/profile.jpeg"  style="margin:0px 0px 0px 200px;" >
             <h3>Adam Rida</h3>
-            <p>AI researcher and Data Scientist </p>
-<p>ex PhD Candidate in ML at Sorbonne University and AXA | Master's degree in Applied Mathematics from CY Tech </p>
+            <p>AI Researcher and Founder</p>
+<p>Founder at <a href="https://deeprecall.io">DeepRecall</a> | ex PhD Candidate in ML at Sorbonne University and AXA | Master's in Applied Mathematics from CY Tech</p>
             adamrida.ra@gmail.com<br>
             [<a href="https://github.com/adrida/adrida.github.io/blob/master/CV_ADAM_RIDA.pdf?raw=true">download CV</a>] [<a href="https://www.linkedin.com/in/adam-rida-581296142/">connect on linkedin</a>] 
             <p></p>
         </div>
         <div class='p12'>
-            <p>My name is Adam, and I am a data scientist and AI researcher based in Paris, France, with a strong passion for leveraging artificial intelligence to solve complex, real-world problems.</p>
+            <p>I am an AI researcher and founder based between Paris and San Francisco, building systems that make AI more efficient, interpretable, and deployable at scale.</p>
 
-            <p>I've worked across various companies including Société Générale, AXA, Qantev, Rebellion Research, and now Autoplay AI. My expertise spans applied machine learning, explainable AI, unsupervised learning, and complex systems modeling.</p>
+            <p>I currently lead <a href="https://deeprecall.io">DeepRecall</a>, an AI-powered regulatory intelligence platform for marketplace enforcement, monitoring 120,000+ safety alerts across 8+ jurisdictions. I also created <a href="https://tracer.deeprecall.io">TRACER</a>, an open-source system that replaces expensive LLM classification calls with lightweight ML surrogates (<a href="https://github.com/adrida/tracer">pip install tracer-llm</a>).</p>
 
-            <p>I previously spent a year as a PhD candidate at Sorbonne University within the <a href="https://trail.lip6.fr/">Trustworthy and Responsible AI Lab (TRAIL)</a>, a collaboration between Sorbonne and AXA. There, I worked on novel methods for explainable AI (XAI) and interpretability, specifically focusing on understanding model dynamics and concept drift. My research led to a publication at the DynXAI workshop of ECML-PKDD 2023.</p>
+            <p>Before founding DeepRecall, I was a PhD candidate at Sorbonne University within the <a href="https://trail.lip6.fr/">Trustworthy and Responsible AI Lab (TRAIL)</a>, a joint lab between Sorbonne and AXA focused on trustworthy AI. My research on explainable AI and model dynamics produced the <a href="https://github.com/adrida/deltaxplainer">DeltaXplainer</a> method for interpreting model differences over time, published at the DynXAI workshop of ECML-PKDD 2023.</p>
 
-            <p>Driven by the desire to build impactful solutions, I joined <a href="https://joinef.com">Entrepreneur First</a> to co-found a startup aimed at helping private equity deal teams screen deals faster. Through advanced RAG techniques (GraphRAG, Graph Neural Networks), I developed a proprietary document parsing tool capable of extracting actionable insights from over 3,500+ pages of documents. Within two months, I built three live prototypes showcased to 100+ private equity funds.</p>
+            <p>I went through <a href="https://joinef.com">Entrepreneur First</a> (LD22), where I co-founded a venture helping private equity deal teams screen investments faster using advanced RAG techniques (GraphRAG, Graph Neural Networks). I built three live prototypes showcased to 100+ PE funds within two months.</p>
 
-            <p>Currently, I am the Head of AI at Autoplay AI, where I designed and built a comprehensive AI inference and processing pipeline from scratch to understand user behavior. This involved analyzing events, mouse activity, and various interactions to infer hesitation, intention, knowledge gaps, and more. I also developed sophisticated evaluations and unsupervised learning models to detect user cohorts struggling with product adoption and created augmented search capabilities across sessions to uncover hidden insights.</p>
+            <p>As Head of AI at Autoplay AI, I designed and built the company's AI inference and processing pipeline from scratch, analyzing user behavior signals (events, mouse activity, hesitation patterns) to detect cohorts struggling with product adoption.</p>
 
-            <p>I hold an Engineering Degree (Master's) from CY Tech in France, and previously completed the rigorous <a href="https://42.fr/en/homepage/">Ecole 42</a> coding program, where I refined my programming skills through intensive, project-based learning.</p>
+            <p>Earlier, I held ML engineering and data science roles at Societe Generale, AXA, Qantev, and Rebellion Research, working on anomaly detection, portfolio optimization, claims automation, and complex systems modeling.</p>
 
-            <p>Beyond AI and data science, I'm passionate about aviation and am actively working towards obtaining my Private Pilot License (PPL) in France.</p>
+            <p>I hold a Master's in Applied Mathematics from CY Tech and completed the <a href="https://42.fr/en/homepage/">Ecole 42</a> coding program. Outside of work, I am passionate about aviation and working towards my Private Pilot License (PPL).</p>
 
             <p>Areas of Interest:</p>
             <ul style="list-style-type: none; padding-left: 20px;">
-                <li>- Explainable AI (XAI), Concept Drift, and AI-Human Interaction</li>
-                <li>- Outlier Detection & Unsupervised Learning</li>
-                <li>- Deep Learning & Latent Representations</li>
-                <li>- LLMs & Their Application to Advanced NLP Tasks (RAG, Document Parsing, Knowledge Representation)</li>
-                <li>- Transdisciplinary Approaches to High-Impact Problems</li>
+                <li>- LLM Cost Optimization, Routing, and Learning to Defer</li>
+                <li>- Explainable AI (XAI), Concept Drift, and Model Dynamics</li>
+                <li>- Regulatory AI, Compliance Automation</li>
+                <li>- Outlier Detection and Unsupervised Learning</li>
+                <li>- RAG, Document Parsing, Knowledge Representation</li>
             </ul>
         </div>
       </div>
@@ -231,6 +238,22 @@ <h3>Adam Rida</h3>
         <div class="container">
           <a NAME="Open Source Projects"><h4>Open Source Projects</h4></a>
 
+          <!-- Start TRACER project-->
+          <div class="fh5co-spacer fh5co-spacer-xs"></div>
+          <img src="images/tracer_sankey.png" alt="TRACER Sankey Routing Diagram" class="fh5co-align-left img-responsive">
+          <div class='paper-title'>
+            TRACER: Trace-Based Adaptive Cost-Efficient Routing
+            <a href="https://github.com/adrida/tracer" target="_blank" style="margin-left:8px;vertical-align:middle;"><img src="https://img.shields.io/github/stars/adrida/tracer?style=social" alt="Stars" style="height:18px;vertical-align:middle;"></a>
+          </div>
+          <div class='tldr'>
+          </div>
+          <div class='paper-contents'>
+            TL;DR: TRACER is an open-source Python package that replaces expensive LLM classification calls with lightweight ML surrogates. It learns from the LLM's own production traces (zero manual labeling), gates deployment with a parity check, and generates interpretability artifacts that explain the routing boundary. Achieves 90%+ traffic offload on intent classification benchmarks.
+            <br>
+            [<a href="https://tracer.deeprecall.io">website</a>] [<a href="https://github.com/adrida/tracer">github</a>] [<a href="https://pypi.org/project/tracer-llm/">python package</a>] [<a href="https://docs.tracer.deeprecall.io">docs</a>]
+          </div>
+          <!-- End TRACER project-->
+
           <!-- Start One project-->
           <div class="fh5co-spacer fh5co-spacer-xs"></div>
           <img src="images/Schema Temporal Augmented Retrieval.png" alt="Images" class="fh5co-align-left img-responsive">