{"id":148,"date":"2026-03-24T15:34:27","date_gmt":"2026-03-24T15:34:27","guid":{"rendered":"https:\/\/thelab.wppresolve.com\/?post_type=research_pod&#038;p=148"},"modified":"2026-06-17T13:45:24","modified_gmt":"2026-06-17T13:45:24","slug":"self-improving-performance-agent-pod","status":"publish","type":"research_pod","link":"https:\/\/cms.research.wpp.com\/?research_pod=self-improving-performance-agent-pod","title":{"rendered":"Self-Improving Performance Agent Pod"},"content":{"rendered":"","protected":false},"author":18,"featured_media":826,"template":"","meta":{"_acf_changed":false,"_ppma_block_editor_authors":""},"pod_status":[{"id":4,"name":"Active","slug":"active"}],"ppma_author":[{"id":18,"display_name":"Andreas Stergioulas","first_name":"Andreas","last_name":"Stergioulas","nickname":"andreas.stergioulas","user_nicename":"andreas-stergioulas","user_email":"andreas.stergioulas@satalia.com","biographical_info":"Andreas Stergioulas is a Senior Data Scientist. He specializes in LLM-based agentic architectures, generative models, and computer vision for large-scale enterprise applications. Currently working at Satalia (WPP Group), he designs and deploys production-grade AI solutions \u2014 including custom multi-agent LLM systems and diffusion-based image generation pipelines \u2014 for globally recognized clients. He holds an M.Sc. in Electrical and Computer Engineering and is the author of peer-reviewed publications in venues such as CVPR Workshops and IEEE Transactions on Multimedia.","avatar_url":"https:\/\/cms.research.wpp.com\/wp-content\/uploads\/2026\/03\/E05G03JGGFJ-U06MMTF43HT-f2cf3ee352bb-512.jpeg","job_title":"Data Scientist","is_lead":null,"display_as_researcher":null,"order_priority":null},{"id":17,"display_name":"Ilias Papastratis","first_name":"Ilias","last_name":"Papastratis","nickname":"ilias.papastratis","user_nicename":"ilias-papastratis","user_email":"ilias.papastratis@satalia.com","biographical_info":"Ilias Papastratis is a Senior Data Scientist based in United Kingdom. He specializes in LLM-based agentic architectures, generative models, and computer vision for large-scale enterprise applications. Currently working at Satalia (WPP Group) , he designs and deploys production-grade AI solutions\u2014including custom multi-agent LLM systems and diffusion-based image generation pipelines \u2014for globally recognized clients.\r\n\r\nPreviously, he spent five years as a Deep Learning Researcher and developed computer vision models for real-time sign language translation and industrial object recognition. He holds a combined Bachelor\u2019s and Master\u2019s degree in Electrical Engineering and Computer Science from the University of Patras , alongside an MSc in Digital Media and Computational Intelligence from Aristotle University of Thessaloniki. In addition to being the author of peer-reviewed publications, he actively contributes to open-source deep learning projects.","avatar_url":"https:\/\/cms.research.wpp.com\/wp-content\/uploads\/2026\/04\/ilias-1.jpg","job_title":"Senior Data Scientist","is_lead":null,"display_as_researcher":null,"order_priority":null}],"class_list":["post-148","research_pod","type-research_pod","status-publish","has-post-thumbnail","hentry","pod_status-active"],"acf":{"subtitle":"An agentic approach to social media post performance prediction.","quarter":"Q1 2026","focus_focus":"","is_featured":false,"about_pod":"<p>Self-Improving Performance Agent is a research stream focused on this research area. It provides the context for the pod while the detailed technical walkthrough is maintained as a separate Research Output. As influencer marketing budgets scale into the billions, the industry has made significant strides in audience targeting, brand-safety screening, and performance analytics, yet?<\/p>\n"},"related_publications":[{"type":"research_feed","content_type":"article","title":"A self-improving AI agent for optimising and explaining media performance","slug":"a-self-improving-ai-agent-for-optimizing-and-explaining-media-performance","date":"2026-03-24T15:36:37+00:00","quarter":"","authors":[{"id":18,"display_name":"Andreas Stergioulas","first_name":"Andreas","last_name":"Stergioulas","nickname":"andreas.stergioulas","user_nicename":"andreas-stergioulas","user_email":"andreas.stergioulas@satalia.com","biographical_info":"Andreas Stergioulas is a Senior Data Scientist. He specializes in LLM-based agentic architectures, generative models, and computer vision for large-scale enterprise applications. Currently working at Satalia (WPP Group), he designs and deploys production-grade AI solutions \u2014 including custom multi-agent LLM systems and diffusion-based image generation pipelines \u2014 for globally recognized clients. He holds an M.Sc. in Electrical and Computer Engineering and is the author of peer-reviewed publications in venues such as CVPR Workshops and IEEE Transactions on Multimedia.","avatar_url":"https:\/\/cms.research.wpp.com\/wp-content\/uploads\/2026\/03\/E05G03JGGFJ-U06MMTF43HT-f2cf3ee352bb-512.jpeg","job_title":"Data Scientist","is_lead":null,"display_as_researcher":null,"order_priority":null},{"id":17,"display_name":"Ilias Papastratis","first_name":"Ilias","last_name":"Papastratis","nickname":"ilias.papastratis","user_nicename":"ilias-papastratis","user_email":"ilias.papastratis@satalia.com","biographical_info":"Ilias Papastratis is a Senior Data Scientist based in United Kingdom. He specializes in LLM-based agentic architectures, generative models, and computer vision for large-scale enterprise applications. Currently working at Satalia (WPP Group) , he designs and deploys production-grade AI solutions\u2014including custom multi-agent LLM systems and diffusion-based image generation pipelines \u2014for globally recognized clients.\r\n\r\nPreviously, he spent five years as a Deep Learning Researcher and developed computer vision models for real-time sign language translation and industrial object recognition. He holds a combined Bachelor\u2019s and Master\u2019s degree in Electrical Engineering and Computer Science from the University of Patras , alongside an MSc in Digital Media and Computational Intelligence from Aristotle University of Thessaloniki. In addition to being the author of peer-reviewed publications, he actively contributes to open-source deep learning projects.","avatar_url":"https:\/\/cms.research.wpp.com\/wp-content\/uploads\/2026\/04\/ilias-1.jpg","job_title":"Senior Data Scientist","is_lead":null,"display_as_researcher":null,"order_priority":null}]},{"type":"research_feed","content_type":"technical-walkthrough","title":"Self-Improving Performance Agent Pod: Technical walkthrough","slug":"self-improving-performance-agent-pod-technical-walkthrough","date":"2026-03-24T15:34:27+00:00","quarter":"Q1 2026","authors":[{"id":18,"display_name":"Andreas Stergioulas","first_name":"Andreas","last_name":"Stergioulas","nickname":"andreas.stergioulas","user_nicename":"andreas-stergioulas","user_email":"andreas.stergioulas@satalia.com","biographical_info":"Andreas Stergioulas is a Senior Data Scientist. He specializes in LLM-based agentic architectures, generative models, and computer vision for large-scale enterprise applications. Currently working at Satalia (WPP Group), he designs and deploys production-grade AI solutions \u2014 including custom multi-agent LLM systems and diffusion-based image generation pipelines \u2014 for globally recognized clients. He holds an M.Sc. in Electrical and Computer Engineering and is the author of peer-reviewed publications in venues such as CVPR Workshops and IEEE Transactions on Multimedia.","avatar_url":"https:\/\/cms.research.wpp.com\/wp-content\/uploads\/2026\/03\/E05G03JGGFJ-U06MMTF43HT-f2cf3ee352bb-512.jpeg","job_title":"Data Scientist","is_lead":null,"display_as_researcher":null,"order_priority":null}]}],"featured_image_url":"https:\/\/cms.research.wpp.com\/wp-content\/uploads\/2026\/03\/Gemini_Generated_Image_1wilyy1wilyy1wil-1024x1024.png","featured_image_sizes":{"thumbnail":"https:\/\/cms.research.wpp.com\/wp-content\/uploads\/2026\/03\/Gemini_Generated_Image_1wilyy1wilyy1wil-150x150.png","medium":"https:\/\/cms.research.wpp.com\/wp-content\/uploads\/2026\/03\/Gemini_Generated_Image_1wilyy1wilyy1wil-300x300.png","large":"https:\/\/cms.research.wpp.com\/wp-content\/uploads\/2026\/03\/Gemini_Generated_Image_1wilyy1wilyy1wil-1024x1024.png","full":"https:\/\/cms.research.wpp.com\/wp-content\/uploads\/2026\/03\/Gemini_Generated_Image_1wilyy1wilyy1wil.png"},"_links":{"self":[{"href":"https:\/\/cms.research.wpp.com\/index.php?rest_route=\/wp\/v2\/research_pods\/148","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cms.research.wpp.com\/index.php?rest_route=\/wp\/v2\/research_pods"}],"about":[{"href":"https:\/\/cms.research.wpp.com\/index.php?rest_route=\/wp\/v2\/types\/research_pod"}],"author":[{"embeddable":true,"href":"https:\/\/cms.research.wpp.com\/index.php?rest_route=\/wp\/v2\/users\/18"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cms.research.wpp.com\/index.php?rest_route=\/wp\/v2\/media\/826"}],"wp:attachment":[{"href":"https:\/\/cms.research.wpp.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=148"}],"wp:term":[{"taxonomy":"pod_status","embeddable":true,"href":"https:\/\/cms.research.wpp.com\/index.php?rest_route=%2Fwp%2Fv2%2Fpod_status&post=148"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/cms.research.wpp.com\/index.php?rest_route=%2Fwp%2Fv2%2Fppma_author&post=148"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}