{"id":1163431,"date":"2026-03-10T09:00:41","date_gmt":"2026-03-10T16:00:41","guid":{"rendered":""},"modified":"2026-03-11T13:47:58","modified_gmt":"2026-03-11T20:47:58","slug":"from-raw-interaction-to-reusable-knowledge-rethinking-memory-for-ai-agents","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/en-us\/research\/blog\/from-raw-interaction-to-reusable-knowledge-rethinking-memory-for-ai-agents\/","title":{"rendered":"PlugMem: Transforming raw agent interactions into reusable knowledge"},"content":{"rendered":"\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"2560\" height=\"1441\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-scaled.jpg\" alt=\"blue and purple gradient background with decorative white icons\" class=\"wp-image-1163443\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-scaled.jpg 2560w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-300x169.jpg 300w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-1024x576.jpg 1024w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-768x432.jpg 768w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-1536x865.jpg 1536w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-2048x1153.jpg 2048w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-1066x600.jpg 1066w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-655x368.jpg 655w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-240x135.jpg 240w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-640x360.jpg 640w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-960x540.jpg 960w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-1280x720.jpg 1280w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-1920x1080.jpg 1920w\" sizes=\"auto, (max-width: 2560px) 100vw, 2560px\" \/><\/figure>\n\n\n\n<div style=\"padding-bottom:0; padding-top:0\" class=\"wp-block-msr-immersive-section alignfull row wp-block-msr-immersive-section\">\n\t\n\t<div class=\"container\">\n\t\t<div class=\"wp-block-msr-immersive-section__inner wp-block-msr-immersive-section__inner--narrow\">\n\t\t\t<div class=\"wp-block-columns mb-10 pb-1 pr-1 is-layout-flex wp-container-core-columns-is-layout-9d6595d7 wp-block-columns-is-layout-flex\" style=\"box-shadow:var(--wp--preset--shadow--outlined)\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\">\n<h2 class=\"wp-block-heading h3\" id=\"at-a-glance\">At a glance<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Today\u2019s AI agents store long interaction histories but struggle to reuse them effectively.<\/li>\n\n\n\n<li>Raw memory retrieval can overwhelm agents with lengthy, low-value context.<\/li>\n\n\n\n<li>PlugMem transforms interaction history into structured, reusable knowledge.<\/li>\n\n\n\n<li>A single, general-purpose memory module improves performance across diverse agent benchmarks while using fewer memory tokens.<\/li>\n<\/ul>\n<\/div>\n<\/div>\t\t<\/div>\n\t<\/div>\n\n\t<\/div>\n\n\n\n<p>It seems counterintuitive: giving AI agents more memory can make them less effective. As interaction logs accumulate, they grow large, fill with irrelevant content, and become increasingly difficult to use.<\/p>\n\n\n\n<p>More memory\u00a0means that agents must search through larger volumes of past interactions to find information relevant to the current task. Without structure, these records mix useful experiences with irrelevant details, making retrieval slower and less reliable. The challenge is not storing more\u00a0experiences, but\u00a0organizing\u00a0them\u00a0so that\u00a0agents\u00a0can quickly\u00a0identify\u00a0what matters in the moment.<\/p>\n\n\n\n<p>In our recent paper \u201c<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/plugmem-a-task-agnostic-plugin-memory-module-for-llm-agents\/\" type=\"link\" id=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/plugmem-a-task-agnostic-plugin-memory-module-for-llm-agents\/\">PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents,<\/a>\u201d we introduce a plug-and-play memory system that transforms raw agent interactions into reusable knowledge. Rather than treating memory as text to retrieve, PlugMem organizes that history into structured knowledge designed to support decisions as the agent acts.<\/p>\n\n\n\n<p>Cognitive science offers a useful framework here. It distinguishes between remembering events, knowing facts, and knowing how to perform tasks. Past events provide context, but effective decisions rely on the facts and skills extracted from those events.<\/p>\n\n\n\n<p>This distinction motivated a shift in how we decided to design memory for AI agents. PlugMem implements this shift by converting the agent\u2019s interaction history, such as dialogues, documents, and web sessions, into structured, compact <em>knowledge units<\/em> that can be reused across tasks.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"how-plugmem-works\">How PlugMem works<\/h2>\n\n\n\n<p>A key difference between PlugMem and conventional AI memory systems is what gets stored. Traditional approaches store text chunks or named entities (references to people, places, and concepts). PlugMem uses facts and reusable skills as the fundamental building blocks of memory. This design reduces redundancy, increases information density, and improves retrieval precision. It&#8217;s built around three core components:<\/p>\n\n\n\n<p><strong>Structure.<\/strong> Raw interactions are standardized and transformed into propositional knowledge (facts) and prescriptive knowledge (reusable skills). These knowledge units are organized into a structured memory graph, enabling knowledge to be stored in a form designed for reuse.<\/p>\n\n\n\n<p><strong>Retrieval.<\/strong> Rather than retrieving long passages of text, PlugMem retrieves knowledge units that are aligned with the current task. High-level concepts and inferred intents serve as routing signals, surfacing the most relevant information for the decision at hand.<\/p>\n\n\n\n<p><strong>Reasoning.<\/strong> Retrieved knowledge is distilled into concise, task-ready guidance before being passed to the base agent, ensuring that only decision-relevant knowledge enters the agent\u2019s context window.<br><br>Figure 1 illustrates how these components work together.<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"2560\" height=\"686\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/Figure1-scaled.png\" alt=\"Figure 1. PlugMem organizes different types of agent interactions into a knowledge-centric memory graph, enabling structured retrieval and reasoning.\" class=\"wp-image-1163440\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/Figure1-scaled.png 2560w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/Figure1-300x80.png 300w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/Figure1-1024x275.png 1024w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/Figure1-768x206.png 768w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/Figure1-1536x412.png 1536w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/Figure1-2048x549.png 2048w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/Figure1-240x64.png 240w\" sizes=\"auto, (max-width: 2560px) 100vw, 2560px\" \/><figcaption class=\"wp-element-caption\">Figure 1. PlugMem organizes different types of agent interactions into a knowledge-centric memory graph, enabling structured retrieval and reasoning.<\/figcaption><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"one-memory-any-task\">One memory, any task<\/h2>\n\n\n\n<p>Most AI memory systems are built for one job. A conversational memory module is designed around dialogue. A knowledge-retrieval system is tuned to look up facts. A web agent\u2019s memory is optimized for navigating pages. Each performs well in its target setting but rarely transfers without significant redesign.<\/p>\n\n\n\n<p>PlugMem takes a different approach. It is a foundational memory layer that can be attached to any AI agent without needing to modify it for a specific task.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"evaluating-plugmem\">Evaluating PlugMem<\/h2>\n\n\n\n<p>To test PlugMem, we evaluated the same memory module on three benchmarks that each make different demands on memory:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Answering questions across long multi-turn conversations<\/li>\n\n\n\n<li>Finding facts that span multiple Wikipedia articles<\/li>\n\n\n\n<li>Making decisions while browsing the web<\/li>\n<\/ul>\n\n\n\n<p>Across all three, PlugMem consistently outperformed both generic retrieval methods and task-specific memory designs while allowing the AI agent to use significantly less memory token budget in the process.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"measuring-memory-by-utility-not-size\">Measuring memory by utility, not size<\/h3>\n\n\n\n<p>We wanted to evaluate whether the right information was reaching the agent at the right moment, without overwhelming the model\u2019s context window, which has limited capacity. To do this, we introduced a metric that measures how much useful, decision-relevant information a memory module contributes relative to how much context it consumes. <\/p>\n\n\n\n<p>When we plotted utility against context consumption, PlugMem consistently came out ahead: it delivered more decision-relevant information while consuming less of the AI agent\u2019s context than other approaches, as shown in Figure 2. These results suggest that transforming experience into knowledge\u2014rather than storing and retrieving raw logs\u2014produces memory that is more useful and efficient.<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1990\" height=\"572\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem_Fig2_AH.png\" alt=\"Figure 2. Across all three benchmarks, PlugMem delivered more useful memory with less of the agent\u2019s context window.\" class=\"wp-image-1163441\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem_Fig2_AH.png 1990w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem_Fig2_AH-300x86.png 300w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem_Fig2_AH-1024x294.png 1024w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem_Fig2_AH-768x221.png 768w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem_Fig2_AH-1536x442.png 1536w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem_Fig2_AH-240x69.png 240w\" sizes=\"auto, (max-width: 1990px) 100vw, 1990px\" \/><figcaption class=\"wp-element-caption\">Figure 2. Across all three benchmarks, PlugMem delivered more useful memory with less of the agent\u2019s context window.<\/figcaption><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"why-general-purpose-memory-can-outperform-task-specific-designs\">Why general-purpose memory can outperform task-specific designs<\/h2>\n\n\n\n<p>General-purpose memory modules can outperform systems tailored to specific tasks because the decisive factor is not specialization but whether memory can surface the right knowledge precisely when the agent needs it. Structure, retrieval, and reasoning each play a distinct role, and getting all three\u00a0right matters more than\u00a0optimizing\u00a0for\u00a0a single use\u00a0case.<\/p>\n\n\n\n<p>PlugMem is not meant to replace task-specific approaches. It provides a general memory foundation upon which task adaptations can be layered. Our experiments show that combining PlugMem with task-specific techniques yields further gains.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"toward-reusable-memory-for-agents\">Toward reusable memory for agents<\/h2>\n\n\n\n<p>As AI agents take on longer and more complex tasks, its memory needs to evolve from storing past interactions to actively supplying reusable knowledge. The goal is for agents to carry useful facts and strategies from one task to the next rather than starting from scratch each time.<\/p>\n\n\n\n<p>PlugMem represents a step in that direction, grounding memory design in cognitive principles and treating knowledge as the primary unit of reuse. As agent capabilities expand, knowledge-centric memory may prove to be a critical building block for the next generation of intelligent agents.<\/p>\n\n\n\n<p>Code and experimental results are publicly available on <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/github.com\/TIMAN-group\/PlugMem\" target=\"_blank\" rel=\"noopener noreferrer\">GitHub<span class=\"sr-only\"> (opens in new tab)<\/span><\/a> so that others can reproduce the results and conduct their own research.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>It seems counterintuitive: giving AI agents more memory can make them less effective. As interaction logs accumulate, they grow large, fill with irrelevant content, and become increasingly difficult to use. More memory\u00a0means that agents must search through larger volumes of past interactions to find information relevant to the current task. Without structure, these records mix [&hellip;]<\/p>\n","protected":false},"author":43518,"featured_media":1163443,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":null,"msr_hide_image_in_river":0,"footnotes":""},"categories":[1],"tags":[],"research-area":[13556],"msr-region":[],"msr-event-type":[],"msr-locale":[268875],"msr-post-option":[243984],"msr-impact-theme":[],"msr-promo-type":[],"msr-podcast-series":[],"class_list":["post-1163431","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-research-blog","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-post-option-blog-homepage-featured"],"msr_event_details":{"start":"","end":"","location":""},"podcast_url":"","podcast_episode":"","msr_research_lab":[],"msr_impact_theme":[],"related-publications":[],"related-downloads":[],"related-videos":[],"related-academic-programs":[],"related-groups":[],"related-projects":[],"related-events":[],"related-researchers":[{"type":"guest","value":"ke-yang","user_id":"1163471","display_name":"Ke Yang","author_link":"<a href=\"https:\/\/empathyang.github.io\/\" aria-label=\"Visit the profile page for Ke Yang\">Ke Yang<\/a>","is_active":true,"last_first":"Yang, Ke","people_section":0,"alias":"ke-yang"},{"type":"user_nicename","value":"Michel Galley","user_id":32887,"display_name":"Michel Galley","author_link":"<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/mgalley\/\" aria-label=\"Visit the profile page for Michel Galley\">Michel Galley<\/a>","is_active":false,"last_first":"Galley, Michel","people_section":0,"alias":"mgalley"},{"type":"user_nicename","value":"Chenglong Wang","user_id":41251,"display_name":"Chenglong Wang","author_link":"<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/chenwang\/\" aria-label=\"Visit the profile page for Chenglong Wang\">Chenglong Wang<\/a>","is_active":false,"last_first":"Wang, Chenglong","people_section":0,"alias":"chenwang"},{"type":"user_nicename","value":"Jianfeng Gao","user_id":32246,"display_name":"Jianfeng Gao","author_link":"<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/jfgao\/\" aria-label=\"Visit the profile page for Jianfeng Gao\">Jianfeng Gao<\/a>","is_active":false,"last_first":"Gao, Jianfeng","people_section":0,"alias":"jfgao"},{"type":"guest","value":"jiawei-han","user_id":"621489","display_name":"Jiawei Han","author_link":"<a href=\"http:\/\/hanj.cs.illinois.edu\/\" aria-label=\"Visit the profile page for Jiawei Han\">Jiawei Han<\/a>","is_active":true,"last_first":"Han, Jiawei","people_section":0,"alias":"jiawei-han"},{"type":"guest","value":"chengxiang-zhai","user_id":"1163472","display_name":"ChengXiang Zhai","author_link":"<a href=\"https:\/\/czhai.cs.illinois.edu\/\" aria-label=\"Visit the profile page for ChengXiang Zhai\">ChengXiang Zhai<\/a>","is_active":true,"last_first":"Zhai, ChengXiang","people_section":0,"alias":"chengxiang-zhai"}],"msr_type":"Post","featured_image_thumbnail":"<img width=\"960\" height=\"540\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-960x540.jpg\" class=\"img-object-cover\" alt=\"blue and purple gradient background with decorative white icons\" decoding=\"async\" loading=\"lazy\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-960x540.jpg 960w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-300x169.jpg 300w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-1024x576.jpg 1024w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-768x432.jpg 768w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-1536x865.jpg 1536w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-2048x1153.jpg 2048w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-1066x600.jpg 1066w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-655x368.jpg 655w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-240x135.jpg 240w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-640x360.jpg 640w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-1280x720.jpg 1280w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2026\/03\/PlugMem-BlogHeroFeature-1400x788-1-1920x1080.jpg 1920w\" sizes=\"auto, (max-width: 960px) 100vw, 960px\" \/>","byline":"","formattedDate":"March 10, 2026","formattedExcerpt":"It seems counterintuitive: giving AI agents more memory can make them less effective. As interaction logs accumulate, they grow large, fill with irrelevant content, and become increasingly difficult to use. More memory\u00a0means that agents must search through larger volumes of past interactions to find information&hellip;","locale":{"slug":"en_us","name":"English","native":"","english":"English"},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts\/1163431","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/users\/43518"}],"replies":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/comments?post=1163431"}],"version-history":[{"count":31,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts\/1163431\/revisions"}],"predecessor-version":[{"id":1163718,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts\/1163431\/revisions\/1163718"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/1163443"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1163431"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/categories?post=1163431"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/tags?post=1163431"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1163431"},{"taxonomy":"msr-region","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-region?post=1163431"},{"taxonomy":"msr-event-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event-type?post=1163431"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1163431"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1163431"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1163431"},{"taxonomy":"msr-promo-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-promo-type?post=1163431"},{"taxonomy":"msr-podcast-series","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-podcast-series?post=1163431"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}