[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-databricks-ai-gateway-inference-tables-served-models-en":3,"article-related-databricks-ai-gateway-inference-tables-served-models-en":30,"series-tools-610d3dfe-c451-42a0-a51a-adbee93932f5":73},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":11,"image_url":12,"cover_image":12,"category":13,"language":14,"translated_content":11,"related_article_id":15,"keywords":16,"key_takeaways":22,"views":26,"created_at":27,"published_at":28,"topic_cluster_id":29},"610d3dfe-c451-42a0-a51a-adbee93932f5","databricks-ai-gateway-inference-tables-served-models-en","Databricks adds AI Gateway inference tables for served models","\u003Cp data-speakable=\"summary\">Databricks AI Gateway \u003Ca href=\"\u002Ftag\u002Finference\">inference\u003C\u002Fa> tables log model-serving requests and responses to Unity Catalog Delta tables.\u003C\u002Fp>\u003Cp>Databricks updated its AWS docs on Jun. 30, 2026 to describe AI Gateway-enabled inference tables for served models. The feature automatically captures request and response data from Model Serving endpoints and stores it in Unity Catalog for monitoring, evaluation, debugging, and tuning.\u003C\u002Fp>\u003Ctable>\u003Cthead>\u003Ctr>\u003Cth>項目\u003C\u002Fth>\u003Cth>數值\u003C\u002Fth>\u003C\u002Ftr>\u003C\u002Fthead>\u003Ctbody>\u003Ctr>\u003Ctd>Doc update\u003C\u002Ftd>\u003Ctd>Jun. 30, 2026\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Supported endpoint types\u003C\u002Ftd>\u003Ctd>5\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>AI agent tables created per deployment\u003C\u002Ftd>\u003Ctd>3\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Payload data availability\u003C\u002Ftd>\u003Ctd>Within 1 hour\u003C\u002Ftd>\u003C\u002Ftr>\u003C\u002Ftbody>\u003C\u002Ftable>\u003Ch2>What changed\u003C\u002Fh2>\u003Cp>Inference tables are now described as a built-in logging layer for Databricks Model Serving endpoints. When enabled, they write incoming requests, outgoing responses, HTTP status codes, run time, request IDs, and traces into a Delta table in Unity Catalog.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782939767961-3jwr.png\" alt=\"Databricks adds AI Gateway inference tables for served models\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>The docs also extend the feature to deployed \u003Ca href=\"\u002Ftag\u002Fai-agents\">AI agents\u003C\u002Fa>. For agents, Databricks stores payload and request details plus MLflow Trace logs, and agents deployed with the \u003Ca href=\"https:\u002F\u002Fmlflow.org\u002Fdocs\u002Flatest\u002Fpython_api\u002Fmlflow.deploy.html\" target=\"_blank\" rel=\"noopener\">mlflow.deploy()\u003C\u002Fa> \u003Ca href=\"\u002Ftag\u002Fapi\">API\u003C\u002Fa> get inference tables automatically.\u003C\u002Fp>\u003Cul>\u003Cli>Supported endpoint types include provisioned throughput, pay-per-token, external models, deployed AI agents, and custom models.\u003C\u002Fli>\u003Cli>Workspace requirements include Unity Catalog, serverless compute, and a region with model serving support.\u003C\u002Fli>\u003Cli>Databricks says both the endpoint creator and modifier need Can Manage on the endpoint plus USE CATALOG, USE SCHEMA, and CREATE TABLE in Unity Catalog.\u003C\u002Fli>\u003Cli>Databricks creates a new inference table automatically; existing tables are not supported.\u003C\u002Fli>\u003C\u002Ful>\u003Cp>The docs warn that changing the table schema, renaming the table, or deleting it can stop logging or corrupt the table. For AI agents, Databricks is also deprecating request logs and assessment logs in favor of the newer payload tables.\u003C\u002Fp>\u003Ch2>Why it matters\u003C\u002Fh2>\u003Cp>For developers, the change turns serving telemetry into queryable data instead of opaque logs. Teams can join inference tables with ground truth labels, build training corpora, monitor drift, and use Databricks SQL or notebooks to inspect failures without leaving the platform.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782939765821-evtl.png\" alt=\"Databricks adds AI Gateway inference tables for served models\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>It also gives ops teams a clearer path for \u003Ca href=\"\u002Ftag\u002Fagent\">agent\u003C\u002Fa> debugging. Because the tables can include MLflow traces and request metadata, teams can track slow runs, compare historical requests, and spot where response quality or latency changed.\u003C\u002Fp>\u003Cp>Databricks also points to the new \u003Ca href=\"https:\u002F\u002Fdocs.databricks.com\u002Faws\u002Fen\u002Fai-gateway\u002F\" target=\"_blank\" rel=\"noopener\">Unity AI Gateway\u003C\u002Fa> beta, which it describes as the enterprise control plane for governing \u003Ca href=\"\u002Ftag\u002Fllm\">LLM\u003C\u002Fa> endpoints and coding agents. That suggests inference tables are part of a broader push to make serving, governance, and observability sit in one workflow.\u003C\u002Fp>\u003Cp>The practical question for teams is no longer whether they can log model traffic, but whether they want that traffic governed in Unity Catalog from day one.\u003C\u002Fp>","Databricks now logs model-serving requests and responses to Unity Catalog Delta tables for monitoring, debugging, and agent tracing.","docs.databricks.com","https:\u002F\u002Fdocs.databricks.com\u002Faws\u002Fen\u002Fai-gateway\u002Finference-tables",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782939767961-3jwr.png","tools","en","2ffaf5e5-e155-47dd-80cd-af62c3705516",[17,18,19,20,21],"Databricks","Unity AI Gateway","inference tables","Model Serving","MLflow tracing",[23,24,25],"Databricks now logs serving requests and responses into Unity Catalog Delta tables.","AI agents get payload tables and MLflow traces, with mlflow.deploy() enabling them automatically.","The feature supports monitoring, drift checks, debugging, and training-data creation.",0,"2026-07-01T21:02:21.075884+00:00","2026-07-01T21:02:21.069+00:00","0c42cb32-a243-4a33-92ed-0549a19cbd89",{"tags":31,"relatedLang":32,"relatedPosts":36},[],{"id":15,"slug":33,"title":34,"language":35},"databricks-ai-gateway-inference-tables-served-models-zh","Databricks 為模型服務加上 AI Gateway 推論表","zh",[37,43,49,55,61,67],{"id":38,"slug":39,"title":40,"cover_image":41,"image_url":41,"created_at":42,"category":13},"cb384f83-17c8-4bad-966a-6b1b9801619a","basic09-llvm-compiler-foss-dev-en","BASIC09 gets a new LLVM-based compiler","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782932571339-sbko.png","2026-07-01T19:02:29.128472+00:00",{"id":44,"slug":45,"title":46,"cover_image":47,"image_url":47,"created_at":48,"category":13},"c4ae7d55-663c-4ad6-846d-da941d934571","9-cursor-alternatives-that-beat-lock-in-en","9 Cursor alternatives that beat lock-in","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782914599832-agyf.png","2026-07-01T14:02:57.008648+00:00",{"id":50,"slug":51,"title":52,"cover_image":53,"image_url":53,"created_at":54,"category":13},"3c1791f8-1d25-4e81-b0ac-caa096636b77","ai-video-tools-full-pipeline-wins-en","AI视频生成工具的胜负手，已经不是单次生成而是全流程生产","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782912776582-364i.png","2026-07-01T13:32:24.270244+00:00",{"id":56,"slug":57,"title":58,"cover_image":59,"image_url":59,"created_at":60,"category":13},"60c9b34d-281c-48f1-a389-b30f95af74b9","go-makes-backend-scale-easier-in-production-en","Go makes backend scale easier in production","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782910120371-yueu.png","2026-07-01T12:48:17.148443+00:00",{"id":62,"slug":63,"title":64,"cover_image":65,"image_url":65,"created_at":66,"category":13},"870ef5aa-ccd4-49f6-88e8-7bf52f68577b","boot-dev-go-playground-teaching-tool-en","Boot.dev’s Go Playground is a better teaching tool than a full IDE","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782909173250-xa75.png","2026-07-01T12:32:25.122224+00:00",{"id":68,"slug":69,"title":70,"cover_image":71,"image_url":71,"created_at":72,"category":13},"236310a3-50e1-4125-90ba-e876091ec809","zhihe-a210-riscv-soc-dev-kit-breakdown-en","Zhihe A210 turns RISC-V into a dev kit","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782905601305-w630.png","2026-07-01T11:32:58.099197+00:00",[74,79,84,89,94,99,104,109,114,119],{"id":75,"slug":76,"title":77,"created_at":78},"8008f1a9-7a00-4bad-88c9-3eedc9c6b4b1","surepath-ai-mcp-policy-controls-en","SurePath AI's New MCP Policy Controls Enhance AI Security","2026-03-26T01:26:52.222015+00:00",{"id":80,"slug":81,"title":82,"created_at":83},"27e39a8f-b65d-4f7b-a875-859e2b210156","mcp-standard-ai-tools-2026-en","MCP Standard in 2026: Integrating AI Tools","2026-03-26T01:27:43.127519+00:00",{"id":85,"slug":86,"title":87,"created_at":88},"165f9a19-c92d-46ba-b3f0-7125f662921d","rag-2026-transforming-enterprise-ai-en","How RAG in 2026 is Transforming Enterprise AI","2026-03-26T01:28:11.485236+00:00",{"id":90,"slug":91,"title":92,"created_at":93},"6a2a8e6e-b956-49d8-be12-cc47bdc132b2","mastering-ai-prompts-2026-guide-en","Mastering AI Prompts: A 2026 Guide for Developers","2026-03-26T01:29:07.835148+00:00",{"id":95,"slug":96,"title":97,"created_at":98},"3ab2c67e-4664-4c67-a013-687a2f605814","garry-tan-open-sources-claude-code-toolkit-en","Garry Tan Open-Sources a Claude Code Toolkit","2026-03-26T08:26:20.245934+00:00",{"id":100,"slug":101,"title":102,"created_at":103},"66a7cbf8-7e76-41d4-9bbf-eaca9761bf69","github-ai-projects-to-watch-in-2026-en","20 GitHub AI Projects to Watch in 2026","2026-03-26T08:28:09.752027+00:00",{"id":105,"slug":106,"title":107,"created_at":108},"9f332fda-eace-448a-a292-2283951eee71","practical-github-guide-learning-ml-2026-en","A Practical GitHub Guide to Learning ML in 2026","2026-03-27T01:16:50.125678+00:00",{"id":110,"slug":111,"title":112,"created_at":113},"1b1f637d-0f4d-42bd-974b-07b53829144d","aiml-2026-student-ai-ml-lab-repo-review-en","AIML-2026 Is a Bare-Bones Student Lab Repo","2026-03-27T01:21:51.661231+00:00",{"id":115,"slug":116,"title":117,"created_at":118},"6d1bf3f6-e191-4d30-b55b-8a0722fa6afe","ai-trending-github-repos-and-research-feeds-en","AI Trending Tracks Repos and Research Feeds","2026-03-27T01:31:35.709532+00:00",{"id":120,"slug":121,"title":122,"created_at":123},"010539a1-4c3a-4bd3-937a-26616422ee0d","awesome-ai-for-science-research-tools-map-en","Awesome AI for Science Is Becoming a Real Research Map","2026-03-27T01:46:50.89513+00:00"]