--- title: Announcing the Databricks Big Book of AgentOps | daily.dev description: Databricks announces a new eBook, the Big Book of AgentOps, framing AgentOps as the next operational discipline after MLOps and LLMOps for running AI agents... canonical: https://daily.dev/posts/announcing-the-databricks-big-book-of-agentops-gt8yfloe4 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Announcing the Databricks Big Book of AgentOps | daily.dev og:description: Databricks announces a new eBook, the Big Book of AgentOps, framing AgentOps as the next operational discipline after MLOps and LLMOps for running AI agents... og:url: https://daily.dev/posts/announcing-the-databricks-big-book-of-agentops-gt8yfloe4 og:image: https://api.daily.dev/og/posts/gT8yfLOE4.png og:image:alt: Announcing the Databricks Big Book of AgentOps og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Announcing the Databricks Big Book of AgentOps **[databricks](https://daily.dev/sources/databricks)** · 8 min read · 1 upvotes · 0 comments ## Summary Databricks announces a new eBook, the Big Book of AgentOps, framing AgentOps as the next operational discipline after MLOps and LLMOps for running AI agents reliably in production. The book covers agent architecture patterns, a seven-phase delivery roadmap, evaluation and feedback loops adapted from DevOps principles, governance and cost management, and stakeholder alignment across engineering, security, compliance and finance. Customer examples include FactSet, DXC Technology, Intercontinental Exchange, and Block, with Databricks tools like Unity Catalog, Unity Gateway, and MLflow positioned as the governance foundation. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is AgentOps and how is it different from MLOps or LLMOps? AgentOps is the operating discipline for building, deploying, and improving AI agents in production, bringing together architecture, evaluation, observability, governance, security, and cost management into a repeatable process. It extends MLOps (managing models in production) and LLMOps (prompt/model versioning, serving, cost control) to systems that reason, use tools, and take action autonomously, since agents introduce new failure points like bad tool calls and permission issues. _daily.dev surfaces practical operating patterns for teams standing up production AI agent systems._ ### Why is monitoring only the final output not enough for AI agents in production? Because so much can happen between a request and an answer that only watching the final output misses it: tool calls, retrieval, permission checks, retries, and orchestration steps each affect quality, risk, latency, or cost independently. Tracing multi-step execution end to end is necessary to catch failures like bad tool calls, overbroad permissions, or unexpected cost spikes before they become liabilities. _engineers building observability into agent pipelines can track these practices on daily.dev._ ## Similar posts on daily.dev - [AgentOps: Operationalize agentic AI at scale with Amazon Bedrock AgentCore](https://daily.dev/posts/agentops-operationalize-agentic-ai-at-scale-with-amazon-bedrock-agentcore-bexrxqy2l) · AWS · 0 upvotes · 0 comments - [The Practitioner’s Guide to AgentOps](https://daily.dev/posts/the-practitioner-s-guide-to-agentops-jqo8sudet) · Machine Learning Mastery · 1 upvotes · 0 comments - [Building Trusted AI Agents: New Capabilities to Choose, Govern, and Scale with Confidence](https://daily.dev/posts/building-trusted-ai-agents-new-capabilities-to-choose-govern-and-scale-with-confidence-ihrflgih5) · databricks · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#ai-agents](https://daily.dev/tags/ai-agents), [#databricks](https://daily.dev/tags/databricks), [#mlops](https://daily.dev/tags/mlops) [View this post on daily.dev](https://daily.dev/posts/announcing-the-databricks-big-book-of-agentops-gt8yfloe4) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Announcing the Databricks Big Book of AgentOps","url":"https://daily.dev/posts/announcing-the-databricks-big-book-of-agentops-gt8yfloe4","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/announcing-the-databricks-big-book-of-agentops-gt8yfloe4"},"datePublished":"2026-09-02T01:17:05.323Z","dateModified":"2026-09-02T01:17:34.820Z","description":"Databricks announces a new eBook, the Big Book of AgentOps, framing AgentOps as the next operational discipline after MLOps and LLMOps for running AI agents...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/60c6efd6c39768642ce6cb5d40b28610?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/60c6efd6c39768642ce6cb5d40b28610?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"databricks","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"databricks","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/fa7aa720f2db4d1eba826814730482c8","url":"https://daily.dev/sources/databricks"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/announcing-the-databricks-big-book-of-agentops-gt8yfloe4","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,ai-agents,databricks,mlops","timeRequired":"PT8M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"databricks","item":"https://daily.dev/sources/databricks"},{"@type":"ListItem","position":3,"name":"Announcing the Databricks Big Book of AgentOps"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/announcing-the-databricks-big-book-of-agentops-gt8yfloe4#faq","mainEntity":[{"@type":"Question","name":"What is AgentOps and how is it different from MLOps or LLMOps?","acceptedAnswer":{"@type":"Answer","text":"AgentOps is the operating discipline for building, deploying, and improving AI agents in production, bringing together architecture, evaluation, observability, governance, security, and cost management into a repeatable process. It extends MLOps (managing models in production) and LLMOps (prompt/model versioning, serving, cost control) to systems that reason, use tools, and take action autonomously, since agents introduce new failure points like bad tool calls and permission issues. daily.dev surfaces practical operating patterns for teams standing up production AI agent systems."}},{"@type":"Question","name":"Why is monitoring only the final output not enough for AI agents in production?","acceptedAnswer":{"@type":"Answer","text":"Because so much can happen between a request and an answer that only watching the final output misses it: tool calls, retrieval, permission checks, retries, and orchestration steps each affect quality, risk, latency, or cost independently. Tracing multi-step execution end to end is necessary to catch failures like bad tool calls, overbroad permissions, or unexpected cost spikes before they become liabilities. engineers building observability into agent pipelines can track these practices on daily.dev."}}]} ```