{"podcast":{"title":"AI Engineering Podcast","slug":"ai-engineering-podcast","podcast_index_feed_id":5875646,"rss_url":"https://serve.podhome.fm/rss/c9abdd38-a5dc-5eb2-96fd-f833f93208a7","website_url":"https://www.aiengineeringpodcast.com","image_url":"https://assets.podhome.fm/f6ff0caa-931b-4c08-bfdd-08dc7f5cd336/638557211890591941ai_engineering_podcast_logo.jpg","author":"Tobias Macey","episode_count":79,"summary":"This show is your guidebook to building scalable and maintainable AI systems. You will learn how to architect AI applications, apply AI to your work, and the considerations involved in building or customizing new models. Everything that you need to know to deliver real impact and value with machine learning and artificial intelligence.","last_synced_at":null,"page_url":"https://stenobird.com/podcast/ai-engineering-podcast"},"episode":{"title":"From Probabilistic to Trustworthy: Building Orion, an Agentic Analytics Platform","slug":"from-probabilistic-to-trustworthy-building-orion-an-agentic-analytics-platform","published_at":"2025-10-11T22:22:32+00:00","page_url":"https://stenobird.com/podcast/ai-engineering-podcast/from-probabilistic-to-trustworthy-building-orion-an-agentic-analytics-platform","show_page_url":"https://stenobird.com/podcast/ai-engineering-podcast","url":"https://www.aiengineeringpodcast.com/orion-agentic-analytics-platform-episode-64","audio_url":"https://op3.dev/e/dts.podtrac.com/redirect.mp3/serve.podhome.fm/episode/f6ff0caa-931b-4c08-bfdd-08dc7f5cd336/638958176438672283d46eab73-f4ec-413c-841f-665129baa0c5.mp3","summary":"Building reliable AI agents requires moving beyond probabilistic guesswork toward deterministic, grounded systems. This episode explores how the Orion platform uses semantic layers and quality-assurance loops to deliver trustworthy, proactive business analytics.","meta_description":"Learn how to build trustworthy agentic analytics by grounding LLMs in semantic layers, fact tables, and parallel test-time compute to ensure accuracy.","key_points":["Main idea: Transitioning from probabilistic LLM outputs to deterministic tools and grounded semantic layers is essential for enterprise trust","Practical takeaway: To prepare for AI agents, maintain clean metadata, descriptive column names, and well-structured fact tables","Failure mode: Compounding error rates in multi-agent sequences can lead to significant inaccuracies if not managed via orchestration","Practical takeaway: Use parallel test-time compute and validation loops to verify that agentic reasoning aligns with business reality","Main idea: The role of the professional is evolving from a manual contributor to an 'AI manager' who oversees agentic workflows"],"chapters":[{"start_ms":60000,"title":"Infrastructure for AI Tools","summary":"An overview of using Prefect and FastMCP to manage orchestration, OAuth, and serverless scaling for AI tool infrastructure."},{"start_ms":345000,"title":"Foundations of Orion","summary":"The origins of the Orion platform and the founders' backgrounds in machine learning and business intelligence."},{"start_ms":650000,"title":"Proactive Analytics","summary":"How agentic systems can perform root cause analysis and anomaly detection by understanding organizational context."},{"start_ms":960000,"title":"The Challenge of Grounding","summary":"Addressing the risks of unconstrained SQL generation by implementing schema metadata and historical trend grounding."},{"start_ms":1280000,"title":"Ensuring Metric Accuracy","summary":"Strategies to prevent the misrepresentation of data and ensure that automated insights remain trustworthy."},{"start_ms":1645000,"title":"Agentic Design Patterns","summary":"Discussing the risks of compounding error rates in sequential LLM architectures and the evolution of agent design."},{"start_ms":2000000,"title":"The Future of Knowledge Work","summary":"How agentic processes can capture institutional knowledge and the emerging career path of the 'AI Manager'."}],"topics":["Agentic Workflows","Business Analytics","Semantic Layer","LLM Reliability","Data Engineering","Context Engineering","AI Orchestration","Automated Insights"],"duration_seconds":4339,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/ai-engineering-podcast/episodes/from-probabilistic-to-trustworthy-building-orion-an-agentic-analytics-platform/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/ai-engineering-podcast/from-probabilistic-to-trustworthy-building-orion-an-agentic-analytics-platform.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}