https://www.m365.fm/entity/semantic-caching/Semantic caching returns a stored LLM response for prompts that are similar in meaning to an earlier prompt, avoiding a new model call. Azure API Management offers semantic cache lookup and store policies for Azure OpenAI APIs.enhttps://www.m365.fm/community/u/mirko-p/blog/unlocking-hidden-costs-in-azure-ai-context-reasoning-and-autonomy/https://www.m365.fm/community/u/mirko-p/blog/unlocking-hidden-costs-in-azure-ai-context-reasoning-and-autonomy/Wed, 26 Aug 2026 15:49:47 -0000articleWelcome to our deep dive into the financial and structural realities of deploying intelligent workloads in the enterprise cloud. If you have been experimenting with…https://www.m365.fm/community/u/mirko-p/blog/unlocking-hidden-taxes-context-reasoning-and-autonomy-in-azure-ai-agents/https://www.m365.fm/community/u/mirko-p/blog/unlocking-hidden-taxes-context-reasoning-and-autonomy-in-azure-ai-agents/Wed, 26 Aug 2026 09:51:07 -0000articleWelcome back to the podcast companion blog! Today, we are expanding on a topic that has been keeping cloud architects, FinOps professionals, and IT leaders up at ni…https://www.m365.fm/show/episodes/how-to-architect-low-cost-ai-agents-in-the-microsoft-cloud/https://www.m365.fm/show/episodes/how-to-architect-low-cost-ai-agents-in-the-microsoft-cloud/Wed, 10 Jun 2026 00:00:00 -0000episodeLearn how to build low-cost AI agents in Microsoft Cloud with Azure OpenAI, Copilot Studio, Power Platform, and practical cost controls.