Content by john savill (66)
John Savill reviews Microsoft's October 2026 AI updates, covering foundation models, inference hardware, and agent capabilities. The overview also covers GitHub Copilot features, including session continuity and code review, alongside Azure API Management integration and broader changes to Microsoft's AI tooling.
John Savill reviews this week's Azure updates, covering Container Apps logging, confidential VMs, network security, storage quotas, and cross-tenant backup restore. The Halloween edition also covers Azure AI Foundry model cost management, Azure MCP Server 3.0, new model topics, and GitHub Universe.
John Savill explains where Microsoft security solutions fit as AI accelerates both attacks and defenses. The video covers MDASH, Perception, Defender ISOC, security foundations, securing AI, and DART, providing an overview of how these offerings relate to cybersecurity.
John Savill examines why AI agents fail beyond the model itself, covering unclear goals, bad context, tool misfires, reasoning errors and lost state. He also discusses hijacking, excessive privileges, limited visibility and an improvement loop for understanding and addressing failures.
John Savill reviews this week's Azure and AI updates, including networking, backup, monitoring, storage, and identity changes. Topics include Traffic Manager integration with Azure DNS, keyless TLS, Cosmos DB key rotation, Azure Databricks private networking, and Copilot Studio agent identity.
John Savill explains what an agent control plane is and why it matters when you start running AI agents at scale, focusing on the need for centralized oversight, evaluation, and cost governance.
John Savill shares a short Azure Weekly Update for 16 October 2026, covering a handful of platform changes across resiliency, compute, networking, storage, and Azure’s AI hardware/model announcements.
John Savill gives a quick overview of “computer use” in AI: why a model alone isn’t enough, what an agent harness provides, and how desktop-style interaction changes the way AI systems can execute tasks while still needing boundaries, governance, and visibility.
John Savill runs through the Azure Weekly Update for 9th October 2026, covering a set of platform changes and retirements across AKS, App Service, developer environments, networking/WAF, API Management, PostgreSQL, SQL Server, and Fabric/OneLake, plus a security-focused note on Always Encrypted with Intel SGX enclaves.
John Savill gives a quick, practical overview of MCP (Model Context Protocol), explaining why it matters for integrating AI with external tools and services. He frames MCP as a standard way for models to discover capabilities and interact with “target services” through local or remote MCP servers.
John Savill recaps major Microsoft AI announcements from September 2026, focusing on Azure AI Foundry updates (models, routing, agent features, and controls), Copilot platform changes, and developer-facing items like GitHub Copilot and VS Code agent workflows, plus data/AI additions such as Azure SQL vector capabilities.
John Savill runs through the Azure Weekly Update for 2nd October 2026, covering a mix of retirements and new capabilities across compute, containers, storage, databases, Arc, and regional expansion, plus an AI model availability update.
John Savill explains Azure Container Apps (ACA) Sandboxes, focusing on how they provide isolated, secure hosting for agent workloads. He covers the MicroVM-based model, egress controls via proxy and rules, lifecycle and pricing considerations, how sandbox groups work, and operational topics like managing instances and logging.
John Savill gives a quick overview of the Azure Container Apps (ACA) Sandboxes capability and how it relates to Microsoft’s own agentic solutions.
John Savill runs through the Azure Weekly Update for 25 September 2026, covering a grab bag of platform changes across compute, serverless, containers, PostgreSQL, and Azure AI Foundry, plus several GitHub Copilot and model availability updates and a retirement notice.
John Savill shares practical lessons from customer work and Microsoft’s own AI efforts, focusing on what drives real value, why initiatives stall, and how to think about the human side, trust, and risk when adopting AI.
John Savill runs through a quick Azure weekly update covering AKS Azure Linux with OS Guard retirement, Azure Red Hat OpenShift hosted control planes, Application Gateway HTTP/3 over QUIC, AVNM high-scale mesh, storage migration over SMB, PostgreSQL skills and MCP, Azure SQL DB soft delete, AVD endpoints, and Azure Payments HSM v2.
John Savill shares a quick Azure Weekly Update covering recent platform changes and previews, including VM ephemeral OS disk caching, Azure Functions Flex Consumption custom TLS, user delegation SAS updates, AZD extension framework work, Azure Load Testing Playwright expansion, and new Copilot-related items.
John Savill recaps the major Microsoft AI updates from August 2026, including new and updated models, routing and content-understanding changes, and a set of Copilot and Azure Copilot improvements that affect how teams use AI features across developer and enterprise environments.
John Savill runs through the Azure Weekly Update for 4th September 2026, covering a set of platform changes across compute, AKS, networking, monitoring, security, and Azure AI Foundry, with quick pointers to what’s new and where the updates land in the Azure stack.
John Savill gives a quick, practical explanation of why generative AI models sometimes “hallucinate” (confidently produce incorrect information) and why this behavior is a natural outcome of how models generate text from probabilities rather than retrieving verified facts.
John Savill gives an overview of Azure Linux 4.0 (formerly CBL-Mariner), explaining why Microsoft built it, how it’s put together, where it can be used in Azure, and how it relates to Azure Container Host and WSL scenarios.
John Savill shares a short weekly Azure update, highlighting what’s new across Microsoft Azure and pointing viewers to related learning resources and playlists on his channel.
John Savill gives an overview and demo of Project Perception, focusing on how AI-driven workflows and agent-style collaboration can speed up cybersecurity operations across red/blue/green team activities and playbook-driven response.
John Savill runs through the Azure updates for 21st August 2026, covering changes across App Service, AVS licensing, ASR options, VM sizing, Application Gateway, Azure Firewall IPv6, SQL tooling in VS Code, SQL MI zone redundancy, Databricks region expansion, WSL Azure Linux, and new models and Copilot capabilities in Azure AI Foundry.
John Savill explains what an AI “harness” is and why it matters when working with large language models, focusing on how models behave (including their lack of native memory) and how the harness provides the surrounding logic and context needed to make an LLM useful in real applications.
John Savill runs through a fast-paced AI-103 study cram focused on building AI apps and agents on Azure, covering Azure AI Foundry concepts, model selection and deployment options, API/SDK usage, evaluations, and agent tooling including Microsoft Agent Framework and Foundry Agent Service.
John Savill shares a short Azure update for 14th August 2026, covering a channel milestone plus a set of platform changes across App Service, AKS, networking, security, storage, Fabric, PostgreSQL, and AI—including a note about Gemini 3.7 Flash appearing in GitHub Copilot.
John Savill gives a quick, practical overview of tokens and tokenization in LLMs, how models generate tokens, why context windows matter, and how token usage affects both user experience and cost.
John Savill introduces the core differences between AI, machine learning, deep learning, and generative AI in a short “Tech in Five” explainer, giving a practical mental model for how these terms relate and where LLMs fit in.
John Savill runs through the 7th August 2026 Azure update, covering changes across compute, networking, security, storage, SQL, and Databricks—highlighting VM defaults and retirements, new routing and proxy capabilities, Private Link over IPv6, and several Databricks and Azure SQL enhancements.
John Savill recaps major Microsoft AI updates from July 2026, including new and updated models, Azure AI Foundry changes, and GitHub Copilot feature additions such as new “harness” options, @-mentioning app agents, and browser tools for Copilot in VS Code.
John Savill explains Azure Standard Service Endpoints, focusing on how Network Identifiers (NIDs) simplify and scale VNet-to-PaaS access, and how they work alongside Network Security Perimeter controls for securing inbound access to supported Azure services.
John Savill gives a quick overview of Azure’s new Standard service endpoints, focusing on what they are and why they matter for networking scenarios that connect VNets/subnets to Azure platform services.
John Savill rounds up a week of Azure platform updates, spanning AKS, networking, API Management, monitoring, data services, and regional expansion, plus a few notable AI model availability items and security-related changes like Azure Enclave and Key Vault symmetric keys.
John Savill gives a very quick overview of Rayfin and Microsoft Fabric Apps, focusing on where they fit in the Fabric ecosystem and why they matter for analytics and data platform work.
John Savill gives a quick overview of Rayfin and Microsoft Fabric Apps, focusing on the problem they’re trying to solve, how the Fabric Apps data model works, and what app hosting looks like in practice, with a short demo and key takeaways.
John Savill recaps a small set of Azure updates for the week of 24th July 2026, covering new capabilities across AKS, Azure Functions runtimes, networking, DDoS protection, Defender security assessments for PostgreSQL Flexible Server, and a new Log Analytics table aimed at generative AI workloads.
John Savill gives a quick, practical introduction to Windows Sandbox, showing how to install it, what the underlying architecture looks like, and how to customize a sandbox session for safely running apps or processes in an isolated Windows environment.
John Savill gives an overview of Microsoft IQ and how it’s meant to bring the right intelligence (enterprise data, web data, and model capabilities) to AI agents, including the different “IQ” surfaces (Work, Fabric, Foundry, Web) and the security/identity considerations around least privilege and protection.