Artificial Intelligence

Technical articles about Microsoft’s artificial intelligence services. Read about Azure AI topics such as their Bot Framework, Cognitive Services, and Machine Learning. Learn how to use tools such as Java, Python, Jupyter Notebooks, Visual Studio Code, along with open-source frameworks like TensorFlow and PyTorch.

Cohere Parse v5 is now available in Microsoft Foundry

Artificial Intelligence / By / Published / Updated 08/27/2026 / 2 minutes of reading

Cohere Parse, a vision language model built for converting enterprise documents into structured, machine-readable data, is now available in the Microsoft Foundry model . Parse joins Cohere’s Embed and Rerank models in Foundry. What Parse does Cohere Parse takes complex, multimodal files and returns clean Markdown suitable for downstream indexing and application logic.  According to […]

Cohere Parse v5 is now available in Microsoft Foundry Continue Reading

Grok 4.6 comes to Microsoft Foundry Models: Built for long-horizon reasoning and complex workflows

Artificial Intelligence / By / Published / Updated 08/26/2026 / 4 minutes of reading

The next wave of AI applications won’t be defined by how quickly models answer questions. They’ll be defined by how much work they can complete. Whether resolving repository issues, navigating codebases, generating engineering designs, or executing multi-step enterprise workflows, developers are increasingly building systems that need models capable of staying on task across complex, long-running

Grok 4.6 comes to Microsoft Foundry Models: Built for long-horizon reasoning and complex workflows Continue Reading

Consume Dataverse MCP server in Microsoft Foundry-Bringing business data to AI Agents

Artificial Intelligence / By / Published / Updated 08/25/2026 / 4 minutes of reading

Introduction Building AI agents that can actually do things in your business systems—create records, update opportunities, trigger workflows—typically requires weeks of custom integration work. The Dataverse MCP Server changes that. In this tutorial, you’ll connect a Microsoft Foundry agent to your Dataverse environment in under 30 minutes, giving your AI agent secure, real-time access to

Consume Dataverse MCP server in Microsoft Foundry-Bringing business data to AI Agents Continue Reading

Benchmark Retrieval Patterns for Copilot Studio and Foundry IQ

Artificial Intelligence / By / Published / Updated 08/24/2026 / 16 minutes of reading

Part 2 of a series. Part 1, Grounding Copilot Studio Agents with Azure AI Search and Foundry IQ, defined five grounding patterns. This article gives you a reproducible way to compare them without mixing latency boundaries, billing units, or quality signals. Reference implementation, not a production template. This article is for architects, agent developers, and

Benchmark Retrieval Patterns for Copilot Studio and Foundry IQ Continue Reading

Enabling A2A endpoint and Agent Card for a Hosted Agent

Artificial Intelligence / By / Published / Updated 08/24/2026 / 6 minutes of reading

Building an agent shouldn’t require you to reinvent platform capabilities. With Microsoft Foundry, hosted agents inherit essential capabilities such as authentication, ingress management, A2A transport, and discovery endpoints, freeing developers to focus on business logic and user value. This article demonstrates the quickest route from a local containerized agent to a fully discoverable A2A endpoint

Enabling A2A endpoint and Agent Card for a Hosted Agent Continue Reading

Building Production-Ready AI Agents in Microsoft Foundry: 10 Lessons Learned

Artificial Intelligence / By / Published / Updated 08/24/2026 / 7 minutes of reading

A Real-World Scenario Imagine a customer support agent that answers invoice questions. During testing, everything works perfectly. But in production: The Finance API occasionally times out. The knowledge base contains outdated information. Tool calls fail during peak traffic. Token consumption rises unexpectedly. The result isn’t a broken AI model. It’s an unreliable system. This is

Building Production-Ready AI Agents in Microsoft Foundry: 10 Lessons Learned Continue Reading

Expanding Open Model Choice in Microsoft Foundry with New DeepSeek and NVIDIA Nemotron Models

Artificial Intelligence / By / Published / Updated 08/21/2026 / 5 minutes of reading

Open models are driving a new wave of AI innovation, giving organizations more freedom to choose the models that best fit their requirements for performance, cost, latency, customization, and governance. As the open model ecosystem evolves rapidly, developers want access to the latest innovations without being locked into a single model provider or deployment approach.

Expanding Open Model Choice in Microsoft Foundry with New DeepSeek and NVIDIA Nemotron Models Continue Reading

Model router updates: new regions, a refreshed model pool, and understanding the hill climb

Artificial Intelligence / By / Published / Updated 08/21/2026 / 6 minutes of reading

Across Microsoft, “hill climbing” has become shorthand for how real AI progress happens: not in one dramatic leap, but through a disciplined loop. Microsoft AI defines the hill climb as an organization that continuously improves, cycle after cycle, through more compute, better data, and sharper evaluation. Reinforcement fine-tuning in Foundry defines it as improving the deployable model package one

Model router updates: new regions, a refreshed model pool, and understanding the hill climb Continue Reading

Build a SAFE Agent on Microsoft Foundry

Artificial Intelligence / By / Published / Updated 08/20/2026 / 20 minutes of reading

Use ACS to enforce Scope, Anchored Decisions, Flow Integrity, and Escalation while the agent runs, then prove the controls without model variance. Two sign-in failures, two correct outcomes A help desk agent receives two reports that sound almost identical: “I cannot sign in.” In the first case, the identity service is healthy, the account is

Build a SAFE Agent on Microsoft Foundry Continue Reading

Updates to GPT-chat-latest in Microsoft Foundry

Artificial Intelligence / By / Published / Updated 08/13/2026 / 3 minutes of reading

GPT-chat-latest in Microsoft Foundry is built on GPT-5.6 Sol, bringing focused responses, improved factual reliability, and consistent behavior to conversational applications without requiring developers to select a newly named model endpoint. This update gives developers access to the latest chat model improvements for advanced, natural, multimodal, and context-aware experiences while preserving an existing integration path

Updates to GPT-chat-latest in Microsoft Foundry Continue Reading

Contact Us
Contact Us