HomeTags#foundry

Tag timeline

#foundry 11 total

同じキーワードで束ねられた更新を確認できます。カテゴリをまたいだ関連ニュースや実装トピックの追跡に使えます。

Total 11
Showing 11
Page 1/1
Updated just now

Entries page 1/1 · 11 total

YESTERDAY 1 entries
blog copilot 1d ago · microsoft-foundry

Outcome-driven learning systems: Enterprise RL with OpenEnv and Foundry Outcome-driven learning systems: Enterprise RL with OpenEnv and Foundry

通常 Normal 深掘り候補 · 技術記事 · GitHub Copilot Deep-dive candidate · technical post · GitHub Copilot 公開 6月19日 Published Jun 19

原文EN We shipped a lot at Build 2026: hosted agents, Toolboxes, Foundry IQ, Memory, Managed Compute, fine‑tuning, Frontier Tuning, and a new evaluation and optimization stack. Read as a feature list, it is

EN We shipped a lot at Build 2026: hosted agents, Toolboxes, Foundry IQ, Memory, Managed Compute, fine‑tuning, Frontier Tuning, and a new evaluation and optimization stack. Read as a feature list, it is

fallback
Thu, Jun 4 8 entries
blog copilot 2w ago · microsoft-foundry

Accelerate Edge AI Development with Foundry Local Accelerate Edge AI Development with Foundry Local

通常 Normal 深掘り候補 · 技術記事 · GitHub Copilot Deep-dive candidate · technical post · GitHub Copilot 公開 6月4日 Published Jun 4

原文EN Why edge AI development is still hard AI is no longer confined to cloud experiments. Developers are increasingly expected to deliver AI inside apps, devices, and edge systems where responsiveness, pri

EN Why edge AI development is still hard AI is no longer confined to cloud experiments. Developers are increasingly expected to deliver AI inside apps, devices, and edge systems where responsiveness, pri

fallback
blog copilot 2w ago · microsoft-foundry

Build 2026: From observability to ROI for AI agents on any framework Build 2026: From observability to ROI for AI agents on any framework

通常 Normal 深掘り候補 · 技術記事 · GitHub Copilot Deep-dive candidate · technical post · GitHub Copilot 公開 6月4日 Published Jun 4

原文EN 9 min read · June 3, 2026 · Sebastian Kohlmeier Shipping an AI agent is the easy part. Keeping it accurate, safe, and accountable in production is where teams get stuck. Agents are non-deterministic.

EN 9 min read · June 3, 2026 · Sebastian Kohlmeier Shipping an AI agent is the easy part. Keeping it accurate, safe, and accountable in production is where teams get stuck. Agents are non-deterministic.

fallback
blog copilot 2w ago · microsoft-foundry

Expanding the Reach of Document Translation – New Capabilities Announced at Microsoft Build Expanding the Reach of Document Translation – New Capabilities Announced at Microsoft Build

通常 Normal 深掘り候補 · 技術記事 · GitHub Copilot Deep-dive candidate · technical post · GitHub Copilot 公開 6月4日 Published Jun 4

原文EN Learn how new Document Translation capabilities in Azure Translator, available in Foundry Tools, help developers translate images, PDFs, Office files, DITA, XLIFF, and future LLM-powered document work

EN Learn how new Document Translation capabilities in Azure Translator, available in Foundry Tools, help developers translate images, PDFs, Office files, DITA, XLIFF, and future LLM-powered document work

fallback
blog copilot 2w ago · microsoft-foundry

Announcing Foundry Managed Compute: Run open models in Microsoft Foundry Announcing Foundry Managed Compute: Run open models in Microsoft Foundry

重要度 Medium Medium priority 重要度 Medium · 技術記事 · GitHub Copilot Medium priority · technical post · GitHub Copilot 公開 6月4日 Published Jun 4

原文EN Microsoft Foundry Managed Compute is a new GPU platform-as-a-service for hosting open-source and custom AI models behind the same endpoint, SDKs, and bill as frontier models. The post Announcing Found

EN Microsoft Foundry Managed Compute is a new GPU platform-as-a-service for hosting open-source and custom AI models behind the same endpoint, SDKs, and bill as frontier models. The post Announcing Found

fallback
blog copilot 2w ago · microsoft-foundry

Introducing Agent Optimizer in Foundry Agent Service Introducing Agent Optimizer in Foundry Agent Service

通常 Normal 深掘り候補 · 技術記事 · GitHub Copilot Deep-dive candidate · technical post · GitHub Copilot 公開 6月4日 Published Jun 4

原文EN With hosted agents, we made it straightforward to build and deploy agents on Foundry. You write your logic, run azd deploy, and your agent is live. But “live” and “production-ready” aren’t the same th

EN With hosted agents, we made it straightforward to build and deploy agents on Foundry. You write your logic, run azd deploy, and your agent is live. But “live” and “production-ready” aren’t the same th

fallback
blog copilot 2w ago · microsoft-foundry

Making agent memory more reliable, transparent, and production-ready Making agent memory more reliable, transparent, and production-ready

通常 Normal 深掘り候補 · 技術記事 · GitHub Copilot Deep-dive candidate · technical post · GitHub Copilot 公開 6月4日 Published Jun 4

原文EN Memory has always mattered for personalization and continuity. But as customers move agents from demos into production, another requirement becomes just as important: reliability. Enterprise teams nee

EN Memory has always mattered for personalization and continuity. But as customers move agents from demos into production, another requirement becomes just as important: reliability. Enterprise teams nee

fallback
blog copilot 2w ago · microsoft-foundry

Discovery to Execution: Scaling Agents with Toolboxes and Routines in Microsoft Foundry Discovery to Execution: Scaling Agents with Toolboxes and Routines in Microsoft Foundry

重要度 Medium Medium priority 重要度 Medium · 技術記事 · GitHub Copilot Medium priority · technical post · GitHub Copilot 公開 6月4日 Published Jun 4

原文EN Tooling doesn’t break at a small scale—it breaks when teams move to production. AI adoption accelerates, so does the number of tools available to them. Discovering, managing and securing the right too

EN Tooling doesn’t break at a small scale—it breaks when teams move to production. AI adoption accelerates, so does the number of tools available to them. Discovering, managing and securing the right too

fallback
blog copilot 2w ago · microsoft-foundry

From Building Agents to Working with Them: Enterprise Agent Distribution in Microsoft Foundry From Building Agents to Working with Them: Enterprise Agent Distribution in Microsoft Foundry

通常 Normal 深掘り候補 · 技術記事 · GitHub Copilot Deep-dive candidate · technical post · GitHub Copilot 公開 6月4日 Published Jun 4

原文EN The past year was about building agents. The next year is about putting them to work. Organizations have moved quickly from experimenting with AI agents to building ones that perform complex business

EN The past year was about building agents. The next year is about putting them to work. Organizations have moved quickly from experimenting with AI agents to building ones that perform complex business

fallback
Wed, Jun 3 2 entries
blog copilot 2w ago · microsoft-foundry

Build smarter document workflows: What’s new in Azure Content Understanding at Build 2026 Build smarter document workflows: What’s new in Azure Content Understanding at Build 2026

通常 Normal 深掘り候補 · 技術記事 · GitHub Copilot Deep-dive candidate · technical post · GitHub Copilot 公開 6月3日 Published Jun 3

原文EN Azure Content Understanding (CU) in Foundry Tools is Microsoft’s comprehensive content AI service. It ingests diverse data types — documents, audio, images, and video — and extracts the most critical

EN Azure Content Understanding (CU) in Foundry Tools is Microsoft’s comprehensive content AI service. It ingests diverse data types — documents, audio, images, and video — and extracts the most critical

fallback
blog copilot 2w ago · microsoft-foundry

A Developer’s Guide to Managing Models, Cost and Quality in Microsoft Foundry A Developer’s Guide to Managing Models, Cost and Quality in Microsoft Foundry

通常 Normal 深掘り候補 · 技術記事 · GitHub Copilot Deep-dive candidate · technical post · GitHub Copilot 公開 6月3日 Published Jun 3

原文EN Learn a practical model lifecycle for Microsoft Foundry: select the right model, evaluate quality, optimize cost, operate safely, and improve as production needs change. The post A Developer’s Guide t

EN Learn a practical model lifecycle for Microsoft Foundry: select the right model, evaluate quality, optimize cost, operate safely, and improve as production needs change. The post A Developer’s Guide t

fallback