aiqbenchInformații despre AI & calcul cuantic

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

perspectiva aiqbenchProduse AI

Microsoft extends Azure Logic Apps' agent capabilities by integrating sandboxed code interpreters that allow LLMs to generate and execute Python, JavaScript, C#, and PowerShell within isolated Hyper-V sessions. This architecture enables secure, end-to-end workflow automation where agents can process complex data tasks without requiring manual coding or risking host system integrity. The feature effectively transforms Logic Apps into a governed platform for executing untrusted code generated by models, bridging the gap between natural language intent and production-grade integration.

Surse care acoperăInfoQ, Latent Space

Azure Logic Apps Adds Sandboxed Code Interpreters to Agent Workflows

InfoQ27 mai 20264 min de cititArticolul și perspectiva sunt în engleză.

Microsoft added sandboxed code interpreters to Azure Logic Apps, enabling agents within integration workflows to generate and execute Python, JavaScript, C#, and PowerShell in Hyper-V isolated sessions. Architects get full control over model selection per workflow. The capability positions Logic Apps as an agent platform for integration alongside Foundry and Copilot Studio. By Steef-Jan Wiggers

Microsoft has introduced code interpreters for Azure Logic Apps, enabling AI agents within Logic Apps workflows to generate and execute Python, JavaScript, C#, and PowerShell code in Hyper-V isolated sandboxes. The code interpreters run as tools within the Logic Apps agent loop, meaning an LLM can receive a natural-language instruction, generate code to fulfill it, execute that code in a secure sandbox, and return the results, all within a single governed workflow. The capability is powered by…

Extras afișat conform termenilor RSS ai publicației · 77 cuvinte · textul integral și figurile sunt pe site-ul publicației

Citește pe InfoQ ↗Întreabă despre acest articol