AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

microsoft-foundry

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent, managed harness agent, Copilot harness, voice agent, create/update/invoke/evaluate agent, add tool to agent, agent insights, batch/continuous eval, continuous monitoring, agent CI/CD, optimize/improve prompt, optimize agent instructions, Agent Optimizer, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

Original source
microsoft
License
MIT
Pinned revision
3f5b461b2314e01c400564051e92469114c5b68f

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

This skill also requires local files or dependencies. Remote reading alone may not be enough.

Ask your assistant

Use Agentic Memory skills to read microsoft--microsoft-foundry at revision 3f5b461b2314e01c400564051e92469114c5b68f, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 151

foundry-agent/create/references/langchain-langgraph-hosting.md

LangChain and LangGraph Hosting

Use this guidance when creating, migrating, or re-hosting a LangChain or LangGraph agent on Foundry.

Design Intent

Preserve the agent's existing framework behavior and minimize migration-specific code. Choose the least invasive hosting path that satisfies the requested behavior.

Treat migration as additive. Do not delete or replace user-authored code, and do not remove existing dependencies. Add only the hosting configuration, files, and dependencies required to run the existing agent on Foundry.

Do not add, remove, or replace the agent's checkpointer unless the user explicitly requests a checkpointing change. Checkpointing belongs to the agent's application logic, not its hosting configuration.

Hosting Decision

| Need | Hosting path | |------|--------------| | Standard LangChain or LangGraph agent hosting with no custom server behavior | Configuration-only | | Custom request handling, protocol behavior, lifecycle control, or other hosting behavior that configuration cannot express | Host server integration |

Prefer configuration-only hosting unless the user explicitly requests custom hosting behavior or the existing agent demonstrably requires it. Do not add host server integration merely because the project already contains agent code.

Sample Selection

Use the parent workflow's azd sample selection guidance. For configuration-only hosting, select the sample matching the required protocol:

| Protocol | Sample | |----------|--------| | Responses | Configuration-driven agent (Responses, LangGraph, Python) | | Invocations | Configuration-driven agent (Invocations, LangGraph, Python) |

Use a host server integration sample only when the hosting decision above requires that path.

Samples provide hosting patterns only. Use their manifests, adapters, protocol wiring, and deployment configuration as references; do not treat sample application structure or conventions as the desired final application.