AGENTIC MEMORY

Skills

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

← Back to Skills

foundry-agentic-loop

Build agentic solutions on Microsoft Foundry, GitHub and Azure: hosted agents, toolbox tools and skills, Foundry IQ grounding and a React/FastAPI app. Three modes: rapid prototyping in an existing Foundry project; spec-driven development (SDD), where the foundry-agentic-loop-workflow runs Specify, Implement, Verify and Deploy to create the Foundry project and deploy with azd, or one phase runs alone; and Improve, which refines this skill and the workflow from past runs. Use for Agentic Loop requests and canvas actions, or end-to-end agent solutions from architecture to Azure deployment. Not for isolated Azure administration or unrelated UI edits.

Original source
github
License
MIT
Pinned revision
5269f7ea2d6c3a9bfda5ed878b6726cf509121fd

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 github--foundry-agentic-loop at revision 5269f7ea2d6c3a9bfda5ed878b6726cf509121fd, 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 · 41

evals/fixtures/improve-history/docs/LOOP.md

Agentic Loop lessons

Verified lessons from building this workspace. Improve mode turns them into skill and workflow changes, only with approval.

2026-09-02 expense-assistant, SDD

Outcome: Deployed after two Verify rounds.

| Observation and evidence | Proposed skill change (file, section) | Expected benefit | Regression check | Status | | --- | --- | --- | --- | --- | | Verify r1 (wr_101): no execute_tool spans for get_receipt; the MCP server had no OpenTelemetry exporter. Fixed by configuring the exporter; trace rerun passed. | references/observability.md, MCP server | Saves one Verify round (measured once) | eval 11 | proposed | | Deploy (wr_101): TOOLBOX_ENDPOINT missing in the hosted agent; mapped it in azure.yaml env and redeployed; smoke passed. | references/azd-layout.md, environment mapping | Avoids a failed deploy (estimate) | eval 26 | adopted |

2026-09-20 travel-desk, SDD

Outcome: Deployed after two Verify rounds.

| Observation and evidence | Proposed skill change (file, section) | Expected benefit | Regression check | Status | | --- | --- | --- | --- | --- | | Verify r1 (wr_117): MCP tool spans missing again in Application Insights; same missing exporter in the MCP server. Trace rerun passed after the fix. | references/observability.md, MCP server | Saves one Verify round (measured twice) | eval 11 | proposed | | Implement (wr_117): the frontend dev server picked port 5174 because 5173 was busy; restarted on 5173. | none | — | — | rejected | | Hosted checkpoint (wr_117): runtime skill load verified through the toolbox before backend work. | references/hosted-integration-checkpoint.md | Validated by wr_117 | eval 8 | validated |

2026-10-05 lease-review, SDD

Outcome: Blocked at Verify; user stopped the run.

| Observation and evidence | Proposed skill change (file, section) | Expected benefit | Regression check | Status | | --- | --- | --- | --- | --- | | Verify r1 (wr_123): Playwright timed out once on a cold Container Apps start; the rerun passed without changes. | none | — | — | proposed |