demo-caldova-evidence-agent
Guide or rehearse the Caldova Evidence Agent demo one beat at a time. Use when: demo the Caldova evidence agent, rehearse the SQL MCP demo, walk through the evidence agent, start the evidence demo, next beat, show Foundry Log stream, or practice the causal evidence follow-up.
- License 许可
- MIT
- 最近更新
- 2026-11-01
- Stars
- ★ 3
- Forks
- 0
01 前言 Front Matter
- name
- demo-caldova-evidence-agent
- description
- Guide or rehearse the Caldova Evidence Agent demo one beat at a time. Use when: demo the Caldova evidence agent, rehearse the SQL MCP demo, walk through the evidence agent, start the evidence demo, next beat, show Foundry Log stream, or practice the causal evidence follow-up.
03 SKILL.md 正文
Demo Caldova Evidence Agent
Guide the presenter from DEMO-RUNBOOK.md. Do not provision, redeploy, or modify resources during a demo request.
Preflight
- Read
DEMO-RUNBOOK.mdcompletely. - Run
deploy/11-verify-system.ps1synchronously. - Follow the
run-caldova-evidence-agentskill to open or reuse the app and verify its standalone Edge window. - Ask the presenter to open the hosted agent Log stream in Microsoft Foundry if it is not already visible.
- Report readiness and wait for the presenter to say
start.
Beat Order
Guide exactly one beat at a time:
- Establish the natural research question.
- Show the live Foundry skill and three direct SQL MCP calls.
- Read the five-phase visual briefing.
- Use Find strongest causal evidence and show the visual comparison.
- Close on the governed three-tool SQL MCP boundary.
After each beat, provide only the action, expected visual proof, and concise talk track. Wait for next before advancing.
Guardrails
- Never run deployment scripts during a presentation walkthrough.
- Never reset the database or corpus during the demo.
- Do not claim the human clinical evidence is high-confidence; say confidence is high for mechanistic plausibility and qualified for human causality.
- The causal follow-up should reuse evidence and make no new MCP search when the existing sources are sufficient.
04 同仓库更多 Skills
keynote-demo-app
Build or extend a SQLCon EU 2026 keynote demo application so it looks and behaves like the other keynote apps. Use when creating a new demo view (invoices, operations, orders), restyling an existing app to match, adding a deliberate database anti-pattern for a troubleshooting demo, or wiring an app to Azure SQL or Fabric SQL with managed identity. Triggers include "make this look like the keynote app", "build a demo view", "add the slow query demo", "match Caldova styling".
validate-post-migration-data
Validate data and schema after migrating SQL Server to Azure SQL Database, Azure SQL Managed Instance, or SQL Server on Azure VM. Use after migration, restore, BACPAC import, LRS completion, cutover validation, row-count comparison, or source-target reconciliation.
sql-server-to-sql-mi-lrs-migration
Migrate SQL Server databases to Azure SQL Managed Instance with Log Replay Service (LRS) using managed identity for Blob access. Use for SQL Server to SQL MI, LRS, log replay, continuous restore, or low-downtime backup-chain migrations.
sql-bacpac-to-azure-sql-db-migration
Migrate one or all user databases from SQL Server to Azure SQL Database with an offline BACPAC workflow. Use for BACPAC, SqlPackage export/import, bulk database migration, or offline Azure SQL Database migration requests.
sql-backup-restore-to-azure-sql-vm-migration
Migrate a SQL Server 2008 through SQL Server 2025 source to a SQL Server 2025 target wherever it runs, including SQL Server on Azure VM, by creating a local full backup, uploading it to Azure Blob Storage with AzCopy and the operator's Microsoft Entra identity, and restoring from URL with the target SQL Server managed identity. Sources newer than SQL Server 2025 are blocked because target restore compatibility has not been validated. Use for SQL-to-SQL, local-backup, AzCopy, managed-identity, Azure SQL VM, or SQL Server 2025 restore migrations.
run-migration-assessment
Route generic or unresolved SQL Server assessment, readiness, compatibility, cost, and SKU recommendation requests. Use for bare server names or whenever Azure versus local/on-premises is not explicit; ask which source applies, then delegate.