We are moving past the era of simply “chatting” with AI code editors. The difference between a junior developer using AI and a senior architect using AI is context orchestration.

If you treat Cursor like a chatbot, you get generic code. If you treat it like a specialized agent operating within rigid architectural boundaries, you get production-ready software.

With Cursor’s latest updates, specifically the removal of Custom Modes and the introduction of Slash Commands, Skills, and Subagents, we now have a powerful framework to automate development standards.

Here is the concise guide to mastering this workflow.

1. Structure Your Intelligence (.cursor/rules/)

Forget the single, massive .cursorrules file. It is unmanageable and prone to context loss. Instead, use the .cursor/rules/ directory to create modular, domain-specific rule files.

We use the .mdc extension, which allows for metadata frontmatter to control exactly when the AI reads the rule.

Example: .cursor/rules/css-architecture.mdc

---
description: "Apply this rule when writing CSS or styling components"
globs: "**/*.css"
alwaysApply: false
---
# CSS Architecture Rules
- NO :root or @import declarations in widget files.
- MUST use var(--design-token) variables.
- NEVER use raw hex codes.

Configuration Options:

• Always Apply: Use for high-level context that must be present in every request (e.g., project-context.mdc).
• Apply Intelligently: Let Cursor decide relevance based on the description. Perfect for library-specific patterns (e.g., @react-patterns.mdc).
• Scoped (Globs): Enforce rules only on specific file types.

2. Define the “Source of Truth”

You must prevent the AI from hallucinating about your tech stack. Create a single rule file (e.g., project-context.mdc) with alwaysApply: true.

• Content: Project goals, current tech stack, folder structure, and “No-Go” zones.
• Example: “We are migrating FROM React TO Vanilla JS. The final output must be 100% vanilla. Do not suggest React solutions for output files.”

3. Replace “Custom Modes” with Slash Commands

Custom Modes have been removed from Cursor. The new, superior alternative is Custom Slash Commands. These allow you to bundle specific prompts and rule sets into a reusable trigger.

How to Implement:

• Create a folder .cursor/commands/.
• Add a markdown file, e.g., convert-widget.md.
• Define your workflow prompt inside.

Example: .cursor/commands/convert-widget.md

You are an expert frontend developer. Convert the selected React component into a production-ready vanilla HTML/CSS/JS widget.

You MUST follow these rules:
- @css-architecture.mdc
- @design-system.mdc
- @parallax-effects.mdc
Step-by-step plan:
1. Analyze the React props and state.
2. Create the HTML structure using our BEM naming convention.
3. Extract CSS using only allowed design tokens.

Usage: Type /convert-widget in chat to trigger this specialized agent behavior immediately.

4. Extend Capabilities with Skills

Use Skills (.cursor/skills/) to give the AI executable tools, not just text instructions. A skill is a package that can contain scripts (Python, Bash, etc.) that the Agent can actually run.

Use Cases:

• Minification: Create a skill that runs npm run minify automatically after generating code.
• Docs Fetching: A skill that fetches the latest documentation from your internal wiki or specific URLs.

5. Delegate Deep Thinking to Subagents

For tasks that require heavy reasoning, research, or multi-step architecture, use Subagents (.cursor/agents/). Subagents run in their own isolated context window, preventing them from polluting your main chat history or hitting token limits.

When to use a Subagent:

• The “Planner”: Before coding a complex feature, use a planner.md subagent to generate a detailed implementation plan.
• The “Architect”: Use a subagent to analyze the entire codebase map before suggesting a refactor.

Pro Tip: The “Two-Pass” Protocol

One of the most effective workflows I have discovered is decoupling creation from verification.

If you ask an AI to “Create this component and make sure it follows the rules,” it often prioritizes creation and glosses over the rules. Instead, split this into two distinct Slash Commands.

Step 1: The Maker (/build-widget)

This command focuses purely on logic and implementation. It generates the code based on your requirements.

Step 2: The Checker (/qa-review)

Once the code is generated, do not accept it yet. Run a second command against the specific context of the generated code.

Create .cursor/commands/qa-review.md:

You are a Senior QA Engineer.

Review the code generated in the previous turn. Cross-reference it STRICTLY against:
1. @design-system.mdc (Did it use raw hex codes?)
2. @css-architecture.mdc (Did it use :root?)
3. @accessibility.mdc (Are ARIA labels present?)

Output a checklist of PASS/FAIL.
If there are failures, rewrite the code to fix them immediately.

Why this works:

When you force the AI to switch “personas” from a Creator to a Reviewer, it re-reads the output with a critical “eye,” catching 90% of the errors it would have otherwise missed.

Bonus: The AI-Native Designer Handoff

The most powerful application of this workflow isn’t just writing code from scratch — it’s transforming “raw” AI output into production-ready software.

Here is a real-world example of how I collaborate with designers who also use AI tools:

1. The Designer’s Role: My designer uses Figma (and tools like Figma’s “Make” or Dev Mode) to generate a raw React export of the design. This code is visually correct but often lacks our specific architectural standards or logic.
2. The Developer’s Role: Instead of coding from zero, I treat this React export as my “Source Material.”
3. The Cursor Workflow: I drag the raw React files into Cursor and run a custom Slash Command like /adapt-design.

Example Command (/adapt-design):

You are a Senior Frontend Architect.
Input: The raw React code from Figma in the current file.
Task: Refactor this strictly into our project structure.

1. KEEP the visual structure and Tailwind classes.
2. REPLACE hardcoded strings with our i18n keys.
3. EXTRACT types to `types.ts` according to @tech-stack.mdc.
4. ENSURE accessibility rules from @a11y.mdc are applied.

The Result: A seamless pipeline where the designer handles the visuals via AI, and your Cursor workflow instantly sanitizes and architects that code into your system. This turns the dreaded “handoff” into a simple 30-second conversion task.

Stop typing code. Start orchestrating intelligence.

\

The Azure SQL Migration extension for Azure Data Studio is being deprecated and will be retired by February 28, 2026. As part of our unified and streamlined migration strategy for Azure SQL, we are consolidating all migration experiences into a consistent, scalable platform.

If you are currently using the Azure SQL Migration extension, this blog will guide you through recommended replacement options for every phase of migration, whether you are moving to Azure SQL Managed Instance, SQL Server on Azure Virtual Machines, or Azure SQL Database.

What is happening to the Azure SQL Migration extension in ADS?

As you already know, Azure data studio will officially retire on February 28, 2026. The Azure SQL Migration extension in Azure Data Studio will also retire along with Azure Data Studio on February 28, 2026. The Azure SQL Migration extension will no longer be available in the marketplace of Azure Data Studio.

What should you use instead?

Below is the updated guidance for the migration tool categorized by migration phase and target.

1) Pre‑Migration: Discovery & Assessments

Prior to migration, it is advisable to evaluate the SQL Server environment for readiness and to determine the right-sized Azure SQL SKU. Below are the recommended options:

A) SQL Server enabled by Azure Arc

Use the SQL Server migration experience in the Azure Arc portal for:

1. 1. Instance discovery at scale
   2. Migration assessments at scale, including:

• • • Readiness assessment for all Azure SQL targets.
    • Performance-based, right-sized target recommendations.
    • Projected Azure costs with the recommended target configuration.

Reference: 

Steps to get started with the Azure Arc assessments-

1. 1. Deploy Azure Arc on your servers.
   2. SQL Server instances on Arc-enabled servers are automatically connected to Azure Arc. See options to optimize this.

B) Automated assessments at scale using Azure DMS PowerShell and Azure CLI

The Azure DataMigration modules in Azure PowerShell and Azure CLI can be used to automate assessments at scale. Learn more about how to do this.

Here are the sample templates to automate the assessment workflow:

• 1. Azure PowerShell DataMigration cmdlets
  2. DMS Azure CLI commands

C) Azure Migrate

For scenarios where assessments are required at data center level including different types of workloads like Applications, VM Servers and databases, use Azure Migrate to perform discovery and assessments at scale. Learn more about Azure Migrate.

References:

1. 1. Review inventory
   2. Create SQL Assessment
   3. Review SQL Assessment

2) Migrations

Based on the migration targets, here are the recommended tools you can use to carry out the migration:

A.    To Azure SQL Managed Instance

The following options are available for migrating data to Azure SQL Managed Instance:

1. SQL Migration experience in Azure Arc 

For migrations to Azure SQL MI, leverage the streamlined SQL Migration experience in Azure Arc which lets you complete the end-to-end migration journey in a single experience.

This experience provides:

• • • Evergreen assessments and right-fit Azure SQL target recommendation.
    • Inline Azure SQL Target creation.
    • Free Azure SQL MI Next generation General Purpose service that lets you experience the power of Azure SQL MI for free for 12 months.
    • Near zero downtime migration using Managed Instance link powered by Distributed Availability Group technology.
    • Secure connectivity.

Reference blog: SQL Server migration in Azure Arc

2.  Automated migration at scale using Azure DMS PowerShell and Azure CLI

To Orchestrate migrations to Azure SQL MI at scale programmatically, use:

• • • DMS PowerShell cmdlets 
    • DMS Azure CLI commands

Learn more about how to do this.

B.    To SQL Server on Azure Virtual Machines

To migrate to SQL Server on Azure Virtual Machines, use:

1. Azure Database Migration Service (DMS) 

DMS supports migrating to SQL Server on Azure Virtual Machines using both online and offline methods. Your SQL Server backups can be in Azure Blob Storage or on a network SMB file share. For details on each option, see:

• • • Backups stored in Azure Blob Storage
    • Backups maintained on network SMB file shares

Note: The migration experience from SQL Server on-premises to SQL Server on Azure VM will soon be available in SQL Server enabled by Azure Arc.

2. Automated migration at scale using Azure DMS PowerShell and Azure CLI

For programmatic migrations to Azure SQL Virtual Machines:

• • • DMS PowerShell cmdlets
    • DMS Azure CLI commands

Learn more about how to do this.

3. SSMS option: SQL Server Management Studio (SSMS) migration component

If you can connect to both SQL Server on-premises and SQL Server running on Azure VM using SQL Server Management Studio, the migration component in SSMS can help you to migrate to SQL Server on Azure VM.

For details, see SSMS Migration component.

C.   To Azure SQL Database

Migrating a SQL Server database to Azure SQL Database typically involves migrating schema and data separately. Here are the options to perform offline and online migration to Azure SQL Database:

1. Offline migration to Azure SQL Database

a. Azure Database Migration Service (DMS) portal experience

Use Azure DMS portal to migrate both schema and data. Azure DMS uses Azure Data Factory and leverages the Self-hosted Integration Runtime (SHIR). Installation steps are here.

b. Automated migration at scale using Azure DMS PowerShell and Azure CLI

Use Azure DMS PowerShell and Azure CLI command line to orchestrate the schema and data migration to Azure SQL Database at scale:

• • • DMS PowerShell cmdlets
    • DMS Azure CLI commands

 Learn more about how to do this.

2. Online migration to Azure SQL Database

Using Striim

To enable online migration of your mission critical databases to Azure SQL Database leverage Striim. Microsoft and Striim have entered a strategic partnership to enable continuous data replication from off-Azure SQL Servers to Azure SQL Database with near-zero downtime.

For more details, refer to:

• • • Zero downtime migration from SQL Server to Azure SQL Database | Microsoft Community Hub
    • Removing barriers to migrating databases to Azure with Striim’s Unlimited Database Migration program...

To leverage the Striim program for migrations, please reach out to your Microsoft contact or submit the below feedback to get started.

Summary

The table below provides a summary of the available alternatives for each migration scenario.

Final Thoughts

Simplify your SQL migration journey and improve migration velocity to all Azure SQL targets, leverage the connected migration experiences in SQL Server enabled by Azure Arc, DMS, and SSMS.

For SSMS, as a first step we brought the capabilities to perform assessment and migration to higher versions of SQL Server including to SQL Server on Azure Virtual Machines. As a next step, we are bringing cloud migration capabilities as well into SSMS.

Feedback

We love hearing from our customers. If you have feedback or suggestions for the product group, please use the following form:

Feedback form

As you begin your migration to Azure, we welcome your feedback. If you do not see suitable alternatives for any migration phases, use the feedback form to let us know so we can update the options accordingly.

1156. This week, we look at the pronunciation chaos surrounding "forte" and "pianoforte," from the French fencing term meaning "strong point" to the Italian musical direction meaning "loud." Then, we look at "playing the dozens" — the African American insult game with a mysterious origin.

🔗 Join the Grammar Girl Patreon.

🔗 Share your familect recording in Speakpipe or by leaving a voicemail at 833-214-GIRL (833-214-4475)

🔗 Watch my LinkedIn Learning writing courses.

🔗 Subscribe to the newsletter.

🔗 Take our advertising survey. 

🔗 Get the edited transcript.

🔗 Get Grammar Girl books. 

| HOST: Mignon Fogarty

| Grammar Girl is part of the Quick and Dirty Tips podcast network.

• Audio Engineer: Dan Feierabend
• Director of Podcast: Holly Hutchings
• Advertising Operations Specialist: Morgan Christianson
• Marketing and Video: Nat Hoopes, Rebekah Sebastian
• Podcast Associate: Maram Elnagheeb

| Theme music by Catherine Rannus.

| Grammar Girl Social Media: YouTube. TikTok. Facebook. Threads. Instagram. LinkedIn. Mastodon. Bluesky.

Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

🎧 Episode Notes: The Meta-Habit of High Performers: How Outer Loops Unlock Growth

In today's episode, we are discussing one of the most common habits I see in high-performing managers and senior engineers. It isn't a single trick, a morning routine, or a specific productivity hack—it is a meta-habit. It is a specific way of thinking about how you spend your energy and time to avoid the burnout that comes from working hard without seeing commensurate gains,.

• The Burnout Trap: Understand that if you keep putting more energy in without getting equal or greater results out (sub-linear returns), you are heading for a wall. You cannot simply "grind" your way to the next level,.
• Recognize Your Default Loops: Whether you know it or not, you are already running "loops"—automatic heuristics and behaviors that define your decisions, like "while happy at job, stay at job",.
• The Inner vs. Outer Loop: Learn the difference between the Inner Loop (your execution, habits, and daily protocols) and the Outer Loop (the meta-observation that evaluates the system).
• Governing the Experiment: Discover how to use an Outer Loop to set longer-term conditionals for your career experiments (e.g., "I will try this until X"), preventing you from reacting emotionally to single data points,.
• Systematic Evaluation: Move from making random changes to making informed adjustments by stepping out of the daily grind to evaluate the trajectory of your habits,.

🙏 Today's Episode is Brought To you by: Unblocked

There’s a good chance you’ve already tried a few AI code review tools — and you’re probably ignoring most of their comments.

Not because AI can’t review code, but because it’s missing context. Most AI reviewers focus on surface-level issues: style nits, obvious refactors, or restating what’s already clear from the diff. Meanwhile, the things you actually care about, like whether a change violates an earlier architectural decision or quietly duplicates existing logic, go unnoticed.

That’s the problem Unblocked is built to solve.

Unblocked’s AI code review is grounded in decision-grade context, prior PRs, design discussions, documentation, and system-level constraints—the same context senior engineers rely on when reviewing code.

Teams using Unblocked report fewer comments, higher signal, and automated reviews they actually trust — enough that many have turned off other AI review tools entirely.

Even if you’ve already written off AI code review, Unblocked is worth a look.

Get a free three-week trial at getunblocked.com/developertea.

📮 Ask a Question

If you enjoyed this episode and would like me to discuss a question that you have on the show, drop it over at: developertea.com.

📮 Join the Discord

If you want to be a part of a supportive community of engineers (non-engineers welcome!) working to improve their lives and careers, join us on the Developer Tea Discord community by visiting https://developertea.com/discord today!

🧡 Leave a Review

If you're enjoying the show and want to support the content head over to iTunes and leave a review! It helps other developers discover the show and keep us focused on what matters to you.

The post e269 – Behind the Curtain: A Day in the Life of a Presentation Designer appeared first on The Presentation Podcast.