Hey {{first_name|there}},

(If this landed in spam or Promotions, move it to your inbox — it helps make sure you get future editions.)

I work at AWS. I’ve also been testing Cursor, Claude Code, and Codex on my own projects last month. What I found surprised me — not because any single tool was perfect, but because each one solved a completely different problem. So I pay close attention to what engineers are actually using in 2026.

I tested Claude Code to refactor a module straight from my terminal. I pointed Codex at a task and let it run in the background while I focused on something else. Three different tools, three different workflows, same week. Each one solved a problem the others couldn’t.

Here’s what I’ve noticed most engineers get wrong about AI coding tools:

They pick one and go all in.

But the best engineers I've spoken to don’t have “a tool.” They have a toolkit. Different tools for different problems — like choosing between a screwdriver and a drill. Both work on screws, but you wouldn’t use the same one for every job.

Right now, there are 5 tools reshaping how engineers build:

Kiro — AWS's agentic IDE. You describe a feature, it generates requirements, design docs, and tasks, then builds it. Now generally available with a free tier.

Cursor — The AI-native editor that understands your entire codebase. Background Agents work in parallel while you code.

Claude Code — Lives in your terminal. Plans multi-file changes, runs tests, commits code — all via natural language.

Codex — OpenAI's async agent. Assign a task, walk away, come back to a pull request.

Strands Agents SDK — AWS's open-source framework for building your own AI agents. Free forever, Apache 2.0.

The lesson: The question isn’t “should I use AI?” anymore. That debate is over.

The question is: which tool fits which problem?

Engineers who thrive in 2026 won't be the fastest coders. They'll be the ones who know which AI to point at which task.

So I put together The AI Coding Toolkit — a free 2-page guide that breaks down all five — with verified pricing, a side-by-side comparison table, a decision matrix, and step-by-step setup instructions for each one.

Here's your homework this weekend: pick one tool from the list above. Just one.

Download it, and open a real project you're already working on.

Not a tutorial. A real codebase. Give it 2 hours.

You'll know within the first 30 minutes whether it changes how you build.

Hit reply with MY STACK and tell me: which AI coding tools are you using right now? Or which one from this list are you trying first? I read every single reply.

Build smarter, not harder,

Olushola

If you’re a decision maker at your company, you need to be on the bleeding edge of, well, everything. But before you go signing up for seminars, conferences, lunch ‘n learns, and all that jazz, just know there’s a far better (and simpler) way: Subscribing to The Deep View.

This daily newsletter condenses everything you need to know about the latest and greatest AI developments into a 5-minute read. Squeeze it into your morning coffee break and before you know it, you’ll be an expert too.

Subscribe right here. It’s totally free, wildly informative, and trusted by 600,000+ readers at Google, Meta, Microsoft, and beyond.

P.S. Know 1 person trying to break into cloud? Share your personal referral link and I’ll send you my LinkedIn Profile Optimisation Checklist as a thank you.

P.P.S. Need personalised guidance on your cloud career or AI skills? I mentor people through exactly this → mentorship.sholastechnotes.com