Claude Code, better in pair

Improve your AI generated software development plans by running it by one of its peers.

PublishedFebruary 5, 2026

I love technology and everything related, from gadgets to new professional techniques. I like thinking, researching, optimizing, inventing and developing. I have a strong background in software research and development, operating systems, Voice-over-IP, network security, wired and wireless network engineering, complemented with electronic engineering background.

My career goal is to always keep learning, to be challenged, and to work remotely so I can be present for my family.

Bug hacker and master troubleshooter, my strength is understanding a problem and getting to the root of it. I'm mostly a self-taught individual and a constant learner. I push my technical boundaries daily and search for ways to improve my skills every day. With over 20 years of experience writing software in various languages, creating or optimizing algorithms, the digital development world is my turf.

Sample challenges which I particularly enjoyed:

Created a GLSL based magnification tool for a client who was turned down by three other companies as "impossible to do on macOS".
Optimized several SQL queries to reduce load time of a particular web page from several seconds to sub 50ms.
Identified the root cause of stuttering animations in iOS mobile app and implemented mitigation strategy

Specialties: Swift, Objective-C and PHP Software Development; TCP/IP and Wireless Network Engineering

Comments

Join the discussion

No comments yet. Be the first to comment.

More from this blog

A case for API-level cryptography

Do you rely on TLS Pinning or OS level HTTPS handling for all your API privacy? You may either break your app or insufficiently protect your information on corporate networks. It is not unusual for large corporations to use HTTPS proxy for data ins...

Feb 17, 20268 min read

Strategies for dealing with Swift actor data races

When Swift introduced actors in Swift 5.5, many developers breathed a sigh of relief. Finally, a language-level construct that would protect us from data races! But here's the uncomfortable truth: actors don't eliminate data races—they just change wh...

Jan 28, 20269 min read

Strategies for dealing with Swift actor data races

Massive View Controllers and SwiftUI

Commenting on this post on LinkedIn: https://www.linkedin.com/posts/jacobmartinbartlett_the-biggest-problem-with-swiftui-is-that-activity-7261769674034409472-qGVe?utm_source=share&utm_medium=member_desktop I replied with: *The "Massive View Controll...

Nov 14, 20245 min read

Safely distributing API keys in your mobile app

The safest way is to keep your API keys server side. But if you have a library that's useable offline and it requires a license key to unlock, you will need a way to securely store that license key at runtime, without access to a server. Strap your h...

Jan 10, 20245 min read

Safely distributing API keys in your mobile app

Blog on Mobile app security and reliability on iOS and macOS.

16 posts

I'm a passionate senior iOS & macOS developer with over 13 years in the Apple ecosystem and 25 years in the software industry. I have a special interest for data security and privacy compliance!

When using Claude Code in terminal, I always have two separate Claude code sessions opened, each with their own context.

When one session gives me an implementation plan, I copy/paste the plan into the other and ask for a review of the plan for any issues.

While the AI attempts to review its own work, during the development of the plan it made assumptions and may have poisoned its own context with those decisions. But when you paste the plan in a new context and ask for analysis, this new context will not have those assumptions known and may point out interesting findings.

As a "Human in the loop", I decide whether the feedback on the plan requires me to go back to the original drawing board, or if I should just provide the feedback to the first session to self-correct.

This is also a really good time to re-evaluate what changes would have been required in the original inputs (your CLAUDE.md, Skills, MCP or your prompt) to avoid the highlighted issues. Sometimes, it means scrapping the entire session, and changing your original prompt to contain more information.

This process is what leads me to use external markdown files most of the time for my tasks, then just ask the AI to read the markdown file to know what is needed. This way, if any corrections are needed, I always have access to the original prompt data (in the markdown file).

I treat AI as a genius brand new developer joining your team. It doesn't matter how good they are, without context they won't be able to succeed. So knowing what to add, or what to remove, is what will make your AI session succeed or fail.

#HumanInTheLoop #AIDevelopment #CodeQuality

Command Palette

Comments

More from this blog