I Built a Personal Developer Gem — Here's What It Actually Does

A Gemini Gems conversation interface showing a code review with syntax-highlighted code snippets and a clean minimal design
Part of the "My AI Team" Series — Each post covers one specific Gem I use daily. See the full series overview.

My primary work is network infrastructure, not software development. But I write scripts regularly — automation, monitoring tools, configuration management. I'm competent in Python and shell scripting, less so in everything else. When I run into a problem outside my comfort zone, I want an answer that fits my context, not a tutorial written for a junior developer starting from zero.

My Developer Gem knows that about me.

What Is a Personal Developer Gem?

It's a Gemini assistant configured as a senior developer who knows your stack, your skill level, and your coding style. You don't have to re-explain your environment every time. You just ask the question.

For someone who codes as a secondary skill rather than a primary one, that context is the difference between a useful answer and a frustrating one.

Why I Built This Gem

The pattern that pushed me to build this:

  • I'd ask a generic AI a Python question and get an answer that assumed a completely different environment than mine
  • I'd get code that technically worked but wasn't idiomatic or didn't match how the rest of my scripts were structured
  • I'd ask about a debugging problem and receive a wall of explanations I already knew before getting to the part I actually needed

A Gem that knows my setup skips all of that.

The Prompt I Use

Here's the core of my Gem's instructions:

You are my personal senior developer and code reviewer. When I ask coding questions: - Give direct, working answers — skip basics I already know - Match code style to my existing patterns when I share context - Explain the why when something isn't obvious, skip it when it is - Flag anything that looks like a security or performance issue - Ask for clarification if the problem isn't clear rather than guessing My context: IT/network infrastructure professional. Primary languages: Python, Bash. Occasional work in JavaScript. Environment: Linux servers, macOS workstations, Docker containers. I write automation and monitoring scripts, not applications.

The "skip basics I already know" instruction changes the quality of responses significantly. Without it, AI tends to over-explain.

Real Examples — What I Actually Ask It

Some recent questions I've put to this Gem:

  • "This Python script is taking 40 seconds to run against 200 hosts. Here's the code — where's the bottleneck?"
  • "I need to parse syslog output and extract specific fields. What's the most readable way to do this in Python?"
  • "This Bash script works but feels fragile. Can you review it for edge cases I might have missed?"

For the performance question, it identified that I was making sequential SSH connections where I could use concurrent threads, showed me the specific change, and estimated the speedup. No preamble about what SSH is. Just the answer.

What It's Good At (and Where It Falls Short)

Good at:

  • Code review that matches your actual skill level and context
  • Debugging with specific, actionable suggestions
  • Translating solutions from one language to another that you know better
  • Identifying security and performance issues before they become problems

Where it falls short:

  • It doesn't have access to your actual codebase unless you paste it in or use Drive integration
  • For very large codebases, pasting context becomes cumbersome — Claude Code handles that better
  • It can suggest solutions that work in principle but need adaptation for your specific environment

Try It Yourself — Starter Prompt

If you want to build a similar Gem, here's a starting point:

You are my personal senior developer and code reviewer. Give direct, working answers. Skip introductory explanations I already know. Flag security and performance issues. Ask for clarification rather than guessing. My context: [your role, primary languages, environment, what kind of code you write]

Paste this into a new Gem at gemini.google.com, fill in your context, and test it with a real piece of code you've been meaning to improve.

My AI Team Series

Related Posts

Sources & Further Reading

Do you use AI for code review or debugging? What's the most useful way you've found to give it context about your environment? Let me know in the comments.

Comments

Post a Comment

Popular posts from this blog

Free AI Tools You Should Start Using Right Now (2026 Guide)

Image
⚡ TL;DR: You don't need to pay to use powerful AI. This guide covers the best free AI tools in 2026 — including ChatGPT, Claude, Gemini, Canva AI, and more — with what each one is best for and how to get started today. You don't need to spend a dollar to start using AI today. Some of the most powerful AI assistants in the world offer genuinely useful free plans — enough to meaningfully change how you write, research, plan, and work. The confusing part: there are hundreds of AI tools competing for your attention, and many have misleading "free" labels that turn out to be very limited. In this guide, I'll cut through the noise and show you the free AI tools that are actually worth your time in 2026, what each one is best for, and exactly how to get started. I've personally tested every tool in this guide. I'll tell you honestly where each one shines and where the free version falls short. Why Free AI Tools Are Worth Your Time A common misco...
Read more

Gemini Gems vs. ChatGPT GPTs vs. Claude Projects: Which Is Right for You?

Image
Part of the "My AI Team" Series — This is the series overview. Each post after this covers one specific Gem I actually use, from a personal doctor to a DNS expert. Most people using Gemini or ChatGPT are doing it the basic way: type a question, read the answer, close the tab. That works. But every major AI platform now lets you go one step further and build a customized AI expert, a version of the AI you've configured for a specific role with context about your life and how you want it to communicate. Google calls these Gems . OpenAI calls them GPTs . Anthropic calls them Projects . I've tried all three, though not equally. Here's my honest take on each one. What Are Custom AI Assistants? A regular AI conversation starts from zero every time. The AI doesn't know you, your background, or what kind of answers actually help you. Custom AI assistants solve that. You write a set of instructions once: the role, your background, how you want it ...
Read more