Tips to improve your AI vibe coding

Bill Doerrfeld | June 3, 2025

My latest for InfoWorld outlines some top tips to make the most out of AI coding.

"So I finally tried vibe coding, and it didn't go so well..."


Posts like this are everywhere lately — and for good reason. Developers are realizing that being productive with AI coding assistants takes a lot more than just asking nicely. There's real craft to it.


These tools can hallucinate, delete code, hit context limits, degrade session quality, and quietly introduce security flaws.


So, today for InfoWorld, I pulled together expert tips from leaders at Cockroach Labs, DX, Graphite, Honeycomb, Sonar, and beyond. Their key recommendations to improve your AI coding results:


  • Improve your prompting skills
  • Find the right human-machine balance
  • Pick the right LLM for the task
  • Work in small chunks
  • Leave a trail of breadcrumbs for your AI
  • Test relentlessly
  • Feed it data schemas


In short — AI-assisted development is an entirely new muscle that developers are beginning to hone.


Also check out my previous article, which explores knowing when exactly to use AI coding assistants. Spoiler alert: they work better for some tasks than others.


Photo by Wai Yan Moe on Unsplash



Read: 7 ways to improve your AI coding results
Nordic APIs ranked #1 API blog on the web
By Bill Doerrfeld June 7, 2025
Nordic APIs, the API-specific blog I edit, was recently ranked the top API blog online by FeedSpot. After ten years managing this presence, I reflect a bit on the journey thus far.
AI coding is the easy part. Now it's time to focus on production.
By Bill Doerrfeld May 30, 2025
AI coding is the easy part. Now it's time to focus on DevOps to get it into production. In a recent interview for LeadDev's DirectorPlus, Honeycomb's CTO, Charity Majors, shares expert tips on how to accomplish this.
New tools help LLM devs improve training data decisions
By Bill Doerrfeld May 29, 2025
My latest for The New Stack explores new research from Ai2, DataDecide, which helps LLM developers make better decisions around training data.
MCP security vulnerabilities
By Bill Doerrfeld May 21, 2025
My APISEC|CON talk covers the hype around agentic AI and MCP, and delves into inherent flaws in MCP architectures and suggests mitigations.
Knowing when to use AI coding assistants Doerrfeld InfoWorld
By Bill Doerrfeld May 6, 2025
AI coding assistants are a productivity dream in some cases — and a debugging nightmare in others. So, where’s the line?
How semantic caching reduces LLM API calls
By Bill Doerrfeld May 5, 2025
Semantic caching is like typical caching, but for AI. It could eliminate a lot of redundant API calls to LLMs, reducing costs and improving performance.
Using agentic AI for business workflows
By Bill Doerrfeld April 30, 2025
For CIO.com, leading executives shared with me how they're actively utilizing agentic AI to enhance core business workflows.
Making developer productivity metrics actionable LeadDev DirectorPlus
By Bill Doerrfeld April 25, 2025
Developer productivity metrics are useless if they're just sitting in dashboards. So, how can we use them to direct positive, real-world action?
New study reveals what really drives revenue per engineer
By Bill Doerrfeld April 10, 2025
What leads to a higher revenue per engineer? New benchmarking from DX reveals how areas like R&D spend, org size, and growth rate move the needle.
LLMs can now cite their sources
By Bill Doerrfeld April 9, 2025
My latest post on The New Stack reveals how researchers pinpoint the exact sources behind chatbot responses.
More Posts