The AI Coding Perception Gap

Why Your 6-Month-Old Opinion May Need an Update

I’ve spoken with people from various organizations over the past several months as part of my job hunt, and there’s definitely no consensus on what “AI Coding” looks like from an implementation standpoint within organizations. I’ve heard more than once that “it can’t do X very well...” from folks who may have formed that opinion 6 months ago and decided to shelf further exploration until the technology matures.

If you wait a year, IMO you’ll be too late if you have any competitors in your business domain. AI coding is as much of a mindset as it is a modification of status quo software engineering.

From my experience as a senior, staff level engineer, coding with AI agents very much can do “X” in many cases, though certainly not all. And when it doesn’t do X well currently, I’ve found you can often guide it to better results. The technology continues to improve rapidly.

I’ve been doing extensive AI coding over the last several months (Anthropic Claude Code, OpenAI Codex CLI), including working on my own web-based “mini Google Docs replacement” service that lets you bring your own notes in and out of ChatGPT, Claude Desktop, Claude Code and Codex via MCP so that you always maintain control over your own work.

Purposefully, I have not touched a line of code in that project to see if I can bring it all the way to production without significant intervention with manual coding.

But stepping back from the specific “production level code” end product, if you’re A/B testing features with test groups, AI coding speeds up the iteration process for product teams considerably. If it is a POC or MVP, a little imperfection in the code is fine as long as you have guardrails that cover you and security and basic performance. You can put those in place and build some of that into automated PR reviews.

While the jury may still be out on the production viability of a 100% AI coded app, adapting our thinking around the evolution of coding seems increasingly important.

Anecdotally, the piece by Ethan Mollick that I read that inspired this post, is on the money:

The lack of a consensus about how to reconstruct coding workflows around AI isn't helping. This same issue will soon plague every enterprise discussion as "using AI" can stand-in for "having a dumb model do the work," or "having a smart model do the work," or "using co-intelligence along with an expert."