Builders are doing unimaginable issues with AI. Instruments like Copilot, ChatGPT, and Claude have quickly change into indispensable for builders, providing unprecedented pace and effectivity in duties like writing code, debugging tough habits, producing assessments, and exploring unfamiliar libraries and frameworks. When it really works, it’s efficient, and it feels extremely satisfying.
However should you’ve spent any actual time coding with AI, you’ve most likely hit some extent the place issues stall. You retain refining your immediate and adjusting your method, however the mannequin retains producing the identical form of reply, simply phrased just a little in another way every time, and returning slight variations on the identical incomplete resolution. It feels shut, however it’s not getting there. And worse, it’s not clear find out how to get again on observe.
That second is acquainted to lots of people making an attempt to use AI in actual work. It’s what my latest discuss at O’Reilly’s AI Codecon occasion was all about.
During the last two years, whereas engaged on the newest version of Head First C#, I’ve been creating a brand new form of studying path, one which helps builders get higher at each coding and utilizing AI. I name it Sens-AI, and it got here out of one thing I stored seeing:
There’s a studying hole with AI that’s creating actual challenges for people who find themselves nonetheless constructing their growth abilities.
My latest O’Reilly Radar article “Bridging the AI Studying Hole” checked out what occurs when builders attempt to study AI and coding on the identical time. It’s not only a tooling downside—it’s a considering downside. Numerous builders are figuring issues out by trial and error, and it grew to become clear to me that they wanted a greater method to transfer from improvising to really fixing issues.
From Vibe Coding to Downside Fixing
Ask builders how they use AI, and lots of will describe a form of improvisational prompting technique: Give the mannequin a activity, see what it returns, and nudge it towards one thing higher. It may be an efficient method as a result of it’s quick, fluid, and virtually easy when it really works.
That sample is frequent sufficient to have a reputation: vibe coding. It’s an incredible place to begin, and it really works as a result of it attracts on actual immediate engineering fundamentals—iterating, reacting to output, and refining primarily based on suggestions. However when one thing breaks, the code doesn’t behave as anticipated, or the AI retains rehashing the identical unhelpful solutions, it’s not at all times clear what to attempt subsequent. That’s when vibe coding begins to collapse.
Senior builders have a tendency to select up AI extra shortly than junior ones, however that’s not a hard-and-fast rule. I’ve seen brand-new builders decide it up shortly, and I’ve seen skilled ones get caught. The distinction is in what they do subsequent. The individuals who succeed with AI are likely to cease and rethink: They work out what’s going fallacious, step again to take a look at the issue, and reframe their immediate to provide the mannequin one thing higher to work with.
The Sens-AI Framework
As I began working extra intently with builders who had been utilizing AI instruments to attempt to discover methods to assist them ramp up extra simply, I paid consideration to the place they had been getting caught, and I began noticing that the sample of an AI rehashing the identical “virtually there” recommendations stored developing in coaching periods and actual initiatives. I noticed it occur in my very own work too. At first it felt like a bizarre quirk within the mannequin’s habits, however over time I spotted it was a sign: The AI had used up the context I’d given it. The sign tells us that we want a greater understanding of the issue, so we may give the mannequin the knowledge it’s lacking. That realization was a turning level. As soon as I began taking note of these breakdown moments, I started to see the identical root trigger throughout many builders’ experiences: not a flaw within the instruments however a scarcity of framing, context, or understanding that the AI couldn’t provide by itself.
Over time—and after loads of testing, iteration, and suggestions from builders—I distilled the core of the Sens-AI studying path into 5 particular habits. They got here instantly from watching the place learners bought caught, what sorts of questions they requested, and what helped them transfer ahead. These habits kind a framework that’s the mental basis behind how Head First C# teaches builders to work with AI:
- Context: Being attentive to what data you provide to the mannequin, making an attempt to determine what else it must know, and supplying it clearly. This contains code, feedback, construction, intent, and anything that helps the mannequin perceive what you’re making an attempt to do.
- Analysis: Actively utilizing AI and exterior sources to deepen your individual understanding of the issue. This implies working examples, consulting documentation, and checking references to confirm what’s actually happening.
- Downside framing: Utilizing the knowledge you’ve gathered to outline the issue extra clearly so the mannequin can reply extra usefully. This entails digging deeper into the issue you’re making an attempt to unravel, recognizing what the AI nonetheless must learn about it, and shaping your immediate to steer it in a extra productive path—and going again to do extra analysis whenever you understand that it wants extra context.
- Refining: Iterating your prompts intentionally. This isn’t about random tweaks; it’s about making focused modifications primarily based on what the mannequin bought proper and what it missed, and utilizing these outcomes to information the following step.
- Vital considering: Judging the standard of AI output slightly than simply merely accepting it. Does the suggestion make sense? Is it right, related, believable? This behavior is very vital as a result of it helps builders keep away from the entice of trusting confident-sounding solutions that don’t really work.
These habits let builders get extra out of AI whereas preserving management over the path of their work.
From Caught to Solved: Getting Higher Outcomes from AI
I’ve watched loads of builders use instruments like Copilot and ChatGPT—throughout coaching periods, in hands-on workouts, and once they’ve requested me instantly for assist. What stood out to me was how usually they assumed the AI had performed a nasty job. In actuality, the immediate simply didn’t embody the knowledge the mannequin wanted to unravel the issue. Nobody had proven them find out how to provide the best context. That’s what the 5 Sens-AI habits are designed to deal with: not by handing builders a guidelines however by serving to them construct a psychological mannequin for find out how to work with AI extra successfully.
In my AI Codecon discuss, I shared a narrative about my colleague Luis, a really skilled developer with over three many years of coding expertise. He’s a seasoned engineer and a sophisticated AI person who builds content material for coaching different builders, works with giant language fashions instantly, makes use of refined prompting methods, and has constructed AI-based evaluation instruments.
Luis was constructing a desktop wrapper for a React app utilizing Tauri, a Rust-based toolkit. He pulled in each Copilot and ChatGPT, cross-checking output, exploring alternate options, and making an attempt totally different approaches. However the code nonetheless wasn’t working.
Every AI suggestion appeared to repair a part of the issue however break one other half. The mannequin stored providing barely totally different variations of the identical incomplete resolution, by no means fairly resolving the problem. For some time, he vibe-coded by it, adjusting the immediate and making an attempt once more to see if a small nudge would assist, however the solutions stored circling the identical spot. Ultimately, he realized the AI had run out of context and adjusted his method. He stepped again, did some centered analysis to raised perceive what the AI was making an attempt (and failing) to do, and utilized the identical habits I emphasize within the Sens-AI framework.
That shift modified the end result. As soon as he understood the sample the AI was making an attempt to make use of, he may information it. He reframed his immediate, added extra context, and eventually began getting recommendations that labored. The recommendations solely began working as soon as Luis gave the mannequin the lacking items it wanted to make sense of the issue.
Making use of the Sens-AI Framework: A Actual-World Instance
Earlier than I developed the Sens-AI framework, I bumped into an issue that later grew to become a textbook case for it. I used to be curious whether or not COBOL, a decades-old language developed for mainframes that I had by no means used earlier than however needed to study extra about, may deal with the essential mechanics of an interactive recreation. So I did some experimental vibe coding to construct a easy terminal app that will let the person transfer an asterisk across the display utilizing the W/A/S/D keys. It was a bizarre little aspect mission—I simply needed to see if I may make COBOL do one thing it was by no means actually meant for, and study one thing about it alongside the best way.
The preliminary AI-generated code compiled and ran simply nice, and at first I made some progress. I used to be capable of get it to clear the display, draw the asterisk in the best place, deal with uncooked keyboard enter that didn’t require the person to press Enter, and get previous some preliminary bugs that precipitated loads of flickering.
However as soon as I hit a extra refined bug—the place ANSI escape codes like ";10H" had been printing actually as a substitute of controlling the cursor—ChatGPT bought caught. I’d describe the issue, and it will generate a barely totally different model of the identical reply every time. One suggestion used totally different variable names. One other modified the order of operations. A couple of tried to reformat the STRING assertion. However none of them addressed the foundation trigger.
The sample was at all times the identical: slight code rewrites that regarded believable however didn’t really change the habits. That’s what a rehash loop seems to be like. The AI wasn’t giving me worse solutions—it was simply circling, caught on the identical conceptual concept. So I did what many builders do: I assumed the AI simply couldn’t reply my query and moved on to a different downside.
On the time, I didn’t acknowledge the rehash loop for what it was. I assumed ChatGPT simply didn’t know the reply and gave up. However revisiting the mission after creating the Sens-AI framework, I noticed the entire trade in a brand new gentle. The rehash loop was a sign that the AI wanted extra context. It bought caught as a result of I hadn’t informed it what it wanted to know.
Once I began engaged on the framework, I remembered this previous failure and thought it’d be an ideal take a look at case. Now I had a set of steps that I may observe:
- First, I acknowledged that the AI had run out of context. The mannequin wasn’t failing randomly—it was repeating itself as a result of it didn’t perceive what I used to be asking it to do.
- Subsequent, I did some focused analysis. I brushed up on ANSI escape codes and began studying the AI’s earlier explanations extra fastidiously. That’s once I observed a element I’d skimmed previous the primary time whereas vibe coding: Once I went again by the AI rationalization of the code that it generated, I noticed that the
PIC ZZCOBOL syntax defines a numeric-edited subject. I suspected that might probably trigger it to introduce main areas into strings and puzzled if that might break an escape sequence. - Then I reframed the issue. I opened a brand new chat and defined what I used to be making an attempt to construct, what I used to be seeing, and what I suspected. I informed the AI I’d observed it was circling the identical resolution and handled that as a sign that we had been lacking one thing elementary. I additionally informed it that I’d performed some analysis and had three leads I suspected had been associated: how COBOL shows a number of objects in sequence, how terminal escape codes have to be formatted, and the way spacing in numeric fields may be corrupting the output. The immediate didn’t present solutions; it simply gave some potential analysis areas for the AI to analyze. That gave it what it wanted to seek out the extra context it wanted to interrupt out of the rehash loop.
- As soon as the mannequin was unstuck, I refined my immediate. I requested follow-up inquiries to make clear precisely what the output ought to appear to be and find out how to assemble the strings extra reliably. I wasn’t simply in search of a repair—I used to be guiding the mannequin towards a greater method.
- And most of all, I used crucial considering. I learn the solutions intently, in contrast them to what I already knew, and determined what to attempt primarily based on what really made sense. The reason checked out. I carried out the repair, and this system labored.
As soon as I took the time to know the issue—and did simply sufficient analysis to provide the AI just a few hints about what context it was lacking—I used to be capable of write a immediate that broke ChatGPT out of the rehash loop, and it generated code that did precisely what I wanted. The generated code for the working COBOL app is on the market in this GitHub GIST.
Why These Habits Matter for New Builders
I constructed the Sens-AI studying path in Head First C# across the 5 habits within the framework. These habits aren’t checklists, scripts, or hard-and-fast guidelines. They’re methods of considering that assist folks use AI extra productively—they usually don’t require years of expertise. I’ve seen new builders decide them up shortly, generally quicker than seasoned builders who didn’t understand they had been caught in shallow prompting loops.
The important thing perception into these habits got here to me once I was updating the coding workouts in the latest version of Head First C#. I take a look at the workouts utilizing AI by pasting the directions and starter code into instruments like ChatGPT and Copilot. In the event that they produce the proper resolution, meaning I’ve given the mannequin sufficient data to unravel it—which suggests I’ve given readers sufficient data too. But when it fails to unravel the issue, one thing’s lacking from the train directions.
The method of utilizing AI to check the workouts within the ebook jogged my memory of an issue I bumped into within the first version, again in 2007. One train stored tripping folks up, and after studying loads of suggestions, I spotted the issue: I hadn’t given readers all the knowledge they wanted to unravel it. That helped join the dots for me. The AI struggles with some coding issues for a similar cause the learners had been scuffling with that train—as a result of the context wasn’t there. Writing coding train and writing immediate each rely upon understanding what the opposite aspect must make sense of the issue.
That have helped me understand that to make builders profitable with AI, we have to do extra than simply educate the fundamentals of immediate engineering. We have to explicitly instill these considering habits and provides builders a method to construct them alongside their core coding abilities. If we wish builders to succeed, we are able to’t simply inform them to “immediate higher.” We have to present them find out how to assume with AI.
The place We Go from Right here
If AI actually is altering how we write software program—and I consider it’s—then we have to change how we educate it. We’ve made it straightforward to provide folks entry to the instruments. The more durable half helps them develop the habits and judgment to make use of them nicely, particularly when issues go fallacious. That’s not simply an training downside; it’s additionally a design downside, a documentation downside, and a tooling downside. Sens-AI is one reply, however it’s only the start. We nonetheless want clearer examples and higher methods to information, debug, and refine the mannequin’s output. If we educate builders find out how to assume with AI, we might help them change into not simply code turbines however considerate engineers who perceive what their code is doing and why it issues.
