The Guides

Guides are the cornerstone content of Ask Good Questions.

Longer, structured pieces designed to stay relevant over time. Each guide focuses on a core idea, framework, or decision model that helps you use AI more deliberately.

These are not prompt tricks. They are frameworks for thinking clearly about how you use AI in real work.

Don't Pave the Cow Paths

August 20, 2026 · Charles Edmonds
One of the easiest mistakes in software modernization is also one of the oldest. We take an existing process, application, or workflow and ask how to reproduce it with newer technology. A manual proce…
Read more

Why Being the Programmer in Charge Still Matters

August 13, 2026 · Charles Edmonds
AI keeps getting better at writing code. That’s good news. It can inspect a problem, trace through existing code, propose a solution, write the implementation, run tests, find mistakes, and come back …
Read more

The Past Is Part of the Specification

August 6, 2026 · Charles Edmonds
Most software testing begins in the present. We install the current build. We create a new project, document, database, or configuration file. We exercise the new feature. We confirm that the informat…
Read more

Roll with the Flow

July 31, 2026
A few weeks ago, I wrote about the importance of trying failed AI experiments again. The point was simple: if you asked an AI to do something several weeks or several months ago and it couldn't do it,…
Read more

A Failed AI Experiment Isn't a Final Answer

July 23, 2026
Someone tries an AI model, asks it to do something useful, and doesn't like the answer. Maybe the writing is bland. Maybe the code doesn't compile. Maybe the model misunderstands the assignment, ignor…
Read more

And One More Thing

July 23, 2026
There’s a dangerous little phrase in AI-assisted programming. “And one more thing.” It sounds harmless. You’re already in the thread. The AI already knows the project. It’s seen the last bug, the curr…
Read more

Make the AI Show Its Receipts

July 23, 2026
One of the easiest mistakes to make with AI-assisted programming is also one of the most expensive. You ask the AI to fix something. It sounds confident. It names plausible files. It explains a reason…
Read more

The Model Is Not the Method

July 16, 2026 · Charles Edmonds
People spend a lot of time asking which AI is best at coding. Is Claude better than ChatGPT? Is ChatGPT catching up? Is one better at architecture while another is better at debugging? Does one produc…
Read more

Let the Big Dog Run

July 9, 2026 · Charles Edmonds
A lot of programmers underuse AI because they’re afraid of the wrong thing. They know AI can make mistakes. They know it can guess. They know it can drift away from the existing design, patch the wron…
Read more

Keep the Build Thread Clean

June 17, 2026 · Charles Edmonds
One of the easiest ways to make AI less useful on a real project is to keep asking one thread to do every job. You're in the middle of building something. The coding thread is moving along well. The A…
Read more

The Moving Target

June 12, 2026 · Charles Edmonds
One of the easiest mistakes to make in AI-assisted development is assuming the target stays fixed just because the feature list does. At first, the moving target may look like the specification itself…
Read more

Stop, Drop, and Roll

June 4, 2026 · Charles Edmonds
Sometimes the problem isn't the code. Sometimes the problem is the conversation. That's one of those things that sounds obvious after you've been burned by it, but it's not obvious while you're in the…
Read more

Do Not Let AI Build the Elephant in the Room

May 28, 2026 · Charles Edmonds
AI usually doesn't build the elephant in one move. That's the dangerous part. A project starts out with good intentions. The file structure makes sense. The responsibilities seem pretty clear. You've …
Read more

You Have to Invite the Vampire In

May 20, 2026
You've seen the scene in every vampire movie. The vampire is standing outside the door, asking to be invited in. The person inside hesitates. The vampire seems calm enough. Reasonable enough. Maybe ev…
Read more

The Blue Water Design

May 13, 2026
One of the most useful shifts I've made in working with AI didn't come from a better prompt. It came from changing the assignment. Early on, like a lot of developers, I would describe the kind of appl…
Read more

The Patch Trap

May 6, 2026 · Charles Edmonds
When people first start using AI to help with code, one pattern shows up almost immediately. You ask for a fix, and the AI comes back with something like this: Replace this block. Add this line below …
Read more

When Account Recovery Becomes Privacy Surrender

April 28, 2026 · Charles Edmonds
Security matters. There is no serious argument otherwise. If a platform believes an account may have been compromised, it should act carefully and protect the user. But in today's environment, another…
Read more

The Hidden Cost of Magic

April 21, 2026 · Charles Edmonds
AI is very good at making hard things feel easy. You ask for something complex and get something useful back almost immediately. Code. Documentation. A plan. A workflow. A working feature. Sometimes s…
Read more

The AI Junk Drawer Problem

April 16, 2026 · Charles Edmonds
One of the easiest ways to make AI less effective is to keep helping it without ever cleaning up. A rule here. A reminder there. A style note. A project file. A lessons-learned document. A copied bloc…
Read more

When AI Defaults to Newer, Better, Faster

April 7, 2026 · Charles Edmonds
If you work with AI long enough, you begin to notice a pattern that is easy to miss at first. When a task is under-specified, AI tends to lean toward what looks like progress. A newer library. A clean…
Read more

Losing the Big Picture

March 13, 2026 · Charles Edmonds
If you work with AI long enough, you will eventually run into a frustrating pattern: the code is improving, but the design is getting harder to reason about. It usually happens one fix at a time. You …
Read more

Choosing AI by Workflow, Not by Benchmark

February 13, 2026 · Charles Edmonds
If you hang around AI discussions long enough, you will notice something predictable. Every debate eventually turns into benchmarks. Which model scored higher. Which one reasons better. Which one has …
Read more