Building a POS and CRM for Pakistani Local Businesses with Claude

Text Post · v1 of 1

Post body

Most local shops in Pakistan still run on a register and a notebook. I want to change that — and I'm building the software with AI doing most of the heavy lifting.

Here's the plan for our new POS and CRM for local businesses.

I'm not opening Claude Code first. That's the mistake I see people make — they jump straight to generating code and then spend a week untangling decisions the AI made for them.

So we go in order:

First, architecture planning. What tables, what flows, how a shopkeeper actually moves through a sale. This part is human-led. AI is bad at knowing what a Lahore kiryana store needs — I'm not.

Then Claude for the UI mockups. Fast, cheap, and good enough to react to before anything is built.

Only then Claude Code to build it out, section by section, against the architecture we already agreed on.

The thing I've learned across client projects: AI is brilliant at execution and weak at judgment. When you feed it a clear plan, it flies. When you ask it to decide, it guesses confidently and you pay for it later.

We're at the start of this one, so I'll share what breaks as we go.

For those of you building with Claude Code — do you plan the architecture by hand first, or let the model propose it and correct from there?

Hook variants — tap to swap in

Reviewer note: Repeated Idea

Live lint — Layer 1

Clean.

Layer 2 — LLM judgment (from last save)

warn · 5. Describes unresolved ongoing problem rather than settled lesson

The post is about a project just starting ('We're at the start of this one, so I'll share what breaks as we go'), so the specific project outcome is genuinely unresolved. However, the core takeaway (AI is strong at execution, weak at judgment; plan architecture by hand first) is presented as a settled, generalizable lesson, which keeps this on the right side of the line.

Acceptable as-is because the lesson is settled. If you want to fully de-risk, make the 'work-in-progress' framing clearly a deliberate build-in-public choice rather than an unresolved struggle — the current wording already does this well.

warn · 9. Hype words, consultant-speak, or salesy tone

Mostly grounded, but a few mild hype phrases: 'AI doing most of the heavy lifting' and 'it flies' lean slightly promotional. Not egregious, but worth tightening.

Optional rewrite: change 'with AI doing most of the heavy lifting' to 'with AI handling a lot of the build' and 'When you feed it a clear plan, it flies' to 'When you feed it a clear plan, it moves fast.' Keeps the grounded, non-salesy tone.