· ·Sources
Ask the internet which AI coding tool to buy and every review measures the same thing: the flagship model tier. Almost nobody tests the question that actually decides your bill — can the budget model, given a strong agent, do real work? So this is a field report, not a vibe check. The target: a personal blog that had been running for years on Java, jQuery and Bootstrap. The job: rewrite it into a Rust backend serving hand-rolled HTML. The tool: CodeBuddy. The model: GLM-5.3-Flash. The time: one focused weekend.
| Before | After | |
|---|---|---|
| Backend | Java web app | Rust |
| Rendering | Server templates + jQuery sprinkles | Server-rendered HTML |
| CSS | Bootstrap + hand-maintained overrides | Hand-rolled, no framework |
| JS | jQuery | Vanilla, only where a page needs it |
| Static assets | 20+ MB folder: jQuery, Bootstrap, Font Awesome, wangEditor, theme files | ≈22 KB total: one stylesheet, one icon |
| Runtime memory | 500+ MB (Java process, idle) | ≈13 MB (Rust process) |
| Build time | Years of accretion | One weekend, agent-driven |
Two things to notice about that table. First, the rewrite removed frameworks, not capabilities — every page the old blog served, the new one serves. Second, nothing here is exotic: a Rust HTTP backend rendering HTML templates is a boring, well-trodden design. That boringness is the point. A rewrite is mostly scaffolding, template plumbing and style discipline — exactly the work AI agents are good at, and exactly the work that made maintaining the old site feel heavier than it should.
A rewrite has a property few software projects have: the acceptance bar already exists. The old site, page by page, defines what "done" means — same content, same links, and it should read better. That single fact changes everything about using a coding agent: you are not asking it to guess what you want, you are asking it to match something you can both see.
The work in CodeBuddy ran as a conversation over the repository. The agent could read the old code and the new tree in the same workspace, so most turns were: a directive ("set up the Rust server with these routes", "build the article template from this old page"), a pass of writes, then a review against the old page in a browser. Day one went to the skeleton — server, templates, the global stylesheet. Day two went to content pages and polish. Neither day had a long dark stretch of copying boilerplate around, which is what consumed the original build years ago.
The honest version of "it was fast": the speed did not come from the AI typing quickly. It came from skipping the parts of frontend work that are pure labor — scaffolding, template duplication, nudging CSS by three pixels until it looks right. Those went to the agent in bulk. What remained for me was judgment, which is the part I would have kept anyway.
The working assumption most people carry from chatbots is that AI code is a draft you rewrite. With a full agent harness on a task this well-defined, that assumption flipped: most pages and modules arrived correct on the first pass — markup, template logic, even the Rust plumbing. Rework happened at the edges, not in the middle. The practical consequence is bigger than the time saved: when first passes are usually right, you stop micro-reviewing and start spot-checking, and that is what makes a weekend scale to a whole site.
This was the genuine shock. Consistency was supposed to be AI's weakness — every file written by a different mood. What actually happened: the agent holds its own conventions better than I held mine. It commits to a spacing scale, a type scale and a palette early, and then — because it re-reads the global stylesheet and shared templates on every pass — it applies them with a discipline I never managed across years of patching a Bootstrap theme. The old blog drifted because I was overriding defaults I didn't control. The new one can't drift the same way: there are no defaults to fight, and the convention lives in files the agent always sees before it writes.
The aesthetic result is hard to overstate for anyone who has fought a CSS framework: the site looks like one site. Not "Bootstrap with modifications", not a patchwork of vintages — one voice, in every page, because one system produced it.
The old stack paid a framework tax on every request, and the folder it lived in told the story: more than 20 MB of static assets — jQuery, Bootstrap, Font Awesome, a wangEditor build, assorted theme files, some of it possibly referenced by nothing. The new site's entire static footprint, measured live at publication time, is the HTML, one 15.5 KB stylesheet and a 4 KB favicon — about 22 KB in total — and the homepage document itself is 2.4 KB. Nothing arrives before the text, because there is nothing left to arrive first.
The server got the same treatment. The old Java process idled above 500 MB of RAM; the Rust backend serves the same pages from about 13 MB — under 3% of the memory for the same site, and a fraction of the deployment anxiety that comes with it. This is the same philosophy this site runs on, and after living on both sides, the lightweight side isn't a compromise. It's just the same site, minus the ballast.
None of this means the agent ran unattended. My actual jobs were three:
One habit solved most disagreements cheaply: instead of hand-patching a file I didn't like, I had the agent re-read the global stylesheet and redo the page against it. Fix the convention, not the instance — the agent then keeps the fix everywhere, which is exactly what hand-patching never does.
Three rules I'd carry to the next project:
In this case, yes — with two conditions: the task had clear boundaries (migrate X to Y), and every page had a visible acceptance bar (the old site). Neither condition holds for every project, so treat this as evidence about the task shape, not a promise about the model.
An AI coding tool from Tencent — an IDE with an agent workflow that reads and writes your repository as you converse with it. See the official site for current capabilities and plans.
GLM-5.3-Flash is one of the model options inside CodeBuddy, and CodeBuddy's Free plan has been advertising all models selectable during its promotional period (checked 6 Sep 2026). Quotas and pricing change — verify against the official pricing page before you plan anything around it. We don't restate numbers we can't re-check.
The agent produced the stylesheet and every page's markup; I reviewed, adjusted direction, and made the taste calls. The hand in "hand-rolled" refers to whose conventions it follows, not whose keyboard it came from.
Static assets: from a 20+ MB folder (jQuery, Bootstrap, Font Awesome, wangEditor, theme files) to roughly 22 KB in total — one 15.5 KB stylesheet, a 4 KB favicon, and page documents that start at 2.4 KB. Server memory: from 500+ MB idling under Java to about 13 MB under Rust. Page-weight figures are reproducible from the live site's network tab; memory figures come from the author's own deployment records.
Three steps that made this one work: pick a target whose current version is its own acceptance bar; have the agent fix global conventions (spacing, type, color) before writing any page; then migrate page by page and compare against the original until the old one can be retired.
It shipped the way code should: reviewed before deployment, with me accountable for what's live. The agent wrote it faster than I would have; it did not remove my responsibility for it.
Tool and model facts on this page are traceable to these pages, checked 6 Sep 2026:
Everything else on this page is first-hand experience, not a benchmark: one project, one tool, one model version, reported as it happened. Page weights were measured from the live site on 6 Sep 2026; the memory figures come from the author's own deployment records and are not independently re-verifiable. We publish it because reviews that only test flagship tiers leave the budget-model question unanswered — and because this site itself runs on the no-framework, content-first approach described above. Tool capabilities move fast; treat this as a data point and verify current behavior against the official docs.
Transparency: links marked ref link are affiliate links — we may earn a commission if you sign up, at no extra cost to you. This never affects the comparison: the cheapest option is highlighted in green regardless of who pays us. Verify current rates before committing spend.