# Compile for coding agents: A-ISL (experimental)

> Source: <https://dev.to/francesco_marconi_282058b/compile-for-coding-agents-a-isl-experimental-2djh>
> Published: 2026-11-02 12:21:16+00:00

I got tired of two extremes: **one-shot prompts** that disappear into the chat, and **hand-written specs** nobody maintains.

**A-ISL** is an experiment in the middle: you describe the product in natural language; a coding agent writes a **reviewable Spec** in classic [ISL](https://github.com/fra00/isl-specification) (`.isl.md`); you accept it; then you **explicitly** ask another skill to **compile** that Spec into `bin-<stack>/` (React, Blazor, WinForms, C# library, …).

You do **not** hand-author ISL or the app.

`a-isl-spec-author``*.isl.md` only
`a-isl-compile`` bin-<stack>/` via a small runtime (builder → queue → packet → lock)
Spec never auto-chains into `bin/`. That’s the whole point: **human gate**, not autopilot.

Same Spec can compile to more than one stack without rewriting intent — see the [sheet demo](https://github.com/fra00/a-isl-agents/tree/main/examples/sheet-workspace) (React / Blazor / WinForms).

A-ISL does **not** invent the product. You decide behavior and accept the Spec. Wrong Spec that compiles is still “faithful.” That boundary is intentional.

Internal bench (`tariffe-v2`, closed Domain/Logic rules, N=5):

| Campaign | Stack | First full-pass | Final | 
|---|---|---|---|
| A-ISL | react-js | 5/5 | 5/5 | 
| Single prompt | react-js | 5/5 | 5/5 | 
| A-ISL | csharp | 5/5 | 5/5 | 
| Prompt (open DTO style) | csharp | **1/5** | 5/5 | 
| Prompt + same “prefer records” rule | csharp | **5/5** | 5/5 | 

**Regression check, not a leaderboard.** On a small closed-rules task, Spec → Compile matches a single prompt (5/5 vs 5/5 on JS). On C#, a prompt that left DTO style open dropped to 1/5 on first pass; adding the same “prefer records” rule closed the gap. The expected payoff is on **large or multi-module projects** and on **change-via-Spec**. This bench does not demonstrate that; it only supports non-regression on a small closed oracle.

Full honesty: [evaluation.md](https://github.com/fra00/a-isl-agents/blob/main/docs/evaluation.md).

Runtime is agent-agnostic. Skills ship for Cursor, Claude Code, and GitHub Copilot (same text, synced). Day-to-day use and the bench were on **Cursor**; other hosts are not separately tested yet.

Modules, evolution via Spec, multi-stack. For a one-shot script, a normal prompt is enough — Spec→Compile costs more turns on purpose.

**Prerequisites:** Node.js 18+; for Blazor / WinForms sheet demos, a .NET SDK (WinForms needs Windows targeting).

```
git clone https://github.com/fra00/a-isl-agents.git
cd a-isl-agents && npm install && npm --prefix runtime/lint install
# open in your agent → /a-isl-spec-author → review → /a-isl-compile
```

Tutorial: [docs/tutorial-first-project.md](https://github.com/fra00/a-isl-agents/blob/main/docs/tutorial-first-project.md)