# I Built a Language Where AI Calls Are Sandboxed by Default

> Source: <https://dev.to/harry_machura_67442b7a2ab/i-built-a-language-where-ai-calls-are-sandboxed-by-default-3eg0>
> Published: 2026-08-03 09:48:25+00:00

Last month I needed a script that reads server logs, classifies errors with an LLM, summarizes them, and writes a report. In Python, it looked like this:

`asyncio.gather()`

because sequential calls took 8 seconds`exec`

and file writes`requirements.txt`

always breaks on the server**80 lines later**, it worked. But it felt wrong. I wasn't building logic — I was plumbing.

So I asked myself: *What if AI operations were language primitives, not library calls?*

Pipe is a small runtime (~10 MB, single binary, zero dependencies) that treats `summarize`

, `translate`

, `classify`

, and `ask`

as first-class citizens — on the same level as `+`

, `sort`

, or `len`

.

Try it

Browser Playground (WASM, no install): pipe-lang.com

Source: github.com/MachuraHarry/pipe

Docs: pipe-lang.com/docs