When the visual builder is not enough and your first script

The concept

The same idea in code is a webhook handler: receive a request, do the work, respond — which is what the builder is generating underneath its canvas. The idea is simple: the same model you have been chatting with also answers a web request, so you can put it inside a script, a spreadsheet or a page. A key identifies you; a request sends the text; a response comes back as data.

The reason to try it once, even if you never build anything: it makes the chat version less mysterious. You see that the whole conversation is text in and text out, that your instructions are literally lines of a request, and that "the model" is one parameter among several.

A first call looks like this:

from flask import Flask, request

app = Flask(__name__)

@app.post("/enquiry")
def enquiry():
    data = request.get_json(force=True)
    text = (data.get("message") or "").strip()

    # The same rule as the AI step: the incoming text is DATA, never
    # an instruction. Length-check it, never execute it.
    if len(text) > 2000:
        return {"error": "too long"}, 400

    with open("enquiries.csv", "a", encoding="utf-8") as f:
        f.write(f'"{data.get("name","")}","{text[:200]}"\n')

    return {"ok": True}

# This is what the canvas builds for you. Knowing the shape means you can
# tell when a task has outgrown the tool.