Stand-in model

A stand-in model is a plain Python function that answers the way a language model does, so a program can be built and tested with no API key.

Last updated: 30 Sep, 2026 · Python 3.14

A real model needs an API key and charges for every call. For learning, a function that answers in the same shape is free, instant and easy to read. It uses Functions and JSON.

Writing ask_model

A model asked to sort a ticket as JSON sends back a string. Usually it is the JSON you asked for. Sometimes it is a polite sentence instead. The stand-in does both:

def ask_model(ticket_text):
    text = ticket_text.lower()
    if "charged" in text or "refund" in text:
        return '{"category": "billing", "priority": 4}'
    if "parcel" in text or "arrived" in text:
        return '{"category": "shipping", "priority": 3}'
    return "I am not sure how to sort this one."

print(ask_model("I was charged twice for one order"))
print(ask_model("How do I change my password?"))

{"category": "billing", "priority": 4}
I am not sure how to sort this one.

It returns strings, not dictionaries, because that is what arrives from a real model: text, which your program then has to read. It decides from the words in the ticket, so a different ticket gets a different answer.

[
  {
    "id": 1,
    "customer": "Asha",
    "text": "I was charged twice for one order"
  },
  {
    "id": 2,
    "customer": "Ben",
    "text": "My parcel has not arrived"
  },
  {
    "id": 3,
    "customer": "Chen",
    "text": "Can I get a refund for the blue mug?"
  },
  {
    "id": 4,
    "customer": "Dara",
    "text": "How do I change my password?"
  },
  {
    "id": 5,
    "customer": "Eli",
    "text": "The parcel arrived but the box was crushed"
  }
]

Asking about every ticket

This reads tickets.json from JSON; keep that file in the same folder as your code.

import json

with open("tickets.json") as f:
    tickets = json.load(f)

for ticket in tickets:
    answer = ask_model(ticket["text"])
    print(ticket["id"], answer)

1 {"category": "billing", "priority": 4}
2 {"category": "shipping", "priority": 3}
3 {"category": "billing", "priority": 4}
4 I am not sure how to sort this one.
5 {"category": "shipping", "priority": 3}

Four answers are JSON and ticket 4's is not. Real models do this too, which is why a program that trusts every answer eventually breaks.

Parsing every answer, and where it breaks

for ticket in tickets:
    data = json.loads(ask_model(ticket["text"]))
    print(ticket["id"], data["category"])

1 billing
2 shipping
3 billing
Traceback (most recent call last):
  File "main.py", line 2, in <module>
    data = json.loads(ask_model(ticket["text"]))
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

Tickets 1 to 3 print, then ticket 4's sentence reaches json.loads and the whole program stops. On your computer the error also lists lines from inside the json module; the last line is the one to read. Ticket 5 is never sorted. try and except keeps the program running.

Stand-in vs a real model

Where stand-ins show up in AI code

• Tests that must run the same way every time, with no key.
• Building the rest of a program before a model account exists.
• The stand-in models the agent framework courses write, which follow the same idea.

Related

• Previous: JSON
• Next: try and except