Why is structured output useful?
PICTURE THIS: AN LLM TURN
Simple meaning
Downstream code needs fields it can parse, not a paragraph.
WHY — Function calling instead of guessing?
Why interviewers care about Function calling:
on Function calling.
the situation, the default choice, and one exception - that reads as experience.
Name the idea, why it exists, then one short example.
End with when you use it and one common pitfall.
STEPS — What happens with tokens?
Before the model can read a sentence, it goes through these steps:
- 1Downstream code needs fields
it can parse, not a paragraph.
- 2JSON mode, schemas, and
tool arguments reduce brittle string scraping.
- 3Structured output is how
you connect LLMs to products safely.
- 4Context mix
Attention looks at nearby tokens together.
- 5Next token
The model scores what should come next.
- 6Decode
IDs turn back into readable text.
EXAMPLE — See it in action
Let's see how a real sentence is tokenized (tokens may vary by model):
Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).
Key takeaway
Downstream code needs fields it can parse, not a paragraph. JSON mode, schemas, and tool arguments reduce brittle string scraping.