liveBook · Manning

Demonstration

As explained in Context Engineering

A demonstration supplied in a model's context to guide its response to a task.

A demonstration is an example supplied in a model’s context to show the desired relationship between an input and an output. It anchors a task in a concrete pattern, helping disambiguate instructions and guide response format and content. section 2.2.1 section 6.2.1

In few-shot prompting, demonstrations precede a new input, and the model continues the pattern during inference. This is in-context learning, not an update to model weights. Examples can appear in a system prompt or a user prompt alongside task instructions and constraints; they complement an explicit output schema rather than settling every formatting decision by themselves. section 6.3.2 section 2.2.1 section 6.2.1

Capital-city pattern

A prompt pairs Spain with Madrid, Japan with Tokyo, and Canada with Ottawa. When asked for Germany’s capital, the model can continue the demonstrated question-answer pattern with Berlin. section 6.3.2

Listing 6.3 Few-shot prompting in the ticket normalizer
"role": "user", #1
"content": "Bug report:\nThe mobile app crashes when I try to upload a
20 MB PDF. It worked yesterday."

"role": "assistant", #2
"content": json.dumps({
    "title": "Crash when uploading large PDF",
    "category": "file_upload",
    "priority": "high",
    "summary": "The mobile app crashes during PDF upload when the file
    is around 20 MB.",
    "next_step": "Investigate upload limits and crash logs for the
    mobile client.",
}, indent=2)

"role": "user",
"content": "Bug report:\nSearch results on the dashboard take a long time
to load, especially in the morning."

"role": "assistant",
"content": json.dumps({
    "title": "Slow dashboard search",
    "category": "performance",
    "priority": "medium",
    "summary": "Dashboard search becomes slow, with the issue being most
    visible during morning usage.",
    "next_step": "Check query latency, indexing, and peak-time load on
    the search service.",
}, indent=2)

"role": "user", #3
"content": f"Bug report:\n{report}\n\nReturn only JSON."

A ticket normalizer uses alternating bug reports and labeled JSON responses to demonstrate a support-ticket schema before a new report is supplied. section 6.6.1

Selection and operational trade-offs:

  • For straightforward transformations, two to five demonstrations usually suffice. Each consumes tokens on every request, leaving less room for retrieved documents or conversation history. section 6.3.2
  • For dynamic few-shot prompting, embed the incoming query and retrieve relevant examples from a demonstration store. Selection fits examples to a fixed token budget, but changing prompt prefixes can reduce caching efficiency. section 6.3.2
  • Place examples within a broader prompt that also specifies the task, constraints, and output format. Stable prompt material can be placed early for caching, while the immediate request remains near the end. section 6.4.1

How Context Engineering covers it

How deep it goes
Explains few-shot inference and dynamic example retrieval, including token-budget and caching trade-offs.
Examples
Uses capital-city question-answer pairs and labeled bug reports normalized into JSON support tickets.
What you can do after
Apply few-shot prompting to guide transformations and select relevant demonstrations within a context budget.
How it connects
Connects demonstrations to in-context learning, retrieval, prompt caching, and output schemas.

Also explained in

Compare how 9 books explain demonstration →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Context Engineering. The section links point to the parts of the book it draws on.