liveBook · Manning

Context cue

As explained in Coding with AI

A prompting technique that supplies hints or surrounding information to steer a model toward an appropriate approach.

A context cue is a prompting technique that supplies guidance about which approach the model should use. It belongs in an iterative workflow: refine the prompt, try multiple methods, and compare the results rather than trusting one generated answer. Cues can narrow the model toward a more appropriate technique, but they do not remove the stochastic behavior of language models. section 9.4.5

Use context cues alongside other refinement steps:

  • Make the instruction increasingly specific. section 9.4.5
  • Try several methods instead of relying on one formulation. section 9.4.5
  • Ask the model to show its work when a process needs examination. section 9.4.5

How Coding with AI covers it

How deep it goes
Defines the technique and places it within refinement steps, but stops short of detailed cue design or implementation.
Examples
Uses increasingly specific prompts, alternative methods, and requests to show work as refinement practices.
What it assumes
Assumes basic prompting familiarity and introduces context cues as one step among several prompt-refinement methods.
What you can do after
Apply context cues within iterative prompts to narrow model responses toward a more suitable approach.
How it connects
Connects context cues with prompt engineering, explicit instructions, multiple methods, and showing work.
Cover of Coding with AI
liveBookmanning.com
Read Coding with AI on liveBook Get the book at manning.com

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