---
id: "prereq-prompt-engineering"
type: "prereq"
source_timestamps: ["00:00:00"]
tags: ["skills", "llm-interaction"]
related: ["concept-literal-instruction-following", "action-front-load-intent"]
reason: "Required to understand the shift from inferred intent to literal instruction following and how to adapt prompts accordingly."
sources: ["s12-opus-47"]
sourceVaultSlug: "s12-opus-47"
originDay: 12
---
# Advanced Prompt Engineering

## Prerequisite

**Advanced Prompt Engineering**

## Why It's Required

Required to understand the shift from inferred intent to literal instruction following and how to adapt prompts accordingly.

## What You Should Already Know

The speaker assumes the audience understands:

- The difference between **zero-shot**, **few-shot**, and **chain-of-thought** prompting.
- How models infer intent versus following literal instructions.
- Why ambiguity in prompts produces variability in outputs.
- Common formatting tricks (system prompts, role assignment, output schemas).

## Why It Matters for This Source

This is necessary to understand:

- Why [[entity-claude-opus-4-7-d12|Opus 4.7]]'s [[concept-literal-instruction-following|literalness]] is a significant change.
- Why [[action-front-load-intent]] is the recommended response.
- Why [[action-force-reasoning]] uses natural-language triggers as compute-allocation knobs.

## Cross-References

- Concept: [[concept-literal-instruction-following]]
- Action: [[action-front-load-intent]], [[action-force-reasoning]]
- Claim: [[claim-combative-model]]