Skip to content
The AI Tech Lead Path
The path
0213 min read · 160 XP

Prompt & context engineering

Treat the context window as an engineered input, not a wish.

0%

The most leveraged daily skill: shaping what goes into the model. Prompting is the surface; context engineering — deciding what information, tools and structure enter the window — is the real discipline. Teams will bring you their broken prompts, so own this cold.

Key ideas

  1. 1

    Context engineering > prompt wording: the biggest wins come from giving the model the right information, examples and tools — not clever phrasing.

  2. 2

    Use structure: clear roles (system vs user), explicit instructions, delimiters, and ask for structured output (JSON / tool calls) when you'll parse the result.

  3. 3

    Few-shot examples beat adjectives. Show 2–5 representative examples instead of describing what you want.

  4. 4

    Mind the window: models degrade with very long context ('lost in the middle') — put the most important instructions at the start and end, and prune irrelevant tokens.

  5. 5

    Decompose hard tasks into steps/chains; let the model 'think' before answering for reasoning tasks; cache stable prefixes to cut cost and latency.

What actually moves quality

  • Right information in context (retrieved facts, schemas, examples) — usually the #1 lever.
  • Clear task framing: role, goal, constraints, output format, and what to do when unsure.
  • Few-shot examples that match the real distribution of inputs.
  • Output contracts: structured output / tool calling so downstream code is reliable.

Engineering practices

  • Version prompts like code; never tweak a production prompt without an eval (see the Evaluation chapter).
  • Prompt caching for stable system prompts / long shared context to cut cost & latency.
  • Decomposition & chaining for complex tasks; reserve 'reasoning' for problems that need it.
  • Defend against prompt injection when prompts include untrusted/retrieved text (see AI Security).

Watch

AI prompt engineering: a deep diveAnthropic
Prompting 101Code w/ Claude · Anthropic

Do the work

0/4 · 0%

Test yourself

Question 1 / 4

What usually gives the biggest quality improvement?

27 chapters · progress saves automatically