Advanced Prompting Techniques
Decomposition, self-consistency, ReAct, tree-of-thought, persona prompting, meta-prompting, and how reasoning models change the whole calculus
The technique landscape beyond few-shot and basic chain-of-thought: breaking a task into subtasks, sampling and voting across multiple reasoning chains, interleaving reasoning with tool calls (ReAct), searching over a tree of partial solutions, when a persona measurably helps versus is theater, letting a model or optimizer write the prompt for you (DSPy and friends), and what changes once the model itself does extended, budgeted reasoning at inference time. Each technique is presented the way an interviewer expects: what it costs, what it buys, and the concrete signal that tells you it's the wrong tool for the task in front of you.
Practice questions (5)
-
View →
A Decomposed Pipeline Is Worse Than the Single Prompt It Replaced
Intermediate · Free -
View →
Sizing Self-Consistency Under a Fixed Compute Budget
Intermediate -
View →
A ReAct Agent's Grounding Broke Silently
Advanced -
View →
Should This Task Get Tree-of-Thought?
Intermediate -
View →
Migrating a Hand-Tuned CoT Prompt to a Reasoning Model
Advanced