Prompt Engineering

Algorithm Explanation Prompt — Idea, Steps, Complexity, Tradeoffs

Explain the idea before the implementation: numbered steps with their contribution, honest best/worst-case complexity, and the alternatives each decision point rejected.

Overview

Algorithm explanations fail in two directions: pure narration (restating each line) or pure theory (lecturing about the general algorithm while ignoring this implementation). This prompt demands both halves connected: the approach and why it fits the problem, the logic in numbered steps with what each contributes, complexity analyzed honestly — time and space, best and worst case, and which input shapes trigger the worst — and the tradeoffs named: what this algorithm gives up for what it gains. One concrete input gets traced through the whole thing, state shown after each step. The loaded setup carries a real token-bucket rate limiter to break down.

Workflow

Idea before implementation
What approach this is and why it fits the problem — before any line gets discussed.
Trace one concrete input
Real values walk the whole algorithm, with the state shown after each step.
Name the tradeoffs
Memory for speed, precision for simplicity — and at each decision point, the alternative that lost.

Why This Works

Idea-first ordering builds the mental model the steps then fill
A concrete trace catches misunderstandings abstract description hides
Worst-case honesty is what makes the analysis usable in production decisions

Best for

Algorithm-bearing code inherited without explanation
Performance-sensitive code whose behavior at scale matters
Developers strengthening algorithmic intuition on real code

Not for

Making the algorithm faster — that's the Refactor Prompt Builder's Performance goal
Diagnosing why it produces wrong results — that's the Debugging Prompt Generator

Use cases

Breaking down a rate limiter, cache policy, or scheduling routine
Understanding the complexity profile before scaling
Learning when to use this algorithm — and when not to

Customize This Resource

Opens this setup in Code Explanation Prompt. Generate to get the full understanding contract — then adjust the mode, audience, and depth.

Open in Code Explanation Prompt

Prompt Template

EXPLANATION OBJECTIVE
Break down this rate-limiting algorithm: how it works, its complexity, and its tradeoffs.
Explanation mode: algorithm breakdown — step-by-step logic, complexity, tradeoffs, and decision points.
The goal is understanding, not judgment: explain what this code does and why it is built this way — and clearly separate what the code shows from what you infer.

CODE CONTEXT
System context: Guards a public API; called on every request.
Code to explain:
```
function allow(key) {
  var b = buckets.get(key);
  var now = Date.now();
  if (!b) { b = { tokens: CAPACITY, last: now }; buckets.set(key, b); }
  var elapsed = (now - b.last) / 1000;
  b.tokens = Math.min(CAPACITY, b.tokens + elapsed * REFILL_RATE);
  b.last = now;
  if (b.tokens >= 1) { b.tokens -= 1; return true; }
  return false;
}
```

AUDIENCE PROFILE
Audience: a mid-level developer — fluent in the language and common patterns.
- Assume: language features and common patterns are known; this codebase's conventions and domain are not.
- Skip syntax explanations entirely; spend the depth on intent, structure, and domain meaning.

EXPLANATION STRATEGY
1. Explain the idea before the implementation: what approach this algorithm takes and why that approach fits the problem.
2. Break the logic into numbered steps; for each, state what it contributes to the result.
3. Analyze complexity honestly: time and space, best and worst case, and which input shapes trigger the worst case.
4. Name the tradeoffs: what this algorithm gives up — memory, precision, simplicity — for what it gains.
- Depth: deep dive — behavior, rationale, and the decisions behind the structure.
- For every significant design decision: the rationale, the tradeoffs accepted, and at least one alternative approach with why it likely lost.
- Surface the assumptions the design rests on — and what would break if each assumption stopped holding.
- Where rationale cannot be recovered from the code, say so explicitly — do not fabricate a design story.

KEY CONCEPTS
- Define the algorithmic concepts in play — the invariant, the data structure, the termination condition — before using them.
- Order concepts by how load-bearing they are for understanding this code — not by where they appear in the file.

EXECUTION FLOW
- Trace one concrete input through the whole algorithm, showing the state after each step.
- Where the flow depends on state or configuration, say which, and what each setting changes.

DESIGN DECISIONS
- At each decision point in the implementation, name the alternative not taken and the likely reason it lost.
- Discuss only decisions actually visible in the code; rationale you cannot evidence belongs under ASSUMPTIONS, labeled as inference.

ASSUMPTIONS
- Separate what the code DOES (verifiable from the source) from why it might be that way (inference).
- Label every statement about intent, history, or rationale as an INFERENCE unless the code itself evidences it — a comment, a test, a telling name.
- Where behavior cannot be determined from the provided code, say "cannot be determined from this code" — never fill the gap with a plausible story.

TRADEOFFS
- For each significant tradeoff: what was gained, what was given up, and the alternative that would invert it.
- Evaluate whether each tradeoff still makes sense today, or whether the constraint that justified it has expired.

LEARNING NOTES
- Close with when to reach for this algorithm — and when its tradeoffs make something else the better choice.

NON-GOALS
- Do not review code quality — no findings, no severities, no verdicts.
- Do not debug failures — explain the behavior that exists without diagnosing it.
- Do not refactor the code or propose rewrites.
- Do not generate tests.
- Do not invent requirements or unstated intentions.
- If something looks defective, note it as a question for the team — investigating or fixing it is out of scope.
- Clearly separate facts from assumptions throughout.

OUTPUT REQUIREMENTS
- Structure the explanation with headings that mirror the sections above — a reader should be able to navigate it without reading all of it.
- Anchor every claim about behavior in the code: name the function, branch, or line it comes from when precision matters.
- Calibrate every section to the stated audience — too basic wastes their time, too advanced loses them.
- End with the open questions: what could not be determined from the provided code, and who or what could answer it.

Related Resources

Explore more resources that work well with this one.