Skip to content
sinc-LLMBook a 30-minute call

The Nyquist-Shannon Theorem Applied to AI Prompts

An exploration of the author's proposed mapping from signal sampling to prompt fields, including band design and examples.

On this page
By Mario Alexandre March 21, 2026 sinc-LLM Prompt Engineering

The Nyquist-Shannon sampling theorem has a simple rule. If you want to copy a signal perfectly, you must sample it at least twice per cycle. Shannon proved this in 1949 for phone and radio signals. The same math works for AI prompts. If you skip any part of your instructions, the AI fills in the gap with a guess. That guess is often wrong.

x(t) = Σ x(nT) · sinc((t - nT) / T)

The sinc-LLM paper presents the author’s signal-processing approach to prompts. Use that framework to inspect task details, then ask a vendor for workload-specific evaluations and their limits. The analogy itself does not substantiate a production result.

The Mapping: Signals to Specifications

The match between signals and prompts is exact, not just a loose comparison:

Signal ProcessingLLM Prompting
Continuous signalComplete specification (user's intent)
Frequency bandsSpecification bands (PERSONA, CONTEXT, DATA, CONSTRAINTS, FORMAT, TASK)
Bandwidth B6 distinct specification bands
Sampling rateNumber of bands explicitly covered
Nyquist rate (2B)All 6 bands present (minimum for faithful reconstruction)
AliasingHallucination (model invents missing specifications)
sinc interpolationModel's reconstruction of intent from prompt samples

Why 6 Bands and Not More?

The framework uses six categories to organize instructions across different tasks. Treat them as a review checklist and evaluate their usefulness for your workload; this page does not establish that six is an empirically optimal decomposition.

All 11 agents needed the same 6 kinds of information. They all needed those 6 in about the same amounts, even though their jobs were very different. This tells me that 6 bands capture what an AI truly needs. It is like how light has a small number of color bands that your eye can tell apart.

I also tried splitting the bands into more pieces. For example, I split CONSTRAINTS into two parts: rules about what to do and rules about what not to do. That did not make the answers better. So 6 bands is the right number.

CONSTRAINTS states rules, limits, and exclusions to check in the output. FORMAT states the required output structure.

In signal terms, CONSTRAINTS is the strongest band. When it is missing, the AI makes the most errors. This is why writing "do not hallucinate" in a prompt does almost nothing. That phrase is a rule about rules. It is too vague to help. But writing clear rules like "maximum 200 words, no technical jargon, must include pricing, must not mention competitors" makes the output much better.

Practical Applications

The theorem gives you clear steps to follow. Here is what my production measurements showed:

  • Completeness check, Any prompt missing one or more of the 6 bands is undersampled and will alias
  • Token allocation, Invest 50% of tokens in CONSTRAINTS + FORMAT, 40% in CONTEXT + DATA, 10% in PERSONA + TASK
  • Cost review , Compare prompt changes using the workload, token counts, retries, and output checks for your own system
  • Quality prediction, A prompt's SNR can be estimated from its band coverage before execution

Try the free sinc-LLM prompt transformer or explore the source on GitHub.

The Bigger Question

Nyquist gives you the floor. Skip any band and the AI guesses. No machine learning trick can recover a piece of information you never gave it. Cover all 6 bands, hit the rate, and send the prompt.

Applying Nyquist to your own prompt is the easy part. The hard part is asking your AI vendor whether they do the same. Do they cover all 6 bands in the prompts they build? Can they show you their rules? Do they check whether those rules still work after a model update? Most cannot answer those questions in plain English.

// Free · 10-Point Audit

Now ask your AI vendor the same questions.

You just learned the signal-based reason why AI prompts hallucinate. The 10-Point AI Vendor Audit asks the same engineering questions about the company running your AI: monitoring, error budgets, fallbacks, ownership. Free 16-page PDF, yes/no checklist, 15 minutes per vendor.

→ Get the audit

This is the exact JSON format that sinc-LLM uses. Paste any raw prompt at sincllm.com to generate one automatically.

{
  "formula": "x(t) = Σ x(nT) · sinc((t - nT) / T)",
  "T": "specification-axis",
  "fragments": [
    {
      "n": 0,
      "t": "PERSONA",
      "x": "You are a signal processing professor who can explain complex mathematical concepts to a non-technical audience using analogies and visual descriptions."
    },
    {
      "n": 1,
      "t": "CONTEXT",
      "x": "The Nyquist-Shannon sampling theorem was published in 1949. It states that a signal can be perfectly reconstructed from its samples if the sampling rate is at least twice the highest frequency. This theorem has never been applied to LLM prompts until sinc-LLM."
    },
    {
      "n": 2,
      "t": "DATA",
      "x": "Shannon 1949. Formula: x(t) = Sigma x(nT) * sinc((t - nT) / T). 6 bands on the specification axis. Nyquist rate = 6 samples. Raw prompt = 1 sample = 6:1 undersampling. SNR improvement: 0.003 to 0.92."
    },
    {
      "n": 3,
      "t": "CONSTRAINTS",
      "x": "Explain the theorem without requiring calculus knowledge. Use the music/audio analogy (44.1kHz sampling). Connect every signal processing concept directly to its LLM equivalent. Never say 'it is complicated.' Make it simple."
    },
    {
      "n": 4,
      "t": "FORMAT",
      "x": "Return: (1) The Theorem in Plain English. (2) The Music Analogy (3 paragraphs). (3) Mapping Table: Signal Processing Term to LLM Equivalent. (4) Why 6 Samples (one paragraph per band)."
    },
    {
      "n": 5,
      "t": "TASK",
      "x": "Explain the Nyquist-Shannon sampling theorem and how it applies to LLM prompts in a way that someone with no math background can understand and remember."
    }
  ]
}

Install: pip install sinc-llm | GitHub | Paper

// Production AI Engineering

Build AI systems that hold up in production.

sinc-LLM designs, audits, and stabilises production AI infrastructure: from vendor evaluation and cost accountability to incident controls and MCP architecture.

See what we do →
Additional context

sinc-LLM About Blog Services

The services, methods, and examples described here do not establish an expected performance result for your workload.