Skip to content
sinc-LLMBook a 30-minute call

Engineering reference

The Formula I Put on Every Prompt (And Why It Matters)

An explanation of the formula included in the author's prompt format and the proposed sampling-theory connection.

Methods, definitions, and examples for the topic discussed here. Check applicability against the task and operating conditions.

Mario Alexandre  ·  March 26, 2026  ·  sinc-llm structured-prompts nyquist

Every prompt I build with sinc-LLM starts with this:

x(t) = Σ x(nT) · sinc((t - nT) / T)

People ask me: is that decoration? Is it just branding? Does the model actually use it?

It is the mathematical contract. Yes, the model uses it. It does not solve the equation. It sees the pattern, and that tells it how to read the rest of the prompt.

This is the Whittaker-Shannon interpolation formula, better known as the Nyquist-Shannon sampling theorem. In signal processing it says: if you take a continuous signal and sample it at discrete points (the x(nT) terms), you can rebuild the original signal perfectly using sinc interpolation. You just need to sample at twice the highest frequency in the signal.

Here is how it maps to prompts:

x(t)
The full intent of your prompt — what you actually want, including everything implied and unstated
x(nT)
The discrete samples — the 6 sinc bands (PERSONA, CONTEXT, DATA, CONSTRAINTS, FORMAT, TASK)
T
The specification axis — the spacing between information types, the resolution of your specification
sinc()
The interpolation — how the model reconstructs the full intent from the discrete samples
Σ
The sum — all 6 bands together reconstruct the complete specification

The sampling theorem inspires the framework’s formula. For prompts, the six fields are a checklist for task information; they do not prove that a model has everything needed to answer correctly on its first attempt.

The formula lives in the JSON because the sinc format is built to be machine-readable. When one agent passes a prompt to another, when the scatter hook adds context, or when a sub-agent gets a task, the formula in the JSON acts as a versioned label. It says: this structure follows the sinc-LLM specification.

{
  "formula": "x(t) = Σ x(nT) · sinc((t - nT) / T)",
  "T": "specification-axis",
  "fragments": [
    {"n": 0, "t": "PERSONA", "x": "..."},
    {"n": 1, "t": "CONTEXT", "x": "..."},
    {"n": 2, "t": "DATA", "x": "..."},
    {"n": 3, "t": "CONSTRAINTS", "x": "..."},
    {"n": 4, "t": "FORMAT", "x": "..."},
    {"n": 5, "t": "TASK", "x": "..."}
  ]
}

The formula field is also how the pass-through rule works in the auto-scatter hook. If a prompt has "formula" as a top-level JSON key, the hook sees it as already sinc and skips re-scattering. The formula is both documentation and a detection signal.

I checked that the Nyquist analogy holds before I published the paper (DOI: 10.5281/zenodo.19152668). Here is the key parallel that made it clear:

In Nyquist sampling theory, aliasing happens when you sample below the Nyquist rate. Aliasing means signal corruption, which means wrong reconstruction. In prompting, aliasing happens when the model does not have enough information across all dimensions. It fills the gaps with wrong guesses. The result is prompt aliasing: the model reads your intent wrong because it had too few samples of the full specification space.

The auto-scatter hook organizes input into the six framework fields, including CONSTRAINTS and FORMAT. Inspect what it adds: inferred details need confirmation, and field completion does not establish an output-quality weight or prevent errors.

// 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 →
Scope and context

sinc-LLM About Blog Services

DOI: 10.5281/zenodo.19152668 · © 2026 sinc-LLM · Mario Alexandre