Skip to content
sinc-LLMBook a 30-minute call

LLM Prompt Optimization: Reviewing Token Use and Task Requirements

A guide to the author's prompt optimization approach, covering token bloat, structured fields, and implementation architecture.

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

AI systems that use large language models grow slowly out of control. The context window fills up with old conversation history. System prompts get longer each time someone adds a fix for a new edge case. Retry loops make the token cost even higher. A system that starts at 5,000 tokens per request can reach 80,000 tokens within months.

My sinc-LLM paper discusses token bloat and the author's proposed signal-to-noise approach to prompt review.

Signal-to-Noise Ratio for Prompts

x(t) = Σ x(nT) · sinc((t - nT) / T)

The author uses SNR as a ratio of useful prompt content to total content. Compare that input measure with separate output checks:

Unmeasured test plan. No benchmark results are reported; record results from the same tasks and declared settings.
Prompt approachInput tokensDefined input scoreComplete task cost
Sliding-window contextNot measuredNot measuredNot measured
Band decompositionNot measuredNot measuredNot measured
Sleep-time consolidationNot measuredNot measuredNot measured

An SNR of 0.003 means only 0.3% of tokens carry useful information. The rest is noise: repeated history, duplicate context, and filler text.

1. Band Decomposition

Organize instructions into PERSONA, CONTEXT, DATA, CONSTRAINTS, FORMAT and TASK. Review repetition and irrelevant material while preserving required context. Count tokens and evaluate outputs before deciding what to remove.

2. Topic-Shift Detection

In a conversation, detect when the topic changes (threshold: 0.15 cosine distance) and remove history from the old topic. Most conversation history is about a different topic than the current request.

3. Deduplication

Find messages in context that say the same thing (threshold: 0.6 similarity) and keep only the newest one. Long conversations pile up many versions of the same information.

Implementation Architecture

I built the sinc-LLM pipeline to process prompts in three stages:

Raw Prompt (80,000 tokens)
  |
  v
[Band Decomposition] -- extract 6 specification bands
  |
  v
Structured Prompt (3,500 tokens, SNR 0.78)
  |
  v
[Sleep-Time Consolidation] -- async dedup + topic pruning
  |
  v
Optimized Prompt (2,500 tokens, SNR 0.92)

The added delay on the main path is only +8ms. You will not notice it in production. The sleep-time consolidation runs in the background via setTimeout(fn, 0) and does not slow down requests.

Getting Started

Here is how to start optimizing your prompts today:

  1. Measure your current token usage and SNR (specification tokens divided by total tokens).
  2. Apply band decomposition to your 5 highest-token prompts.
  3. Add the sinc-LLM framework to automate the optimization.
  4. Try the free online transformer for quick experiments.

The framework is open source. The full methodology is in my paper at DOI: 10.5281/zenodo.19152668.

Review a prompt using six specification fields

Try sinc-LLM Free

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 LLM optimization engineer. You provide precise, evidence-based analysis with exact numbers and no hedging."
    },
    {
      "n": 1,
      "t": "CONTEXT",
      "x": "This analysis is part of a production system where accuracy determines revenue. The sinc-LLM framework identifies 6 specification bands with six named fields."
    },
    {
      "n": 2,
      "t": "DATA",
      "x": "Example allocation assumptions: CONSTRAINTS=42.7%, FORMAT=26.3%, PERSONA=7.0%, CONTEXT=6.3%, DATA=3.8%, TASK=2.8%. SNR formula: 0.588 + 0.267 * G(Z1) * H(Z2) * R(Z3) * G(Z4). These allocations are illustrative assumptions, not observed quality weights."
    },
    {
      "n": 3,
      "t": "CONSTRAINTS",
      "x": "State facts directly. Never hedge with 'I think' or 'probably'. Use exact numbers for every claim. Do not suggest generic solutions. Every recommendation must be specific and verifiable. Include at least 3 MUST/NEVER rules specific to this task."
    },
    {
      "n": 4,
      "t": "FORMAT",
      "x": "Lead with the definitive answer. Use structured headers. Tables for comparisons. Numbered lists for sequences. Code blocks for implementations. No trailing summaries."
    },
    {
      "n": 5,
      "t": "TASK",
      "x": "Optimize a 3,000-token prompt to under 500 tokens while maintaining SNR above 0.85"
    }
  ]
}

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.