Reviewing AI Prompts With Six Specification Fields

The Uncomfortable Truth

Review prompts for the task details they state and omit. No universal signal-to-noise score or amount of model guesswork is established here.

You type "Summarize this document." Then you complain the summary is too long, too vague, or misses the point. You type "Write me a blog post." You get a boring wall of words full of maybes and warnings. You type "Analyze this data." You get a shallow overview instead of the deep breakdown you wanted. Then you blame the model.

The model is not the problem. Your prompt is the problem.

One Sample of a Six-Band Signal

I am Mario Alexandre. I am an electrical engineer. When I looked at how people talk to LLMs, I did not see a writing problem. I saw a signal problem. And signal science has a rule for exactly this.

This article uses signal sampling as an analogy for organizing prompt requirements; it does not establish a mathematical model of LLM errors.

When you write a prompt, your intent has 6 bands of information:

1. PERSONA, who should answer (what kind of expert, what voice)
2. CONTEXT, the situation and the facts around it
3. DATA, the exact numbers and details to use
4. CONSTRAINTS, the rules and limits, what NOT to do
5. FORMAT, how the answer should look and how long it should be
6. TASK, what you actually want done

When you type "Summarize this document," you give the model 1 band (TASK) out of 6. The model has to fill in the other 5 bands on its own. Every band it fills in by guessing is a chance for a wrong answer, a vague statement, or a result you did not want.

You are not really giving the model instructions. You are giving it a tiny slice of what you want. Then you blame it for getting the rest wrong.

Measurements for a Prompt Comparison

The following table describes the author’s task-specification fields. A field allocation alone does not establish its contribution to output quality. Related: paper.

Check TASK, CONSTRAINTS, and the other fields for the information the task needs. The allocation alone does not establish output quality.

Rewording TASK can leave other requirements unresolved. Review CONSTRAINTS and FORMAT alongside the objective, context and data instead of assuming phrasing alone captures the specification.

What the Model Does with Your Broken Prompt

When you leave out CONSTRAINTS, the model falls back on its defaults:

• Hedging phrases (like "It is important to note that..." or "While there are many perspectives...")
• Disclaimers (like "I am an AI and cannot..." or "Results may vary...")
• A generic structure (intro, body, conclusion) even if that is not what you need
• A medium length, not too short and not too long
• A bland professional tone that sits in the middle of everything it was trained on

Each of those defaults is the model filling a CONSTRAINTS gap. You did not say "no hedging," so it hedges. You did not say "no disclaimers," so it adds them. You did not say "short and direct," so you get medium-length bland text. The model is doing exactly what you asked, which was almost nothing.

If FORMAT is omitted, inspect the structure the model chooses. A missing format field does not establish a universal response style.

The Author's Measurement Approach

A prompt-format cost comparison needs the workload, model settings, token counts, retries, and output checks for both versions. Related: sinc-LLM research.

The article presents the author's prompt-structuring approach and its measurement methods.

The 6-Band Decomposition

Here is the fix. Before you send a prompt, break it into 6 bands. My sinc-LLM tool does this for you, but you can also do it by hand in 60 seconds:

1. PERSONA: define the perspective and style. For example, ask for a B2B SaaS copywriter using short sentences; verify any claims in the resulting email.
2. CONTEXT: describe the company, industry, stage and relevant situation. Include the facts needed to interpret the request.
3. DATA: supply the numbers, references and specific inputs. For an analysis request, provide the material to analyze.
4. CONSTRAINTS: state word limits, prohibited phrases, required inclusions, tone rules and other boundaries. Review the prompt constraints and check the response for compliance.
5. FORMAT: specify the output structure. For example, “Return: subject line, 3 paragraphs, CTA text.”
6. TASK: state the objective clearly and check that it agrees with the details in the other fields.

A Real Example: Before and After

Here is what a properly decomposed prompt looks like in the sinc JSON format:

{
  "formula": "x(t) = Sigma x(nT) * sinc((t - nT) / T)",
  "T": "specification-axis",
  "fragments": [
    {
      "n": 0,
      "t": "PERSONA",
      "x": "You are a direct-response copywriter who writes high-converting cold emails for B2B SaaS companies. You write in short sentences. You never hedge. Every line earns the next line."
    },
    {
      "n": 1,
      "t": "CONTEXT",
      "x": "DLux Digital is launching a new API product called PayFlow for fintech CFOs. Series A company, 50 employees. The product reduces payment reconciliation time from 4 hours to 12 minutes. Price: $99/month. Competitor Stripe Reconcile charges $299/month."
    },
    {
      "n": 2,
      "t": "DATA",
      "x": "Product: PayFlow API. Price: $99/mo. Target: CFOs at fintech companies, 50-200 employees. Key metric: 4 hours to 12 minutes reconciliation. Competitor: Stripe Reconcile at $299/mo. Launch date: April 1, 2026."
    },
    {
      "n": 3,
      "t": "CONSTRAINTS",
      "x": "Maximum 150 words. No jargon. No buzzwords. No 'revolutionary' or 'cutting-edge' or 'leverage'. One CTA only. Do not mention AI or machine learning. Do not use exclamation marks. Subject line must be under 8 words. First sentence must reference a specific pain point the CFO has. Compliance: CAN-SPAM compliant, include unsubscribe mention."
    },
    {
      "n": 4,
      "t": "FORMAT",
      "x": "Return exactly: (1) Subject line (under 8 words). (2) Email body: 3 short paragraphs. (3) CTA button text (under 5 words). (4) Unsubscribe line. No headers, no formatting, just the raw email text ready to paste into an email tool."
    },
    {
      "n": 5,
      "t": "TASK",
      "x": "Write a cold outreach email for the PayFlow API launch targeting fintech CFOs."
    }
  ]
}

Now compare that to what most people send: "Write a cold email for my new API product PayFlow targeting fintech CFOs." That version forces the model to guess the price, the competitor, the word limit, the tone, the structure, the CAN-SPAM rules, and the ban on buzzwords. Every guess is a place where the answer goes wrong.

Stop Blaming the Model

Evaluate model output against the task and supplied evidence. Improving instructions is one variable to test; incomplete prompts do not explain every model error.

State your intent in six fields, with explicit rules in CONSTRAINTS and output structure in FORMAT. Check the response against them.

Try sinc-LLM free, read the token optimization guide, explore the open-source framework on GitHub, or read the author’s paper. Production consulting is available. Related: open source framework. Related: full paper. Related: I can help.

The age of raw prompting is over. The signal era of AI has started.