Skip to content
sinc-LLMBook a 30-minute call

Engineering reference

RISEN Prompt Framework: What It Gets Right and What It Misses

An explanation of RISEN's fields, limitations, and mapping to the author's sinc prompt structure.

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

RISEN includes a “Narrowing” step for limits. This article compares its five fields with the sinc-LLM six-field format, including where to place context, data, and constraints.

RISEN breaks a prompt into five parts:

  • R — Role: The expert the AI should act as
  • I — Instructions: Clear directions for the task
  • S — Steps: The steps to take, in order
  • E — End goal: What you want the AI to produce
  • N — Narrowing: Rules about what the AI must NOT do

What RISEN Gets Right: The Narrowing Dimension

RISEN includes a Narrowing step for rules and exclusions. This comparison discusses that step alongside the sinc-LLM CONSTRAINTS field.

Most frameworks, such as CO-STAR, RACE, and APE, have no constraints step at all. RISEN earns credit for adding one.

RISEN gets constraints right. But it still has three gaps:

1. No Context Band

RISEN has Role and Instructions but no Context slot. Background facts, such as industry, company size, or market conditions, have to be crammed into Instructions or Role. This creates confusion. The AI cannot tell apart “who you are” (Role), “what the situation is” (Context), and “what to do” (Instructions).

2. No Data Band

RISEN has no place for real inputs like datasets, code snippets, or reference files. If you want the AI to use your data, you have to stuff it into Instructions. That field then becomes a dumping ground and loses its structure.

3. Redundancy Between Instructions, Steps, and End Goal

Instructions, Steps, and End Goal all say roughly the same thing. Clear Instructions already imply Steps. Steps already imply an End Goal. The End Goal just restates the Instructions. So RISEN uses 3 of its 5 slots to describe one idea: the task.

Mapping RISEN to sinc-LLM

RISEN Elementsinc-LLM BandNotes
RolePERSONA (n=0)Direct mapping
InstructionsTASK (n=5)Overloaded — RISEN puts context and data here
StepsTASK (n=5)Redundant with Instructions in most cases
End goalTASK (n=5) + FORMAT (n=4)Split between output description and task objective
NarrowingCONSTRAINTS (n=3)Direct mapping — RISEN's strongest dimension
—CONTEXT (n=1)Missing in RISEN
—DATA (n=2)Missing in RISEN
—FORMAT (n=4)Partially covered by End goal
x(t) = Σ x(nT) · sinc((t - nT) / T)

Comparing RISEN and the Six-Field Format

A workload comparison needs the same tasks, model settings, sources, and scoring rules. Assess usability, factual errors, format compliance, and regeneration separately.

The field mapping below keeps RISEN’s constraints step while giving context and data their own fields. Field coverage alone does not establish a better output. Related: sinc-LLM.

If you like RISEN, you can bring its best parts into sinc-LLM:

  • RISEN's Role maps to sinc-LLM's PERSONA. Keep the role framing.
  • RISEN's Narrowing maps to sinc-LLM's CONSTRAINTS. Keep the constraint habit.
  • RISEN's Steps can go inside sinc-LLM's TASK slot as a numbered list.
  • Add the three missing slots: CONTEXT for the situation, DATA for your inputs, FORMAT for how the output should look.

The result is a prompt that has RISEN's constraint habit plus sinc-LLM's full six-slot coverage.

{
  "formula": "x(t) = \u03a3 x(nT) \u00b7 sinc((t - nT) / T)",
  "T": "specification-axis",
  "fragments": [
    {"n": 0, "t": "PERSONA", "x": "Expert data scientist with 10 years ML experience"},
    {"n": 1, "t": "CONTEXT", "x": "Building a recommendation engine for an e-commerce platform"},
    {"n": 2, "t": "DATA", "x": "Dataset: 2M user interactions, 50K products, sparse matrix"},
    {"n": 3, "t": "CONSTRAINTS", "x": "Must use collaborative filtering. Latency under 100ms. No PII in logs. Python 3.11+. Must handle cold-start users with content-based fallback"},
    {"n": 4, "t": "FORMAT", "x": "Python module with type hints, docstrings, and pytest tests"},
    {"n": 5, "t": "TASK", "x": "Implement the recommendation engine with train/predict/evaluate methods"}
  ]
}

If you use RISEN, compare its field mapping with the six-field format at sincllm.com. Choose the structure for the task and verify the response against the supplied requirements.

// 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

© 2026 sinc-LLM. All rights reserved. DOI: 10.5281/zenodo.19152668