Stop Typing Rubbish into AI — There’s a Better Way
How to use prompt frameworks to get genuinely useful answers from ChatGPT, Copilot, or any AI tool — without any technical knowledge.
Most people use AI the same way they use a search engine. They type a vague question, get a vague answer, and conclude that AI is either brilliant or useless depending on their mood.
The problem isn’t the AI. It’s the question.
This post introduces a free tool that helps you ask better questions — and shows you exactly what to type to get useful, specific, professional output from any AI assistant.
What is a prompt?
Before we go any further: a prompt is simply what you type into an AI tool. It’s your question, your instruction, your request. The quality of the prompt determines the quality of the answer.
Bad prompt
“Write me something about our new service.”
Better prompt
“You are a business consultant helping a small accountancy firm explain a new fixed-fee monthly service to existing clients who are worried about price changes. Write a short, reassuring email of around 150 words in a warm but professional tone.”
Same AI. Completely different result.
What is a prompt framework?
A prompt framework is a simple structure that helps you include the right information in the right order. Think of it like a form — instead of staring at a blank box wondering what to write, you fill in the sections and end up with a prompt that actually works.
The tool at gethynellis.app/tools/prompt-frameworks gives you eight of these frameworks, each suited to a different kind of task.
No technical knowledge needed
You don’t need to understand how AI works. You just need to know roughly what you want — the tool helps you ask for it properly.
We have several Frameworks – unserdtand when to use each one
RTF – Role, Task, Format
Best for: emails, summaries, quick rewrites
The simplest framework. You tell the AI who to be, what to do, and how to present the answer. If you’re in a hurry, start here.
APE – Action, Purpose, Expectation
Best for: simple, well-defined tasks
Even leaner than RTF. Three things: what to do, why, and what the output should look like. Useful when the task is obvious and you just want to get moving.
BAB – Before, After, Bridge
Best for: sales copy, case studies, persuasive writing
Built for persuasion. You describe the problem someone has now, what life looks like when that problem is solved, and how your product or service gets them there. Brilliant for anything where you’re trying to convince someone to change.
CARE – Context, Action, Result, Example
Best for: project reports, stakeholder updates, case studies
Use this when you need to explain what happened and why it mattered. Context sets the scene, Action explains what was done, Result shows the outcome, Example makes it concrete.
RISE – Role, Input, Steps, Expectation
Best for: process design, implementation plans, training outlines
When you have a task with a clear sequence, RISE makes the AI follow your stages rather than invent its own. You define the steps; it fills them in.
CO-STAR – Context, Objective, Style, Tone, Audience, Response
Best for: LinkedIn posts, newsletters, website copy
The content creation framework. When you need the AI to write in a specific voice for a specific audience, CO-STAR gives it all the information it needs to get the tone right. Same message, written differently for a board member versus a first-year apprentice.
WHEELS – Role, Objective, Details, Examples, Sense-check
Best for: technical content, training materials, high-stakes documents
Good for technical or training content where accuracy matters. The Sense-check component tells the AI to review its own output before giving it to you, which catches errors and gaps before you do.
CRIT – Context, Role, Interview, Task
Best for: complex briefs, strategic planning, anything high-stakes
The most powerful framework in the set. Before the AI writes anything, it asks you questions — one at a time — to make sure it understands what you actually need. The Interview step turns the AI from an answer machine into something closer to a consultant. Use this when the task is complex, the stakes are high, or you’re not entirely sure what you want yet.
How the tool works
Visit gethynellis.app/tools/prompt-frameworks. You’ll see the eight frameworks listed. For each one, you can:
Read a plain-English explanation of what it does and when to use it. Fill in the fields for your specific task. Copy a ready-to-use prompt that you can paste straight into ChatGPT, Microsoft Copilot, Claude, or any other AI tool.
Quick example
Say you work in HR and need to write a message explaining a change to the annual leave policy. Using CO-STAR, you’d think through who’s reading this (all staff), what you need them to do (understand the change and feel reassured), what tone fits (clear, calm, not corporate), and what format works (short email, plain English). The tool builds that into a prompt. The result is something you can actually send.
“People who learn to prompt well get genuinely useful output. People who don’t get generic waffle and conclude the technology isn’t worth the hype.”
Why this matters
AI tools are becoming standard in most workplaces. Whether you’re using Microsoft Copilot in Word, ChatGPT in a browser, or a built-in assistant in your HR or finance software, the way you interact with it determines the value you get from it.
This tool removes the learning curve. You don’t need to memorise frameworks or read a textbook. You just need to know it exists and use it once, after that, the logic sticks.
For teams rolling out AI tools, this is also a practical starting point for training. Rather than abstract workshops about “AI adoption”, giving people a concrete tool they can use in their first five minutes is often more effective than anything else.
Try it now – it’s free
No login required. Eight frameworks, plain-English guidance, and prompts you can copy and paste immediately into any AI tool (Co-pilot, ChatGPT, Claude etc).
PakarPBN
A Private Blog Network (PBN) is a collection of websites that are controlled by a single individual or organization and used primarily to build backlinks to a “money site” in order to influence its ranking in search engines such as Google. The core idea behind a PBN is based on the importance of backlinks in Google’s ranking algorithm. Since Google views backlinks as signals of authority and trust, some website owners attempt to artificially create these signals through a controlled network of sites.
In a typical PBN setup, the owner acquires expired or aged domains that already have existing authority, backlinks, and history. These domains are rebuilt with new content and hosted separately, often using different IP addresses, hosting providers, themes, and ownership details to make them appear unrelated. Within the content published on these sites, links are strategically placed that point to the main website the owner wants to rank higher. By doing this, the owner attempts to pass link equity (also known as “link juice”) from the PBN sites to the target website.
The purpose of a PBN is to give the impression that the target website is naturally earning links from multiple independent sources. If done effectively, this can temporarily improve keyword rankings, increase organic visibility, and drive more traffic from search results.
Comments are closed, but trackbacks and pingbacks are open.