AI ACADEMY / AI FOUNDATIONS
Use AI with more clarity and confidence
Get more useful help from AI by knowing what to ask and what to check. Practise clearer instructions, spot weak answers and improve drafts for writing, planning and organising information.
01 / THE CHALLENGE
Make progress on a real working problem.
A fluent response can look convincing even when it misses your purpose or adds facts you never supplied.
WHAT WE’LL SHAPE WITH YOU
- A reusable instruction checklist
- A simple method for checking AI responses
- Worked examples you can adapt to everyday tasks
Build the habits behind useful AI assistance
DEEPER PRACTICE / AI FOUNDATIONS
Foundations helps you move from experimenting with an assistant to asking clearer questions and assessing its answers. The programme starts at an introductory level; scope is agreed before booking. The curriculum and exercises described here are illustrative.
Explore the detail · See the practice method · Questions before booking
Understand what you are asking the assistant to do
01 / PRACTICAL DETAIL
An AI assistant can produce fluent text from a vague request, but fluency does not tell you whether the result fits your purpose. Foundations starts with the task: what you need, who will use it and what evidence is available. These decisions are more useful than collecting elaborate prompt phrases.
You will consider the difference between drafting, extracting, organising and recommending. Asking for a summary of supplied text is different from asking for current factual research. A helpful instruction makes that distinction clear and gives the assistant a way to ask about missing information.
Task checklist
- Identify the task and intended audience.
- Separate supplied facts from questions requiring research.
- Choose a useful output format.
- Decide how the response will be checked.
Suggested curriculum: ask, inspect and improve
02 / PRACTICAL DETAIL
The first module introduces AI assistance and its limits using everyday examples. The second builds clear instructions: provide context, define the result, state constraints and include relevant examples. The third uses focused feedback to revise a draft rather than restarting with increasingly vague demands.
The fourth module develops checking habits. Compare an answer with its source, notice unsupported additions and identify places where a confident tone hides uncertainty. Privacy practice sits within the task: use information appropriate for the tool, remove unnecessary personal details and practise with invented material while learning.
Learning checkpoints
- What an assistant can help with
- Clear context, constraints and formats
- Specific revision requests
- Source comparison and uncertainty
- Appropriate input choices
Illustrative exercise: describe a café item accurately
03 / PRACTICAL DETAIL
Start with an invented café menu item and a short ingredient list. Ask for a customer-friendly description with a defined length and tone. Include no dietary certification, nutritional figures or origin claims. Review whether the assistant added any detail that the brief did not support.
Revise the instruction so the assistant uses only supplied facts and flags anything missing. Then try a second fictional item. The acceptance check is that the draft preserves the ingredients, avoids unsupported dietary claims, follows the format and remains understandable to its audience. A polished sentence that fails those checks needs revision.
Example checks
- Facts trace back to the brief.
- The requested audience and format are respected.
- Missing information stays visible.
- The revised instruction works on another example.
Illustrative exercise: organise a week without guessing
04 / PRACTICAL DETAIL
Use a fictional weekly schedule with fixed commitments, optional tasks and one conflicting appointment. Ask the assistant to organise the information rather than silently decide priorities. Compare the output with the original and check whether the conflict is preserved.
This exercise shows why constraints matter. If a task has no deadline, the assistant should not invent one. If two appointments overlap, a useful response asks for a decision. Participants can compare a table, an action list and a short narrative to see which format supports the real purpose.
Review criteria
- Preserve fixed commitments.
- Separate optional tasks from obligations.
- Flag conflicts and missing deadlines.
- Keep personal decisions with the user.
05 / PRACTICAL DETAIL
Preparation, fit and useful references
Foundations suits beginners and people who already use AI but want more reliable working habits. It is less suitable as a substitute for specialist coding, a live automation project or expert advice in a consequential field. SearchScale’s existing AI Code Club remains a separate learning destination for its coding scope.
Prepare a simple task you would like to improve and a non-sensitive example of the desired result. Useful practice artefacts may include an instruction checklist, a claim-check worksheet and revised examples. The exact content is agreed before booking. Official OpenAI and Anthropic documentation can support product-specific follow-up; use the guidance relevant to your actual tool.
Preparation checklist
- Describe your experience honestly.
- Bring a task rather than private documents.
- Ask about supported tools and account requirements.
- Plan how you will check your next independent attempt.
The method matters as much as the output.
A VISUAL PRACTICE MAP
Use this four-stage map to organise the exercises on this page. It describes a learning method, rather than a deployed system or client result.
A grounded first prompt
Illustrative input: Fictional café brief: a warm oat drink with cinnamon. No calorie figures, allergy assurances or dietary certifications have been provided.
Try this instruction: “Write a friendly, two-sentence menu description using only the supplied ingredients. Do not add health, allergy or certification claims. List information needed for any such claim.”
What to check: The draft preserves the ingredients, follows the length and flags missing evidence. A separate human check is needed before using it on a real menu.
01 / BRIEF
Define the request
State audience, supplied facts and desired format.
02 / PROMPT
Make an attempt
Ask for a draft that flags missing information.
03 / INSPECT
Check each claim
Compare facts and constraints with the original input.
04 / REVISE
Improve the instruction
Apply specific feedback and try another fictional example.
BRIEF → PROMPT → INSPECT → REVISE
QUESTIONS & SCOPE
Make an informed choice.
Do I need technical experience?
The introductory scope uses everyday tasks and plain-language instructions. Explain your starting point when enquiring.
Will better instructions make every answer correct?
No. Clear instructions improve task definition, but outputs still need appropriate review and factual checking.
Can I apply the skills to several tools?
Many habits transfer. Features, account requirements and data handling vary, so confirm the practical tool arrangements.
What should I practise afterwards?
Repeat a low-consequence task using suitable information, keep the source and assess the result against the same checklist.
Make your first enquiry useful.
Share the points below in your enquiry. SearchScale will discuss suitability and the programme scope before you commit. Dates, format, fees and required accounts are confirmed directly.
- Your current AI experience
- A task you want help with
- The output you would consider useful
- Your preferred tool, if any
- Any practical or accessibility requirements
Practical experience. Transparent learning.
SearchScale Coaching is founded by Chris Matthews, an entrepreneur and SEO practitioner since 2011. The Academy applies a practical business perspective: start with a real task, understand the method and check the result. Explore our approach and the separate Business Builder programme for more about SearchScale’s wider work.
Worked example: a grounded first prompt
Give the tool this fictional brief: “A customer wants a 30-minute introduction to our service. We have not agreed a date or price.” Ask it to draft a warm reply using only those facts and to list missing details separately. Check that it does not invent availability, fees or a booking confirmation. Compare the first answer with a revised prompt that explicitly forbids unsupported claims.
Illustrative learning example. These exercises use fictional inputs. They are not client case studies, measured business results or a promise of a particular outcome.
Learn from original sources
Tool behaviour changes. Read the current documentation alongside any exercise: OpenAI’s prompt engineering guide and Anthropic’s prompting documentation. These are independent reference sources; linking to them does not imply endorsement, certification or partnership.
Quality checks that matter
Check factual claims against their source. Keep confidential information out of practice exercises. Identify missing inputs instead of filling them with guesses. Retain a human decision before publishing, sending or acting on an output. For an automated process, define permissions, failure handling and a way to stop it.
A clear scope before you commit
All five Academy programmes are available now. Contact SearchScale to agree scope, dates and fees. Before booking, agree the audience, starting level, learning goals, delivery format, included resources and fees with SearchScale. Confirm any required tool accounts or separate subscriptions. The examples on this page explain the practical focus; your agreed programme scope determines the exercises and deliverables.
Have a question or spotted an error? Contact SearchScale with the page and the point you would like clarified. This Academy content was updated on 2 October 2026. The guides use AI-assisted drafting, original fictional exercises and linked primary documentation. Illustrations show the learning method; they do not document client results. Report a factual correction through the contact link above.
PERSONALISED GUIDANCE
A clear starting point for a new skill.
You do not need a technical background or a finished plan. SearchScale’s approach is to begin with a useful task, explain the method and check the result. Discuss your experience level and goals so the Foundations programme can be scoped appropriately.
Meet Chris Matthews and explore the approach →
Start with a free 20-minute discovery call. Receive a report outlining proposed deliverables afterwards. For focused advice, choose a one-hour consultation at US$150, with written follow-up.
LET’S FIND YOUR STARTING POINT
Bring the task.
We’ll help shape the training.
Tell us what you want to improve and who will take part. We’ll agree the programme scope, relevant exercises and resources, delivery arrangements and fees.
Opens your email app. Include your goal and experience level; leave confidential records out of the enquiry.