Essentials
8 guided hoursModules 1-2. An introduction with practical exercises and a small reviewed artifact.
FOUNDATIONS · BEGINNER FRIENDLY
AI Foundations & Prompt Engineering
Understand AI before putting it to work.
Build a grounded understanding of generative AI and learn how to use an assistant for useful tasks. Practise clear prompting, verification and responsible handling of information.
COURSE OVERVIEW
Is AI foundations suitable for beginners?
This outline starts with basic AI concepts and practical assistant use. It covers task selection, prompting, source checking and responsible use without requiring programming or advanced mathematics.
YOUR SHARED FOUNDATION
Learn prompt engineering fundamentals.
Learn clear task framing, useful context, examples, constraints and evaluation. Then apply the approach in the ChatGPT, Claude, Gemini or Codex course.
Choose Your Next AI CourseA STARTING POINT THAT FITS
Three learning levels.
Practitioner
24 guided hours totalModules 1-6, including Essentials. Complete the core labs and an assessed practical project.
Advanced
12 additional guided hoursTwo extension modules and a four-hour project clinic after practitioner readiness.
These are curriculum planning options. We confirm the timetable, delivery format, fees and required accounts before enrolment. Practitioner includes Essentials; the two durations are not added together.
Download the Curriculum PDFCheck your starting point
- Create a folder and save a text file. If this is difficult, start with Computer Literacy.
- Audit two factual claims against the course sheet. Start Essentials if source checking is unfamiliar.
- Write and test a bounded prompt on three cases. Consider Practitioner or Advanced when this is independent.
WHAT YOU’LL LEARN
Skills to put into practice.
- Explain the difference between AI, machine learning and generative AI.
- Choose a suitable task and set realistic expectations.
- Write prompts with context, examples and a clear output format.
- Check outputs and recognise when specialist or human judgement is needed.
Who this is for
Students, educators and professionals beginning to explore AI tools for learning or work.
Before you begin
Basic computer and internet skills. No programming or advanced mathematics is required.
THE COURSE OUTLINE
A clear path, module by module.
Each module connects a concept to a practical task. Open a module to see its topics and exercise.
01How to think about AI
- Understand models, training, inference and generated output at a high level.
- Compare prediction, generation and rule-based automation.
- Recognise uncertainty, bias and fabricated claims.
What you will understand
A model learns statistical patterns from examples. During use it generates an output that fits the input and its learned patterns. A generated sentence can sound convincing without matching reality. Rule-based automation follows explicit conditions, while a generative model can produce different acceptable drafts from the same brief. Training changes a model using a collection of examples. Inference uses a trained model to respond to a request. A conversation normally supplies context for that request, rather than retraining the model. Separate the supplied source facts from background knowledge and from conclusions you still need to check. Confidence in wording is not a measurement of correctness. Check a factual claim against an appropriate source, a total against the underlying rows, and a code change by running it. When an input lacks a fact, the useful output says the fact is missing and asks for clarification.
PUT IT INTO PRACTICE
Explain the limits of an assistant using three everyday examples.
02Choose a practical use case
- Identify useful drafting, organising and learning tasks.
- Define the expected output and how you will check it.
- Avoid using generated text as an unquestioned source of truth.
What you will understand
Choose work whose quality you can judge: restructuring notes, drafting a short email or generating practice questions from an approved reference. Separate low-cost drafting from decisions that affect people. Identify the exact output and who will use it before selecting a tool or prompt. A criterion states what you can observe in the result. A weekly update can require every action to have an owner, every date to match the notes and every uncertain fact to carry a label. Define criteria before drafting so you do not lower the standard to fit the answer. Estimate the current task time, the AI-assisted time and the review time. A faster draft is useful only when verification still produces a reliable output. Include setup effort and corrections in the estimate. Start with one bounded use case that a learner can complete and inspect during class.
PUT IT INTO PRACTICE
Write a task brief for a small learning or work activity.
03Prompt engineering fundamentals
- Describe the task and supply only the context that affects the result.
- Define a useful format, constraints and examples when needed.
- Ask for missing information and distinguish source evidence from assumptions.
- Set quality criteria, compare prompt versions and revise with specific feedback.
What you will understand
Begin with the result you need and give the facts that affect it. For a course enquiry, the context includes the course sheet and the prospective learner question. Excess background can distract from the task. Label reference material clearly so quoted instructions inside a document do not become new task instructions. Specify a useful output shape, audience and limits when they matter. A table with claim, source and confidence is easier to review than an unstructured paragraph. A word limit or tone requirement improves presentation, but neither guarantees accuracy. Use a short example when a format is difficult to explain. Compare prompt versions against the same examples and criteria. Change one feature at a time so you can explain the effect. A better result on one easy input may fail on a missing-information case. Keep the prompts and scores, and describe the trade-off without claiming a universal best prompt.
PUT IT INTO PRACTICE
Test two prompt versions on the same sample inputs and record accuracy, completeness and useful improvements.
PROMPT & REVIEW
Try this brief
Turn this task into a useful prompt using only the context it needs. Specify a good result, relevant constraints and how I should check it.
Check the result
Compare two revisions on the same sample inputs. Record accuracy, completeness and the reason for each improvement.
04Work from source material
- Ask questions about a provided document.
- Separate statements supported by the source from assumptions.
- Check quotations, calculations and references.
What you will understand
Extraction copies specific fields from a source into a structure. A summary compresses meaning and requires choices about relevance. Define which operation the task needs. During extraction, preserve dates and quantities exactly. During summary, verify that omitted context does not change the meaning of the original. An empty field means the source does not supply a value. It does not justify inventing one. Use a consistent missing-value marker and distinguish missing, not applicable and contradicted. If two sources conflict, retain their labels and ask the person responsible to resolve the conflict. Provenance records where a fact came from. A small action table can include a source line number or document heading beside every row. This makes review fast and supports later corrections. A citation is useful only when the linked passage actually supports the claim. Open the source and inspect the relevant passage.
PUT IT INTO PRACTICE
Create a summary with a source-checking table.
05Use AI responsibly
- Handle private information and account access carefully.
- Recognise academic integrity and authorship requirements.
- Decide where human review is necessary.
What you will understand
Share the least information needed for the exercise. Fictional records usually teach the same skill as private customer records. Remove identifiers before classroom demonstrations and verify that the resulting examples still represent the intended problem. A copied name may remain identifying even when a phone number is removed. Test whether different but equivalent inputs receive different treatment. A tone or language change should not justify a different course recommendation when readiness evidence stays the same. Discuss the impact of a wrong recommendation and keep consequential decisions with an informed person. The lesson evaluates behaviour rather than claiming bias-free operation. Record substantial AI assistance in an assessed project. A learner should explain the artifact, identify what changed after review and reproduce important checks. Separate a draft from an external action: sending a message or publishing a page requires a responsible person to approve the actual result.
PUT IT INTO PRACTICE
Create a checklist for your institution or workplace context.
06Create a repeatable workflow
- Combine a task brief, prompts and quality checks.
- Compare output quality before and after revision.
- Document limitations and your own contribution.
What you will understand
A repeatable routine has explicit input, transformation, verification and release stages. Store the source material separately from the reviewed output. Give the prompt a version identifier and preserve the acceptance checklist. This structure helps a different learner run the same routine and find a failing step. Choose at least three examples: a normal case, a missing-information case and a contradictory or malformed case. Keep the expected behaviour beside each example. These cases reveal failures that a polished demonstration can hide. A small set supports learning but does not establish broad reliability for every future situation. A useful guide explains setup, the input contract, the output format, review responsibilities and failure handling. Include a manual fallback when account access is unavailable. Mark the point at which a person approves the output for use. Another learner should be able to follow the guide without the author narrating every click.
PUT IT INTO PRACTICE
Demonstrate a small workflow you can explain and repeat.
PROMPT & REVIEW
Try this brief
Use this task template with a new sample document. Return the requested output and flag anything the source does not establish.
Check the result
Test the workflow on three inputs, including an incomplete one, and keep a prompt and review record.
AFTER THE CORE COURSE
Advanced extension.
07Advanced evaluation and error analysis
- Failure categories
- Scoring and agreement
- Generalisation
ADVANCED PRACTICE
Mini evaluation study
08Advanced reusable assistants and retrieval
- Instructions and knowledge
- Retrieval coverage
- Maintenance
ADVANCED PRACTICE
Knowledge-pack maintenance
Complete both four-hour extension modules and a four-hour project clinic. Entry uses the core project and readiness evidence.
BRING THE SKILLS TOGETHER
Your first checked AI workflow
Build a study or work assistant routine using sample material. Show the prompt, output, source checks and improvements so someone else can follow your process.
Your project deliverables
- A clear task brief and reusable prompts
- Reviewed outputs with source checks
- A short guide to limitations and responsible use
A learning project using sample or permitted material. The final scope is agreed for your learning plan.
KEEP EXPLORING
Useful official resources.
Reference material to complement the Hawa Enterprises curriculum. Account features may vary; basic-feature or manual alternatives support the core exercises.
Course outline published by Hawa Enterprises. Updated . Ask about the learning plan.
GOOD TO KNOW
Before you take the next step.
Is this machine learning programming?
This is an introduction to understanding and using AI assistants. It does not cover advanced model training or promise a machine learning engineering qualification.
Which AI tool will we use?
The suitable tool and account requirements are confirmed for the agreed learning plan. The prompting and verification approach is designed to be transferable.
What are the fees, schedule and delivery format?
These details are confirmed by email before you commit. The curriculum gives guided-hour options for Essentials, Practitioner and Advanced. Actual schedules, fees and delivery arrangements are confirmed before enrolment. Ask about the course you want and your preferred timeline.
How do I enrol?
Choose a course and complete the enrollment wizard with your name, email and WhatsApp number. Review your details before sending the enquiry. Hawa Enterprises will discuss your starting level, goals and course arrangements before enrolment is confirmed.
YOUR NEXT SKILL STARTS HERE
Let’s find the right
course for you.
Tell us your goal, starting level and preferred timeline.