Essentials
8 guided hoursModules 1-2. An introduction with practical exercises and a small reviewed artifact.
AI TOOLS · BEGINNER FRIENDLY
Learn ChatGPT
Turn a question into a checked, useful result.
Use ChatGPT for writing, learning, document work and everyday research. Practise prompting in every module, compare revisions and build a reusable workflow you can explain.
COURSE OVERVIEW
What will I learn in the ChatGPT course?
Learn to use ChatGPT for writing, document questions, research and checked work routines. Every module includes a task-specific prompting exercise and quality check; the final project produces a reviewed weekly update from sample notes and a task table.
PROMPTING IN EVERY MODULE
Brief it. Check it. Improve it.
Each of the six modules includes a sample prompt and a specific quality check. Compare revisions and keep a record of what improves the result.
Explore the Prompting FoundationA 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
- Label a decision, proposal and unknown in three notes. If uncertain, start Essentials module 1.
- Extract an action table with one missing deadline. If successful, begin Practitioner after a prompting recap.
- Design three failure cases and a scoring rule. If successful, take Advanced following a Practitioner readiness review.
WHAT YOU’LL LEARN
Skills to put into practice.
- Turn a real task into a prompt with useful context and clear boundaries.
- Draft, summarise and organise information without inventing missing facts.
- Check sources, calculations and unsupported claims before using a result.
- Build and evaluate a reusable ChatGPT workflow with a prompt record.
Who this is for
Students, professionals and business owners who want to use ChatGPT for practical study or work tasks.
Before you begin
Basic computer and internet skills, plus access to ChatGPT. No coding is required. Feature availability and account requirements are confirmed before training.
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.
01Start with an everyday task
- Choose between drafting, learning, analysis and factual research.
- Recognise that confident answers can still be incorrect.
- Define a small task, its audience and a useful result.
What you will understand
A useful ChatGPT task names who needs an output and what they will do with it. 'Help with training' hides several possible jobs. 'Prepare a coordinator update from three meeting notes' narrows the work. Define success before asking, so attractive wording does not become the only measure of quality. An assistant produces a plausible response from its available context; fluency is not independent evidence. Separate drafting, which can use supplied facts, from factual research, which needs checked sources. For Riverstone Learning, a missing class date stays missing even when the assistant can invent a date that looks sensible. A blank owner or tentative suggestion should not become an assigned action. Missing information is itself useful: it identifies a follow-up question. Teach learners to distinguish decisions, proposals and open questions, then give each a visible label. This reduces accidental commitments when a draft is shared with a team.
PUT IT INTO PRACTICE
Compare two responses to a vague request and a clearly scoped request.
PROMPT & REVIEW
Try this brief
Help me turn these fictional meeting notes into a short team update. Put decisions and next actions first. Mark any missing owner or date instead of guessing.
Check the result
Compare the update with the notes. Check that no decision, owner or deadline was invented.
02Write prompts and improve drafts
- Provide the goal, relevant context, constraints and desired format.
- Use an example when it clarifies the result you need.
- Give specific feedback and compare revisions against a checklist.
What you will understand
The goal describes the work, context supplies facts, constraints bound the answer and format makes it usable. A role label alone cannot supply missing policy. Put Riverstone Learning's approved course facts in a separate block so learners can check whether the assistant followed instructions while preserving the source material. A tone example can demonstrate short paragraphs and courteous phrasing. Its names, promises or prices should not leak into a new reply. Say which features to imitate and which to ignore. This helps learners use examples as formatting guidance without accidentally carrying fictional details from one customer into another. Specific feedback makes improvement observable. 'Make it better' changes several things without a clear test. If a draft is accurate but confusing, request shorter sentences while keeping every fact unchanged. Compare versions against accuracy, permitted commitments and readability rather than choosing the one that sounds most impressive.
PUT IT INTO PRACTICE
Prepare and refine a customer email for a fictional business.
PROMPT & REVIEW
Try this brief
Draft a reply about the delayed order using only the facts below. Use a calm tone and fewer than 150 words. Do not promise a refund or delivery date that is not provided.
Check the result
Check factual accuracy and tone, then request one targeted revision and explain why it is better.
03Work from documents and tables
- Supply permitted sample material with clear source labels.
- Ask for summaries, action lists or structured extraction.
- Verify quotations, missing values and calculations against the original.
What you will understand
Summaries compress information and may merge related statements. Extraction requires a predictable row for each source item. Define column names, missing-value rules and whether repeated actions should be merged. Riverstone Learning's coordinator needs an action register, so a polished paragraph cannot replace a table with owners and evidence. Give each note or document a short label and preserve supporting text for every extracted fact. A citation-looking label is only a pointer; the learner still checks the original. When two notes disagree, list both statements and request resolution instead of silently selecting the version that produces the cleanest table. A generated total can be wrong even if individual rows look correct. Recalculate small tables by hand or in a spreadsheet. Separate missing amounts from zero and count excluded records. This makes the summary's denominator visible and prevents a partial dataset from being described as a complete financial picture.
PUT IT INTO PRACTICE
Create a checked action table from sample meeting notes.
PROMPT & REVIEW
Try this brief
Extract each action from this sample transcript into Task, Owner, Due date and Source excerpt. Write “not specified” for missing values.
Check the result
Check every row against the transcript, including a sample with no stated deadline.
04Research and learn with evidence
- Separate explanations from claims that need an external source.
- Use search and source links where available; check the actual source.
- Ask for practice questions and assess your own understanding.
What you will understand
An assistant can suggest useful search terms or sources, but a plausible title is not evidence that a page exists or supports a claim. Open the page, identify its publisher and locate the relevant passage. If browsing is unavailable, use an instructor-provided reference excerpt and record that limited scope. Learning prompts should ask for an explanation plus an example that can be checked. A definition alone encourages recognition without application. When studying averages, learners calculate one small dataset, describe what the result means and identify what it cannot show. This creates a concrete test of both learner and assistant understanding. Answer practice questions before viewing the model answer. Then compare reasoning, not just final numbers. Ask why an alternative answer fails and make a new example yourself. Riverstone Learning's study assistant supports this process, but the learner remains responsible for attempting retrieval instead of passively rereading fluent explanations.
PUT IT INTO PRACTICE
Build a short learning brief with a source-checking record.
PROMPT & REVIEW
Try this brief
Create a beginner study brief about the topic below. Separate explanations from claims needing verification. Suggest sources I can check and finish with three practice questions.
Check the result
Open and check the references. Answer the questions yourself and correct any misleading explanation.
05Review visual and analytical work
- Define the question before asking about an image or dataset.
- Use available file or image tools, or a text-based alternative.
- Check visual observations, totals and interpretation yourself.
What you will understand
For visual work, distinguish visible elements from interpretation. A course poster can show a missing label; it cannot prove users will abandon enrolment. Ask the assistant to list observable issues, then test any usability hypothesis separately. When image upload is unavailable, describe the layout faithfully and label the description as a substitute. A completion rate requires a numerator and denominator chosen for the question. Mixing enrolled learners with visitors yields a different metric. Write units, period and exclusions before computation. Riverstone Learning's sample results can teach this without claiming real performance or uploading identifiable learner records into a third-party service. A difference between groups is an observation, not proof that a course or design caused it. Other explanations include cohort size, prior experience and missing records. A useful analysis states the measured difference and proposes what further evidence would distinguish explanations. Avoid converting small classroom examples into marketing success claims.
PUT IT INTO PRACTICE
Create a readable summary from a small sample table and verify its totals.
PROMPT & REVIEW
Try this brief
Using the sample table below, calculate totals by category and show the calculation method. Flag missing amounts instead of treating them as zero.
Check the result
Recalculate totals in a spreadsheet or by hand and compare every category with the source.
06Build a reusable work routine
- Keep task instructions and reference material organised.
- Record prompt versions, expected results and failure cases.
- Use human review before sending, publishing or acting on outputs.
What you will understand
Reusable instructions describe stable requirements such as headings and unknown-value handling. Fresh source notes belong in a separate input block. This separation lets Riverstone Learning update facts without accidentally changing the procedure. A saved document is sufficient; optional account features are conveniences rather than prerequisites for learning the method. A template that succeeds on one clean input may fail on missing or contradictory data. Prepare normal, incomplete and conflicting cases before revising. Define expected facts for each manually. Compare outputs with these answers so the evaluation detects invented owners and dates rather than merely judging presentation or verbosity. A draft-to-review workflow ends with someone checking and approving the result. State who reviews factual claims, what stops release and how work continues when the assistant is unavailable. Generating a document does not authorise sending it. This distinction makes the routine teachable and prevents convenient automation from silently expanding its scope.
PUT IT INTO PRACTICE
Present a complete prompt workflow with three sample inputs and a review record.
PROMPT & REVIEW
Try this brief
Prepare a weekly update using this instruction template and new sample notes. Keep the requested headings and list any facts you could not establish.
Check the result
Test three different inputs, record failures and revise the template without adding unsupported assumptions.
AFTER THE CORE COURSE
Advanced extension.
07Evaluate prompts with a benchmark
- Benchmarks make quality comparable
- Hold out cases to detect overfitting
- Measure uncertainty and trade-offs
ADVANCED PRACTICE
A small prompt benchmark
08Design safe multi-step assistant workflows
- Stages need explicit contracts
- Treat source instructions as data
- Clinics test the complete handoff
ADVANCED PRACTICE
Extraction-to-draft review pipeline
Complete both four-hour extension modules and a four-hour project clinic. Entry uses the core project and readiness evidence.
BRING THE SKILLS TOGETHER
A checked weekly work assistant
Build a routine that turns fictional meeting notes and a small task table into a weekly update. Save your prompts, verify the source facts and record improvements across three example inputs.
Your project deliverables
- Reusable task instructions and prompt versions
- Checked weekly updates with a source and calculation review
- A workflow guide covering account requirements, limitations and approval steps
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.
Do I need to complete AI Foundations first?
It is a useful starting point if you are new to AI, but it is not a compulsory prerequisite. This course includes a prompting recap and develops the skill through every module.
Is a paid ChatGPT plan or API key required?
This outline teaches the ChatGPT application, not API development. We confirm account access and any paid features before training; a simpler exercise can use the features available to you. Software subscriptions are not advertised as included.
Is this an official OpenAI course?
No. This is an independent Hawa Academy course outline and does not imply OpenAI affiliation, certification or endorsement.
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.