AI & DIGITAL SKILLS MAGAZINE Learn from beginner to expert
Contact EDITION 2026
ISHRAQA7 — The practical digital learning magazine
ISHRAQA 7 ACADEMY · Artificial intelligence

ChatGPT and Generative AI: from essentials to a professional project

Twelve practical chapters covering prompts, professional writing, critical research, file analysis and human-reviewed outputs, with a capstone project and downloadable resources.

  • LevelBeginner → Intermediate
  • Course programme12 modules
  • Course filesPDF · CSV · JSON · TXT · ZIP

Also available in العربية Français

A hands-on, structured, verifiable twelve-chapter course. Fictional training data, not real ISHRAQA7 performance.

Twelve-chapter curriculum

  1. Generative AI: principles, capabilities and limits
  2. Using ChatGPT and organizing your work
  3. Writing precise, verifiable prompts
  4. Improving outputs through iteration and evaluation
  5. Professional writing, synthesis and documents
  6. Research, sources and fact-checking
  7. Analyzing files, tables and data
  8. Creating responsible editorial and visual content
  9. Building reusable productivity workflows
  10. Advanced capabilities and durable methods
  11. Privacy, bias, rights and human oversight
  12. Capstone: a complete, verifiable document workflow

1. Generative AI: principles, capabilities and limits

Workplace application · Beginner to intermediate

A fictional service company receives eighteen customer requests. It only wants to sort them into information, support and complaint. An assistant can propose triage labels; it cannot know the contract or promise a response. An ambiguous request must remain marked as needing confirmation.

Method and workflow — CLEAR method

Generated output is neither evidence nor access to an infallible database. A conversational model creates plausible language from the supplied context and patterns learned in training. It can help organize ideas, draft text and explore alternatives, yet a polished answer may contain a wrong date, an invented citation or an unchecked calculation. Distinguish drafting, analysis of supplied material and external research: these tasks require different evidence standards.

Before prompting, write a one-sentence objective, define which data may be shared and assign a human reviewer. For drafting, check clarity and fit. For analysis, reconcile figures against source rows. For research, open the cited documents and examine author, date and scope. Label important claims as verified, plausible or requiring validation.

Example prompt

Classify the practice requests as information, support, complaint or needs confirmation. Use only description_en. Return ID, category, evidence, missing information. Do not invent identities or deadlines and do not contact customers.

Independent exercise

Open ia01-demandes-clients-en.csv, classify at least ten records and identify three decisions requiring human confirmation. Re-check every suggested category against the original sentence.

Quality safeguard

Fluent language is not proof. Never upload real personal customer information for this exercise.

Knowledge check

1. Which principle applies to the chapter “Generative AI: principles, capabilities and limits”?

  1. Every citation displayed by AI must be real.
  2. Fluency does not establish factual accuracy.
  3. Long answers guarantee accuracy.
2. What should a responsible team do in a similar case?

  1. Ambiguous cases must be classified randomly.
  2. All ambiguous rows should be deleted.
  3. Ambiguous customer cases should be marked for confirmation.
3. Which control reduces professional errors?

  1. Reconcile generated numbers with source data.
  2. AI numbers never require checking.
  3. Charts alone validate all calculations.

2. Using ChatGPT and organizing your work

Workplace application · Beginner to intermediate

A service manager prepares reply guidance for colleagues. Three deliverables are required: an intake register, response drafts and an approval checklist. Combining them in an unstructured request often hides missing assumptions.

Method and workflow — CLEAR method

Assistant interfaces evolve by plan, device and workspace configuration. The durable skill is organizing a brief, limiting context and documenting decisions, not memorizing button locations. One sprawling conversation may mix unrelated goals and make decisions hard to trace. Separate work by deliverable and keep verified decisions in an external project log.

Create a fictional working folder named Customer welcome pilot. Write five lines covering outcome, audience, permitted data, format and reviewer. Use one conversation for request classification and a separate one for drafting. At each milestone ask for a decision summary; record only checked statements in the project log.

Example prompt

Act as a preparation assistant. We need an approval checklist for classifying fictional customer requests. Propose document sections, required inputs and three open questions. Do not draft customer replies yet.

Independent exercise

Write a 120-word project brief and a decision log recording date, assumption, evidence and approving person. Revise the brief when you discover that priority data is missing.

Quality safeguard

Check which organization features your own account actually provides; menus vary by plan and interface.

Knowledge check

1. Which principle applies to the chapter “Using ChatGPT and organizing your work”?

  1. Starting without a goal improves traceability.
  2. Every task should share one long conversation.
  3. Define a deliverable before opening a conversation.
2. What should a responsible team do in a similar case?

  1. Separate deliverables to simplify review.
  2. A single chat replaces a decision log.
  3. Assumptions should never be recorded.
3. Which control reduces professional errors?

  1. Settings never change over time.
  2. Check actual interface availability.
  3. Every account has identical menus.

3. Writing precise, verifiable prompts

Workplace application · Beginner to intermediate

A team needs a brief note based on eighteen fictional requests. Its manager has two minutes to read it. The note must state trends and uncertainties, without invented quantities or resolution dates.

Method and workflow — CLEAR method

A useful prompt is not a magic phrase. It turns a task into an output contract covering outcome, audience, sources, constraints and success criteria. 'Make a good summary' specifies none of these. 'Summarize for a nontechnical team in 150 words and separate verified facts from open questions' produces an output that can be checked.

Use the CLEAR structure: Context, Learning goal, Evidence, Allowed limits and Requested format. State nonnegotiable items, then instruct the assistant to label missing information instead of guessing. Distinguish task instructions from quoted source material. Review the output against the checklist yourself.

Example prompt

Based only on the attached CSV, write a 130–160 word summary for the service manager. Use counts only when they can be recomputed, separate observation from assumption and end with two decisions requiring confirmation. Do not invent deadlines.

Independent exercise

Rewrite three vague instructions ('summarize', 'make a plan', 'improve the text') as complete CLEAR prompts. Create a five-criterion rubric and score two example outputs from zero to two per criterion.

Quality safeguard

Asking an assistant to 'verify everything' is not independent verification.

Knowledge check

1. Which principle applies to the chapter “Writing precise, verifiable prompts”?

  1. A prompt includes explicit success criteria.
  2. Good prompts never need context.
  3. Output length is never relevant.
2. What should a responsible team do in a similar case?

  1. Vague prompts are reliably more accurate.
  2. Keep supplied evidence separate from instructions.
  3. Remove all format constraints.
3. Which control reduces professional errors?

  1. Missing fields justify plausible inventions.
  2. Unknown names can be selected at random.
  3. Flag missing information rather than guessing.

4. Improving outputs through iteration and evaluation

Workplace application · Beginner to intermediate

An early triage prompt forces all tickets into three categories. Review shows two ambiguous entries wrongly labeled. A later version adds needs confirmation and an evidence field.

Method and workflow — CLEAR method

Prompt improvement should be a controlled cycle, not a random sequence of rewordings. Fix a test set, keep input data stable and change one factor at a time: instructions, examples, format or evaluation criterion. Scoring must separate accuracy, completeness, clarity and risk. Without stable test cases, a new response may merely look better because the question changed.

Create three repeatable test tasks: classification, synthesis and drafting. Score the first result on four criteria from zero to four. Change one instruction and repeat with the same input. Keep both outputs and accept the revision only when it improves quality without breaching a critical constraint.

Example prompt

Compare both versions of this request table for fidelity, uncertainty handling, format and clarity. Suggest one targeted instruction change; avoid rewriting everything at once.

Independent exercise

Run or simulate V0, V1 and V2 on five requests. Log the single variable changed, resulting score and a justified stopping rule.

Quality safeguard

Model-generated self-scores may be biased; spot-check ratings against the supplied evidence.

Knowledge check

1. Which principle applies to the chapter “Improving outputs through iteration and evaluation”?

  1. Testing needs no success criteria.
  2. Compare on a stable set of test cases.
  3. Changing everything at once improves attribution.
2. What should a responsible team do in a similar case?

  1. Longer output is always superior.
  2. Appearance outranks factual quality.
  3. Change one factor at a time when evaluating.
3. Which control reduces professional errors?

  1. Reject critical invented facts even if a score rises.
  2. Ignore errors when scores increase.
  3. Publish the latest result without review.

5. Professional writing, synthesis and documents

Workplace application · Beginner to intermediate

A fictional training center prepares meeting minutes: three decisions were made, but no delivery date was agreed. The minutes must show each action and owner while keeping the deadline as not set.

Method and workflow — CLEAR method

AI-assisted writing should support editorial judgment rather than replace it. An effective meeting record separates facts, decisions and actions; an email states audience and requested action without inventing deadlines; a strategic note distinguishes assumptions. Elegant tone does not cure missing evidence.

Provide a writing brief naming audience, channel, tone, approved facts and structure. Use two stages: outline and missing-information check, then draft. Mark uncertain statements. Review people, dates, obligations and any wording that might create a commitment before sharing.

Example prompt

Turn the supplied notes into minutes of at most 300 words: objectives, confirmed decisions, actions and open questions. Add no dates and flag missing owners. Draft a separate circulation email but do not send it.

Independent exercise

Produce minutes and a short colleague email from fictional notes. Compare the two documents for factual fidelity, level of detail and ambiguity.

Quality safeguard

Never invent quotations from attendees or contractual commitments absent from the source notes.

Knowledge check

1. Which principle applies to the chapter “Professional writing, synthesis and documents”?

  1. Mix assumptions with approved decisions.
  2. Inventing deadlines makes text professional.
  3. Separate facts, decisions and actions in minutes.
2. What should a responsible team do in a similar case?

  1. Use approved information when drafting.
  2. Fluency licenses invented quotations.
  3. Tone makes name checking unnecessary.
3. Which control reduces professional errors?

  1. Delete actions without known owners.
  2. Mark a missing deadline as not set.
  3. Pick a random date.

6. Research, sources and fact-checking

Workplace application · Beginner to intermediate

An internal brief says an AI service includes a particular function. A manager must check whether their own workspace can use it, without treating an old blog post or advertising claim as authoritative evidence.

Method and workflow — CLEAR method

Assisted research has two parts: locating evidence and interpreting it correctly. A URL alone is insufficient; you must open the document and check the specific claim. Prices, models and legal requirements change over time. If search is unavailable, an assistant should state that current availability cannot be confirmed rather than implying it was checked.

Create a claim register with claim, primary source, checking date and verification status. For each important statement, consult official documentation, capture the relevant passage and record limitations. Distinguish missing source, inconclusive source and verified claim. Add a date to every time-sensitive statement.

Example prompt

Create a claim-verification table for this draft. For each claim, list the official source type needed, staleness risk and access conditions to check. Do not label availability as verified without evidence.

Independent exercise

Take three claims from the fictional register. Identify primary sources and complete the verification statuses. Where evidence is missing, write a transparent conditional statement.

Quality safeguard

'The assistant cited a source' is different from 'I read and checked the source'.

Knowledge check

1. Which principle applies to the chapter “Research, sources and fact-checking”?

  1. Open and check the cited source.
  2. Any link confirms a claim regardless of content.
  3. Current information needs no date.
2. What should a responsible team do in a similar case?

  1. Prices never change.
  2. Use primary documentation for availability claims.
  3. Advertising is definitive technical evidence.
3. Which control reduces professional errors?

  1. Treat uncertainty as fact.
  2. Avoid keeping verification dates.
  3. Label unverified information clearly.

7. Analyzing files, tables and data

Workplace application · Beginner to intermediate

A fictional team compares six training campaigns. It needs total spending and a list of budget overruns. One campaign is on hold, so its inclusion in the total must be defined explicitly.

Method and workflow — CLEAR method

Useful analysis starts with a data dictionary: every column has a meaning, unit and handling rule. Tables may contain duplicates, missing values or incompatible units. Before reporting a KPI, inspect dates, scope, row counts and calculation rules. Independently reproduce important calculations; a polished chart is not proof of correctness.

Open ia01-budget-campagne-en.csv, document its fields and units (MAD), and check time periods. Recalculate totals from rows rather than accepting a single AI-generated figure. Separate budgeted and actual spending, and define variance as actual minus planned. Verify at least two records manually.

Example prompt

Analyze only the CSV attached. Report columns, row count, missing values and statuses. Calculate total planned and actual amounts in MAD, show the variance formula and provide row-level calculations. Identify and justify exclusions.

Independent exercise

Recalculate planned and actual spending for three campaigns, compare with model output and explain each difference using source records or a stated exclusion rule.

Quality safeguard

Never present a total without documenting its status filter, dates and currency.

Knowledge check

1. Which principle applies to the chapter “Analyzing files, tables and data”?

  1. Ignore duplicate records by default.
  2. Check units and scope before computing KPIs.
  3. Add incompatible currencies directly.
2. What should a responsible team do in a similar case?

  1. Accept totals without a formula.
  2. A tidy chart verifies all arithmetic.
  3. Recompute totals from source rows.
3. Which control reduces professional errors?

  1. Document inclusion and exclusion rules.
  2. Delete statuses silently.
  3. Treat a chart as the sole evidence.

8. Creating responsible editorial and visual content

Workplace application · Beginner to intermediate

ISHRAQA7 Académie drafts a fictional workshop announcement about checking AI-generated claims. The brief provides no price or confirmed date. The content must remain attractive without inventing event details or testimonials.

Method and workflow — CLEAR method

AI-assisted content accelerates ideation, but editorial quality requires a strategy: audience, purpose, message, channel, visual identity and source checking. Distinguish documentary photography, an illustrative generated scene and a genuine product screenshot. A generated image is not evidence of a real event or actual interface. Review image rights, trademarks and personal likenesses before publication.

Write a creative brief covering promise, angle, audience, forbidden claims, CTA and evidence sources. Draft three accurate headline candidates rather than optimizing only for clicks. For images specify the scene, setting, light, framing, alt text and illustrative status. Seek editorial approval for the combined package.

Example prompt

From this practice brief, write three informative headlines, a 90-word summary, a program CTA and a realistic illustration brief without logos or fake interfaces. Add no prices, dates or testimonials.

Independent exercise

Create a magazine card, social caption and longer description. Provide accurate image alt text and a prepublication claim-check list.

Quality safeguard

Do not fabricate endorsements, statistics, official logos or deceptive screenshots.

Knowledge check

1. Which principle applies to the chapter “Creating responsible editorial and visual content”?

  1. Present generated imagery as evidence of an event.
  2. Invent testimonials to build trust.
  3. Distinguish genuine photography from illustration.
2. What should a responsible team do in a similar case?

  1. Stay faithful to audience and brief.
  2. Click-through rates justify sensational misinformation.
  3. Image rights never matter.
3. Which control reduces professional errors?

  1. Hide all information about image provenance.
  2. Write descriptive alt text.
  3. Use keyword stuffing as alt text.

9. Building reusable productivity workflows

Workplace application · Beginner to intermediate

A team prepares a Friday request summary. If source records are missing, the workflow must stop. No message is sent automatically to any recipient.

Method and workflow — CLEAR method

A professional workflow defines who provides inputs, which transformations are authorized and who approves the output. Reusable prompts need named variables, exception handling and stopping rules. Automating an unclear decision does not make it reliable. Responsibility matters when content could reach customers or involve confidential documents.

Map intake, input checks, preparation, assisted drafting, independent checking, human approval and archiving. State success and stop criteria for every step. Build a prompt template with explicit variables. Test once with valid fictional tickets and again with a missing mandatory field.

Example prompt

Design a seven-stage weekly reporting workflow using practice requests. For each stage define input, output, check, owner and stop condition. Do not include any automatic send action.

Independent exercise

Draw a simple workflow and draft a five-variable prompt template: period, audience, source, format and reviewer. Test normal data and data without a reporting period.

Quality safeguard

A documented workflow may remain manual; do not call it automated when no automation is implemented.

Knowledge check

1. Which principle applies to the chapter “Building reusable productivity workflows”?

  1. Define stop conditions before distribution.
  2. Automatically send every draft.
  3. Remove human approval.
2. What should a responsible team do in a similar case?

  1. Invent missing input values.
  2. Test missing mandatory fields.
  3. A workflow must always continue.
3. Which control reduces professional errors?

  1. Document only the first screen.
  2. Ignore decision logging.
  3. Document input, output and owner for each stage.

10. Advanced capabilities and durable methods

Workplace application · Beginner to intermediate

A team wants a chart from the training budget. Some accounts may provide a data-analysis tool while others may not. The required outcome remains a recomputed metric and clearly labeled chart.

Method and workflow — CLEAR method

Assistant capabilities evolve with product, plan and geography: file analysis, web search, workspace tools, image creation and service connections. A responsible course never promises a button to every learner. Teach prerequisite checking—account access, authorization, supported files and limits—and provide an alternative when a feature is unavailable.

Build a matrix of need, capability, observed availability, restriction and fallback. Consult dated official guidance. Run a short non-sensitive test and record whether a feature was actually used or merely described. Prepare a manual option, such as exporting a CSV and verifying calculations independently.

Example prompt

Describe two ways to chart budget-campagne: one using file-analysis tools if available, and a manual alternative with explicit calculations. State prerequisites and checks required.

Independent exercise

Create an access matrix for research, files, images and collaboration. Record only what is observed in your own account, and specify a fallback for unavailable capabilities.

Quality safeguard

Avoid undated claims about prices, quotas or model versions.

Knowledge check

1. Which principle applies to the chapter “Advanced capabilities and durable methods”?

  1. Product features never change.
  2. Check capabilities for the actual account.
  3. Every account has identical access.
2. What should a responsible team do in a similar case?

  1. Stop learning if an optional tool is missing.
  2. Assume premium access without evidence.
  3. Provide fallbacks for unavailable functions.
3. Which control reduces professional errors?

  1. Record tests actually performed.
  2. Claim a feature was tested when only described.
  3. Quote quotas without a verification date.

11. Privacy, bias, rights and human oversight

Workplace application · Beginner to intermediate

A fictional HR team wants to assess applications. An assistant might help draft objective job-related criteria but must not autonomously decide employment outcomes or infer sensitive attributes.

Method and workflow — CLEAR method

Risk depends on context, not only on the model. Fictional requests can be used for practice; real case files with names, contracts or health data require a separate privacy and authorization assessment. Assistants may reproduce bias, and generated content may raise copyright or trademark questions. Put human oversight before consequential action.

Classify information as public, internal, confidential or prohibited. Document purpose, retention and permitted access according to organizational policy. Replace personal identifiers with practice codes. Review advice from multiple perspectives, record exceptions and establish a written approval step.

Example prompt

Help design fair, job-related assessment criteria for a fictional exercise. Do not rank real people, infer sensitive traits or make hiring decisions. Include human review and bias checks.

Independent exercise

Review ten example data fields (name, phone, skill, API secret, etc.), decide what belongs in a practice dataset and prepare a risk register plus approval checkpoint.

Quality safeguard

Retention and privacy settings depend on service and workspace: consult the relevant current documentation.

Knowledge check

1. Which principle applies to the chapter “Privacy, bias, rights and human oversight”?

  1. Upload passwords to speed up work.
  2. HR files need no special care.
  3. Remove unnecessary sensitive information.
2. What should a responsible team do in a similar case?

  1. Document risk and human approval.
  2. AI alone should determine employment outcomes.
  3. Assistant recommendations cannot be biased.
3. Which control reduces professional errors?

  1. Generated content never raises third-party rights issues.
  2. Review rights and image provenance.
  3. Brand marks have no usage rules.

12. Capstone: a complete, verifiable document workflow

Workplace application · Beginner to intermediate

A fictional training organization wants the distribution of incoming requests and spending across six campaigns. It is not requesting predictions or autonomous commercial decisions. A sourced report with assumptions and proposed actions is sufficient.

Method and workflow — CLEAR method

The capstone combines briefing, practice-data analysis, drafting and quality assurance. It can be completed manually without a paid account; if an assistant is available, its use is optional and documented. Quality is not word count: it is a traceable chain in which every number links back to source rows and uncertainty is explicit.

Create a Monthly service report folder. Define the audience and acceptance criteria; check the eighteen practice requests and fictional campaign budget; write a 250-word factual summary; draft an unsent circulation email; assemble a claim register and unresolved-issues list; request human peer approval.

Example prompt

Propose a report outline for a review committee based on the practice files. Separate computable facts, cautious interpretations and decisions awaiting confirmation. Add a numeric provenance table and prepublication checklist. Invent no statistics.

Independent exercise

Submit four deliverables: report, claims register, calculation checks and an unsent transmission email. Explain two model limitations and one decision postponed for lack of evidence.

Quality safeguard

Generated output is not an approved project until a responsible person has reviewed its evidence and risks.

Knowledge check

1. Which principle applies to the chapter “Capstone: a complete, verifiable document workflow”?

  1. Link every reported number to source rows.
  2. Invent metrics for missing data.
  3. Present assumptions as established facts.
2. What should a responsible team do in a similar case?

  1. Ignore ambiguous records.
  2. Keep a verification register.
  3. Discard evidence after generation.
3. Which control reduces professional errors?

  1. Automatically send generated emails.
  2. Trust only the assistant's self-score.
  3. Get human approval before distribution.

Check your knowledge

1. Generative AI: principles, capabilities and limits
1. Which principle applies to the chapter “Generative AI: principles, capabilities and limits”?
2. What should a responsible team do in a similar case?
3. Which control reduces professional errors?
2. Using ChatGPT and organizing your work
1. Which principle applies to the chapter “Using ChatGPT and organizing your work”?
2. What should a responsible team do in a similar case?
3. Which control reduces professional errors?
3. Writing precise, verifiable prompts
1. Which principle applies to the chapter “Writing precise, verifiable prompts”?
2. What should a responsible team do in a similar case?
3. Which control reduces professional errors?
4. Improving outputs through iteration and evaluation
1. Which principle applies to the chapter “Improving outputs through iteration and evaluation”?
2. What should a responsible team do in a similar case?
3. Which control reduces professional errors?
5. Professional writing, synthesis and documents
1. Which principle applies to the chapter “Professional writing, synthesis and documents”?
2. What should a responsible team do in a similar case?
3. Which control reduces professional errors?
6. Research, sources and fact-checking
1. Which principle applies to the chapter “Research, sources and fact-checking”?
2. What should a responsible team do in a similar case?
3. Which control reduces professional errors?
7. Analyzing files, tables and data
1. Which principle applies to the chapter “Analyzing files, tables and data”?
2. What should a responsible team do in a similar case?
3. Which control reduces professional errors?
8. Creating responsible editorial and visual content
1. Which principle applies to the chapter “Creating responsible editorial and visual content”?
2. What should a responsible team do in a similar case?
3. Which control reduces professional errors?
9. Building reusable productivity workflows
1. Which principle applies to the chapter “Building reusable productivity workflows”?
2. What should a responsible team do in a similar case?
3. Which control reduces professional errors?
10. Advanced capabilities and durable methods
1. Which principle applies to the chapter “Advanced capabilities and durable methods”?
2. What should a responsible team do in a similar case?
3. Which control reduces professional errors?
11. Privacy, bias, rights and human oversight
1. Which principle applies to the chapter “Privacy, bias, rights and human oversight”?
2. What should a responsible team do in a similar case?
3. Which control reduces professional errors?
12. Capstone: a complete, verifiable document workflow
1. Which principle applies to the chapter “Capstone: a complete, verifiable document workflow”?
2. What should a responsible team do in a similar case?
3. Which control reduces professional errors?

Glossary for this page

The key terms used in this content, each with a short definition.

prompt
The instruction you write for an AI assistant: goal, context, task and expected answer format.
generative AI
The branch of AI that produces new content (text, images, audio, code) from a written request.
workflow
The sequence of steps a task follows from start to finish, across people or apps.
CSV
A plain text file with delimiter-separated values; the most common format for moving data between programs.
key performance indicator
A figure tracked regularly to measure progress toward a specific goal, such as margin or delay rate.
automation
Making a repetitive task run by itself according to a rule: when this happens, do that.
API
An interface that lets two programs exchange data and commands in a standard way.

Course files

Choose a language, then the format you need.

العربية

FileFormatSizeDownload
الدليل المهني الشامل PDF 1.3 MB Download — الدليل المهني الشامل (PDF)
كراسة التمارين PDF 1.0 MB Download — كراسة التمارين (PDF)
كتاب التصحيح المشروح PDF 1.0 MB Download — كتاب التصحيح المشروح (PDF)
المشروع النهائي التطبيقي PDF 1001 KB Download — المشروع النهائي التطبيقي (PDF)
بطاقات منهجية PDF 1011 KB Download — بطاقات منهجية (PDF)
الأمان والخصوصية PDF 1007 KB Download — الأمان والخصوصية (PDF)
دليل البدء PDF 1005 KB Download — دليل البدء (PDF)
مكتبة الطلبات المشروحة CSV 20 KB Download — مكتبة الطلبات المشروحة (CSV)
بيانات طلبات العملاء التدريبية CSV 1 KB Download — بيانات طلبات العملاء التدريبية (CSV)
سجل الادعاءات المطلوب التحقق منها CSV 1 KB Download — سجل الادعاءات المطلوب التحقق منها (CSV)
سير عمل تجريبي تحت إشراف JSON 1 KB Download — سير عمل تجريبي تحت إشراف (JSON)
شبكة تقييم الجودة CSV 5 KB Download — شبكة تقييم الجودة (CSV)
قائمة التحقق قبل النشر TXT 3 KB Download — قائمة التحقق قبل النشر (TXT)
تعليمات التمارين TXT 7 KB Download — تعليمات التمارين (TXT)
حقيبة تطبيقية كاملة — بيانات وقوالب وطلبات (دون ملفات PDF) ZIP 12 KB Download — حقيبة تطبيقية كاملة — بيانات وقوالب وطلبات (دون ملفات PDF) (ZIP)
Practice campaign budget Shared CSV 1 KB Download — Practice campaign budget (CSV)

Français

FileFormatSizeDownload
Manuel professionnel PDF 1.2 MB Download — Manuel professionnel (PDF)
Cahier d’exercices PDF 1015 KB Download — Cahier d’exercices (PDF)
Corrigés commentés PDF 1.0 MB Download — Corrigés commentés (PDF)
Projet final guidé PDF 992 KB Download — Projet final guidé (PDF)
Fiches méthodes PDF 1000 KB Download — Fiches méthodes (PDF)
Sécurité et confidentialité PDF 997 KB Download — Sécurité et confidentialité (PDF)
Guide de prise en main PDF 995 KB Download — Guide de prise en main (PDF)
Bibliothèque de prompts commentés CSV 17 KB Download — Bibliothèque de prompts commentés (CSV)
Données d’exercice : demandes clients CSV 1 KB Download — Données d’exercice : demandes clients (CSV)
Registre des affirmations à vérifier CSV 1 KB Download — Registre des affirmations à vérifier (CSV)
Workflow supervisé de démonstration JSON 1 KB Download — Workflow supervisé de démonstration (JSON)
Grille de validation CSV 5 KB Download — Grille de validation (CSV)
Check-list de publication TXT 2 KB Download — Check-list de publication (TXT)
Consignes d’exercices TXT 6 KB Download — Consignes d’exercices (TXT)
Kit pratique complet — données, modèles et prompts (sans PDF) ZIP 12 KB Download — Kit pratique complet — données, modèles et prompts (sans PDF) (ZIP)
Practice campaign budget Shared CSV 1 KB Download — Practice campaign budget (CSV)

English

FileFormatSizeDownload
Professional course manual PDF 1.2 MB Download — Professional course manual (PDF)
Practice workbook PDF 1013 KB Download — Practice workbook (PDF)
Worked answer book PDF 1.0 MB Download — Worked answer book (PDF)
Guided capstone project PDF 990 KB Download — Guided capstone project (PDF)
Method cards PDF 998 KB Download — Method cards (PDF)
Security and privacy PDF 995 KB Download — Security and privacy (PDF)
Getting-started guide PDF 994 KB Download — Getting-started guide (PDF)
Commented prompt library CSV 14 KB Download — Commented prompt library (CSV)
Practice customer requests CSV 1 KB Download — Practice customer requests (CSV)
Claims verification register CSV 1 KB Download — Claims verification register (CSV)
Supervised sample workflow JSON 1 KB Download — Supervised sample workflow (JSON)
Quality assessment grid CSV 4 KB Download — Quality assessment grid (CSV)
Publication checklist TXT 2 KB Download — Publication checklist (TXT)
Practice instructions TXT 5 KB Download — Practice instructions (TXT)
Complete practice kit — data, templates and prompts (no PDFs) ZIP 11 KB Download — Complete practice kit — data, templates and prompts (no PDFs) (ZIP)
Practice campaign budget Shared CSV 1 KB Download — Practice campaign budget (CSV)