Core Programme · Module I of CEAL

Generative AI & prompt engineering.

From AI fundamentals through to advanced prompt engineering and real-world application. Participants leave with a personal prompt library, tested workflows, and the C.L.E.A.R. framework mastered on their own work scenarios.

10 modules 60%+ hands-on 1 – 2 days Foundation to Intermediate STOA certified
Andrej Karpathy
Why this programme exists
"A failure to claim the 10X boost from AI feels decidedly like a skill issue."
Andrej Karpathy · OpenAI co-founder, former Director of AI at Tesla
Duration
2 days
Format
Live online or on site
Next open date
Private cohorts
Fee
$1,299 per delegate
includes all materials + certificate
For teams
Private cohort from 8 delegates
Schedule a TNA call
Programme overview

What this programme covers.

This two-day programme is built for professionals across every business function who work with generative AI tools such as ChatGPT, Claude, Microsoft Copilot and Gemini. The quality of what these tools produce depends directly on the quality of the instructions they are given. Prompt engineering is the discipline of structuring those instructions so that AI produces relevant, production-ready results. It is the first of STOA's three core programmes and Module I of the Certified Enterprise AI Leader certification.

Day one opens with the foundations of generative AI: the history of the field and its scaling laws, how large language models work, tokens, context windows and model settings, and where the leading models differ. Participants then learn the C.L.E.A.R. prompt engineering framework and practise the core techniques of K-shot and chain-of-thought prompting on their own work tasks, before moving on to advanced strategies: multi-step, tree-of-thought, meta and multi-modal prompting. Day two covers structured evaluation of AI outputs and responsible use, applied use cases across writing, data analysis, documentation and IT support, agentic prompting and reusable agent skills, and closes with scaling generative AI across a team and the capstone action plan.

By the end of the programme, participants have a personal prompt library of tested prompts for their role, a set of saved, reusable agent skills that work across AI platforms, and a ninety-day action plan for applying generative AI in their daily work. They leave prepared for the next phase of AI at work: agentic AI, where a system is given a goal and plans and carries out the multi-step work itself, with context engineering, retrieval-augmented generation and the Model Context Protocol behind it.

Who should attend

This programme is designed for executives, directors, managers, team leaders and professionals across every business function who want to apply prompt engineering to their day-to-day work:

  • Directors, managers and team leads in HR, finance, sales, marketing, customer support and operations
  • Business analysts, data analysts and reporting specialists
  • Project managers, programme managers and PMO staff
  • Learning and development managers, HR business partners and internal trainers
  • IT service desk, support and helpdesk teams
  • Executive assistants, office managers and administration teams

Learning outcomes

  • Explain how large language models work
  • Write reliable prompts using the C.L.E.A.R. framework
  • Apply K-shot and chain-of-thought prompting to daily tasks
  • Solve complex tasks with multi-step, tree-of-thought and meta prompting
  • Evaluate AI outputs for quality, bias and hallucinations
  • Use AI responsibly within privacy and governance requirements
  • Apply generative AI to writing, data analysis, documentation and IT support
  • Apply agentic prompting to delegate multi-step work to AI agents
  • Build saved, reusable agent skills that work across AI platforms
  • Plan team adoption and an organisational prompt library
  • Build a personal prompt library and a ninety-day action plan
Programme outline

Ten modules. Sixty percent hands-on.

Each module follows the TEA™ framework, twenty percent theory, twenty percent examples, sixty percent hands-on application on your own work scenarios.

Day 1: Generative AI Foundations and the C.L.E.A.R. Framework

01
Day 1 · Module

Introduction to Generative AI

  • Welcome, introductions and participant objectives
  • What is generative AI?
  • The history of AI and scaling laws
  • The competitive landscape (OpenAI, Anthropic, Google, Microsoft, Meta, Mistral)
  • How large language models work:
    • Next-token prediction
    • Training data, pre-training and fine-tuning
    • Chat models and reasoning models
  • Key terminology for professionals (LLM, prompt, token, context window, hallucination, agent)
Live demonstration the calculator test
02
Day 1 · Module

Foundations of Generative AI

  • Transformer architecture fundamentals
  • Tokens, context windows and model memory
  • Temperature and model settings
  • Capabilities and limitations:
    • Hallucination and non-determinism
    • Knowledge cutoffs and live data
    • Confidential data and permitted inputs
  • Comparing the leading models (ChatGPT, Claude, Gemini, Microsoft Copilot)
Individual and pair work one work task run across the leading models
03
Day 1 · Module

The C.L.E.A.R. Prompt Engineering Framework

  • The anatomy of a strong prompt
  • Command: task, persona and output format
  • Layer: context, constraints and scope
  • Examples: showing what good output looks like
  • Assess: evaluating output before use
  • Refine: iterating with follow-up prompts
  • C.L.E.A.R. across platforms and roles
Hands-on exercise applying C.L.E.A.R. to participants' own work scenarios
04
Day 1 · Module

Core Prompting Techniques

  • K-shot prompting (zero-shot, one-shot, few-shot, multi-shot)
  • Chain-of-thought and zero-shot chain-of-thought prompting
  • Role, context and constraint prompting
  • Structured outputs (tables, summaries, memos, JSON)
  • Common prompting errors and their corrections
  • The prompt loop (draft, test, refine, save)
  • Saved prompts and the personal prompt library
Hands-on exercise building the first prompts of the personal prompt library
05
Day 1 · Module

Advanced Prompt Strategies

  • Multi-step prompting and prompt chaining
  • Tree-of-thought prompting
  • Meta prompting
  • Multi-modal prompting with text, images, files and long documents
  • Choosing the strategy for the task
Individual and pair work prompt chaining and tree-of-thought on a complex work task

Day 2: Evaluation, Applied Use, Agentic Prompting and Scaling

06
Day 2 · Module

Evaluating AI Outputs and Responsible Use

  • Identifying hallucinations and fabricated content
  • Critical evaluation methods and quality benchmarks
  • Interpretability and model limitations
  • Verification of AI output before use
  • Bias detection and mitigation
  • Privacy and confidential data handling
  • Governance frameworks and responsible-use guidelines
  • The regulatory landscape (EU AI Act, ISO/IEC 42001, NIST AI RMF)
Hands-on exercise evaluating and improving real AI outputs for hallucinations, bias and confidential data
07
Day 2 · Module

Use Cases and Applications

  • AI for writing (emails, reports, summaries, proposals)
  • Data analysis, tables and structured outputs
  • Meeting notes, minutes and documentation
  • Research and summarisation of long documents
  • IT support and troubleshooting
  • Vibe coding and vibe flowcharting
  • Role-specific use cases across HR, finance, sales, marketing, customer support and operations
Gamified task use-case tournament across the functions in the room
08
Day 2 · Module

Agentic Prompting and Reusable Agent Skills

  • From single prompts to agentic workflows
  • What is an AI agent?
  • Planning and task decomposition
  • Tool use and function calling
  • Guardrails, permissions and human review points
  • Custom assistants (custom GPTs, Claude Projects, Copilot agents)
  • Saved, reusable and tool-agnostic agent skills
  • Beyond prompt engineering:
    • Context engineering
    • Loop engineering and graph engineering
    • Retrieval-augmented generation (RAG)
    • Model Context Protocol (MCP)
Hands-on exercise creating a reusable agent skill for a multi-step work scenario
09
Day 2 · Module

Scaling Generative AI

  • Team adoption strategies
  • Organisational prompt libraries and shared agent skills
  • Integration planning with existing tools and workflows
  • Measuring ROI on AI adoption
  • Change management for AI
  • The personal AI toolkit
  • Maintaining and updating the prompt library
  • Staying current as models and tools evolve
Reflection and feedback adoption barriers and quick wins in participants' own teams
10
Day 2 · Module

Capstone: Personal Action Plans

  • The ninety-day plan (priority use case, next steps, timeline, owners)
  • Committing to the first workflows
  • Support and follow-up options
Personal action planning each participant's ninety-day generative AI plan, with peer review
Day 2 · Course closing

Course closing

  • Course debrief and key takeaways
  • Final Q&A
  • Official closing ceremony and award of certificates
  • Group photo
Proprietary framework

The C.L.E.A.R. prompt engineering framework.

Our signature methodology for structured AI prompting. Taught across every STOA programme, it works across any AI platform and any professional role.

C

Command

Define the task clearly. Persona, format, and specificity markers.

L

Layer

Add context, constraints, and scope. Role, audience, tone, boundaries.

E

Examples

Show what good output looks like. Two to five references work best.

A

Assess

Evaluate the output critically before using it. Facts, tone, completeness.

R

Refine

Iterate through follow-up prompts. Two to three rounds is normal.

Our training methodology

Three frameworks behind every programme.

Whatever programme you choose, it follows three proven instructional frameworks, from design to delivery to evaluation.

Delivery

TEA™ Delivery Framework

  • T Theory, core concepts & frameworks
  • E Examples, live demos & case studies
  • A Application, hands-on exercises & practice

Our signature approach structures every module into three phases for maximum retention and practical application.

Design

ADDIE Instructional Design

  • A Analyse, assess learner needs
  • D Design, structure the learning path
  • D Develop, build materials & activities
  • I Implement, deliver the programme
  • E Evaluate, measure outcomes & refine

The industry-standard model for course design and learning alignment.

Evaluation

Kirkpatrick Model

  • L1 Reaction, participant satisfaction
  • L2 Learning, knowledge & skills gained
  • L3 Behaviour, on-the-job application
  • L4 Results, business impact & ROI

The globally recognised four-level framework for measuring training effectiveness, from initial reaction to long-lasting post-training effects.

Upcoming sessions

Choose your date.

Open-enrolment dates below. Need a private session for your team? Schedule a TNA call, custom proposal within 48 hours, delivery in as little as three weeks.

Date
Format
Duration
Price
Loading available dates…
What every participant gets

You keep everything.

No vendor lock-in, no paywalled materials. Every delegate leaves with the working files, the templates, and the post-programme support to actually use them.

Personal prompt library

8 – 12 tested prompts built during the session on your actual work scenarios.

Templates & dashboards

Dashboards, workflow templates, and evaluation frameworks ready to use.

Learning materials

Full soft copy of all session materials, handouts, and reference guides.

STOA certificate

Certificate of Completion plus a guided pathway to the Google AI certificate.

30-day support

Post-programme Q&A availability and implementation guidance.

Lifetime updates

Access to updated prompt libraries and resources as AI tools evolve.

Delivery options

Choose how your team learns.

In-Person

Instructor-led on-site

Delivered at your offices or venue. Maximum engagement for teams of 8 – 25 participants. All exercises use your team's actual work scenarios.

Live Online

Virtual instructor-led

Real-time delivery via Zoom, Meet, or Teams. Interactive breakout rooms, same content depth as in-person. Ideal for distributed teams.

Hybrid

Blended approach

Combine in-person and virtual sessions. Flexible scheduling across time zones. Pre-work materials and follow-up resources included.

Training catalogue

104 courses in nine families, overview level, methodology up front.

Download the catalogue
Ready to start

Give your team the AI skills that actually stick.

Join the next open session or book a private programme for your team. Custom proposal within 48 hours. Delivery in as little as three weeks.