Available Dates & Venues
No dates are currently available for this course.
Introduction
In business services, technology, government and industry, professionals regularly work with workplace tasks, approved AI tools and relevant data. Clear methods, accurate information and sound judgement help teams manage complexity, improve communication and avoid preventable errors.
An advanced application-development program covering modern LLM architectures, retrieval-augmented generation, tool use and agentic workflows. The focus is on designing useful, testable and governed enterprise applications rather than experimenting without controls.
This programme is designed for professionals, managers, analysts and technical teams. Through structured exercises, guided discussion and a course-specific case, participants connect the subject to workplace needs and identify practical steps for further development.
Objectives
The course aims to build the knowledge, applied judgement and clear communication needed to approach building llm applications, rag & ai agents with confidence.
By the end of the course, participants should be able to:
- Design an LLM application architecture around a defined business use case.
- Implement retrieval-augmented generation concepts and data grounding.
- Build tool-enabled and agentic workflows at a practical level.
- Evaluate quality, latency, cost and safety trade-offs.
- Plan deployment, monitoring and governance for production use.
- Explain the purpose, scope and essential terminology of building llm applications, rag & ai agents.
- Identify key inputs and professional responsibilities relevant to embeddings, vector search and rag.
Training Methodology
Training combines structured explanations with practical opportunities to apply, discuss and review learning.
The course includes:
- Instructor-guided explanations of llm application architecture and the relevant professional context.
- Worked examples and guided exercises addressing embeddings, vector search and rag.
- Approved-tool or fictional task demonstrations.
- Prompt and output quality review.
- Workplace workflow and adoption case exercises.
- Case review, group feedback and practical application of evaluation, observability and guardrails.
- Short knowledge checks and a final action or revision plan to support further learning.
Organisational Impact
Organisations can use this programme to strengthen responsible AI adoption and review of business outputs and develop the capability of relevant teams.
The training is designed to help organisations:
- Create a shared understanding of LLM application architecture among relevant team members.
- Improve the consistency of responsible AI adoption and review of business outputs.
- Encourage well-supported decisions about tool use and structured outputs.
- Strengthen communication, record keeping and review across responsible functions.
- Identify capability gaps linked to evaluation, observability and guardrails for targeted follow-up.
- Use a practical a reviewed, role-specific AI use case as a starting point for coaching or operational improvement.
Corporate delivery can be discussed around the team’s roles, operational context and agreed learning priorities.
Personal Impact
Participants will gain:
- A clearer understanding of the principal concepts behind building llm applications, rag & ai agents.
- Improved ability to discuss embeddings, vector search and rag with colleagues.
- Guided practice in tool use and structured outputs.
- Greater confidence in examining data, assumptions, documents or workplace evidence.
- Experience evaluating case decisions linked to evaluation, observability and guardrails.
- Feedback that supports further progress in practical AI use, human review and workflow improvement.
- A personal workplace application or revision plan to continue learning.
Who Should Attend?
This course is intended for:
- Business professionals and functional teams
- Managers and transformation leaders
- Analysts and process improvement staff
- Technical developers where relevant
- HR, finance, legal and procurement specialists
- Staff involved in responsible AI adoption
Recommended preparation: Working knowledge of Python and APIs is recommended.
Certificates
Upon successful completion of the programme and its published completion requirements, participants may receive a GenTechSkills Certificate of Completion.
The certificate documents course completion and is not presented as a third-party professional certification unless an approved arrangement is separately stated.
Course materials, digital platform access and any optional assessment arrangements should be confirmed in the quotation.
Course Schedule and Corporate Training
Contact GenTechSkills to discuss available dates, delivery options, teaching language and course fees.
For a corporate proposal, share your team size, experience level, preferred schedule and learning priorities.
Request Schedule & Fees | Request Corporate Training
Related Courses
- Generative AI & Prompt Engineering for Workplace Productivity.
- AI for Leaders: Strategy, Governance & Value Creation.
- AI Fundamentals for Business Professionals.
- AI for HR & Talent Management.
- AI for Finance & Financial Planning.
- AI for Procurement & Supply Chain.
Take the Next Step
Develop your building llm applications, rag & ai agents capability through a focused learning plan or explore a relevant corporate programme for your team.
Enquire About Building LLM Applications, RAG & AI Agents Training
Curriculum
- 4 Sections
- 28 Lessons
- 4 Days
- Day 1: LLM application architecture7 Items
- 1.1LLM application architecture.
- 1.2Compare model, application and orchestration responsibilities
- 1.3Define latency and quality requirements
- 1.4Inputs, records and relevant assumptions for llm application architecture.
- 1.5Applied exercise, feedback and review of common misunderstandings
- 1.6Summary of learning priorities and connection to the wider programme.
- 1.7Practical workshop: Sketch a bounded architecture.
- Day 2: Embeddings, vector search and RAG and Tool use and structured outputs7 Items
- 2.1Embeddings, vector search and RAG.
- 2.2Chunk documents, build retrieval and examine relevance
- 2.3Related requirements, data inputs and practical judgements for embeddings, vector search and rag
- 2.4Tool use and structured outputs.
- 2.5Validate structured outputs and tool arguments
- 2.6Restrict permissions
- 2.7Practical workshop: Complete linked exercises: compare retrieval settings on a supplied corpus; implement a controlled tool call.
- Day 3: Agentic workflow patterns and Evaluation, observability and guardrails7 Items
- 3.1Agentic workflow patterns.
- 3.2Design explicit workflow states, stopping conditions and human approvals
- 3.3Related requirements, data inputs and practical judgements for agentic workflow patterns
- 3.4Evaluation, observability and guardrails.
- 3.5Create evaluation cases for groundedness, prompt injection and tool misuse
- 3.6Related requirements, data inputs and practical judgements for evaluation, observability and guardrails
- 3.7Practical workshop: Complete linked exercises: build a limited multi-step agent; record failures and corrective controls.
- Day 4: Deployment, cost and governance7 Items
- 4.1Deployment, cost and governance.
- 4.2Estimate token cost and latency
- 4.3Plan versioning, rollback and monitoring
- 4.4Inputs, records and relevant assumptions for deployment, cost and governance.
- 4.5Applied exercise, feedback and review of common misunderstandings.
- 4.6Summary of learning priorities and connection to the wider programme.
- 4.7Practical workshop: Present a deployable prototype and operational checklist.






