Build AI-powered systems / TWA · Enugu

AI Engineering:
build an application you can evaluate.

A model response is only one part of an AI-powered system. Explore how data, software integration, evaluation and deployment decisions turn a demonstration into something people can inspect and use responsibly.

What if the handbook has no answer?

  1. Question
  2. Retrieve
  3. Respond
  4. Evaluate

No model is connected. The example shows an application decision that should be designed and tested.

Using an AI tool and engineering an AI application are different tasks

Imagine a fictional assistant answering questions about an organisation’s public handbook. A user interface receives a question, software retrieves relevant material and a model proposes an answer. The engineering responsibility includes access, error handling, evidence and what the application does when the handbook does not contain the answer.

An AI engineer may work with software developers, data specialists and product owners. Building a larger model is not the only kind of work in this field. Integration choices and evaluation can matter even when the model is accessed through an API rather than trained from scratch.

Make data and software foundations visible

Python, data handling, APIs and basic programming make it easier to understand inputs, outputs and failure cases. Model selection and evaluation add questions about the intended task and acceptable errors. TWA’s existing direction includes these foundations, embeddings, retrieval-augmented generation, AI workflows and deployment/monitoring concepts.

Microsoft’s RAG documentation explains the role of retrieving grounding material for a generative application. Retrieval is not proof that a generated answer is correct. Google’s evaluation guidance also emphasises assessing responses against criteria. These are industry references, not a guarantee that TWA includes a particular provider, model or evaluation service.

The TWA practice studio / Guided first steps

Help a library assistant answer from evidence.

A visitor asks when a fictional library closes today. An old page says 17:00, today’s notice says 15:00 and a café menu mentions 14:00.

Your role: Choose useful evidence, write a bounded answer and make its source checkable.

What you’ll learn: Use current source information to constrain and check an assistant’s answer.

Read the full guided story without the interactive controls

You can follow the same lesson here without JavaScript.

  1. See why a plausible answer can fail

    Try the archived page and compare its date with the question about today.

    What happens and why: The archive says 17:00 for last year. Repeating it would not establish today’s hours. A fluent answer can still rely on stale information.

  2. Retrieve evidence that answers the question

    Choose documents to bring into the answer workspace. Include today’s library notice.

    What happens and why: Retrieval means bringing relevant information into context. Today’s library notice supports 15:00; a café menu is about a different service and the archive is superseded.

  3. Draft only what the evidence supports

    Write the closing time shown by the current notice. Do not infer other opening arrangements.

    What happens and why: The supported time is 15:00 today for maintenance. Validation compares an answer with the source; it does not require inventing extra detail.

  4. Make verification part of the answer

    Attach the current notice as a citation and require the assistant to abstain when current evidence is absent.

    What happens and why: A citation lets the reader inspect support. Abstention means saying the evidence is insufficient instead of inventing an answer. No model or real library is connected.

Takeaway: Retrieve relevant, current evidence, limit the answer to its support and make verification possible. If the evidence is missing, acknowledge that limit.

Where this is useful: Useful when designing document assistants, help centres and evidence-based AI workflows.

A fictional educational example, not a confirmed TWA assignment, assessment or learner outcome. Simplified to explore one idea; real situations need context and authorised procedures.

Optional deeper exploration: open the original technical workspace

Want to explore the technical model?

The guided story above introduces the idea. This original workspace lets you try actions in different orders. It has its own reset and does not inherit your story choices.

Retrieval
Bringing relevant source information into the answer context.
Validation
Checking an answer against evidence and requirements.
Citation
A reference that lets a reader inspect the supporting source.
Abstention
Declining to assert an answer when support is insufficient.
TWA / The practice studio

Evidence before an answer.

Learning objective: Retrieve relevant current evidence and validate a bounded response.

Explore · Observe · Explain

A fictional library assistant is asked when the library closes today. No model or real library is connected.

Evidence desk

Archived page
Last year: closes 17:00
Current notice
Today: closes 15:00 for maintenance
Unrelated document
Café menu: lunch until 14:00
Worked explanation & takeaway — available without JavaScript

Retrieve the current library notice, cite it, and restrict the answer to its scope. Similar-looking or stale evidence can produce a confident wrong answer. If current evidence is excluded, abstain and request a current source rather than invent a closing time.

Fictional educational model. No live system, personal assessment or confirmed TWA assignment. All actions run locally in your browser.

Explore the idea / software

What if the handbook has no answer?

No model is connected. The example shows an application decision that should be designed and tested.

  1. Question

    Receive a task within a stated scope.

  2. Retrieve

    Look for relevant permitted material.

  3. Respond

    Generate an answer or an honest limitation.

  4. Evaluate

    Compare the result with the expected behaviour.

Read both scenarios and explanations

Relevant evidence is available

Use the permitted material, preserve its context and check whether the response actually answers the question. A citation alone is not a correctness test.

The answer is missing

Say that the available material does not establish the answer and provide an appropriate human follow-up. Do not invent a policy to keep the conversation flowing.

An educational illustration using fictional situations. It is not a confirmed TWA assignment, live system, assessment or promise of a particular tool.

Define the missing-answer behaviour before the impressive demo

For the fictional handbook assistant, list questions the material can answer and questions it cannot. A useful test case records the question, relevant source, expected behaviour and observed result. An answer that sounds confident but invents a policy should fail that case even if its grammar is excellent.

Consider the full path: retrieving the wrong passage, retrieving nothing, a model or network failure, and a request the application is not authorised to perform. A safe-looking prompt does not replace access controls in ordinary application code. Keep private information out of a prototype unless the access and data-handling arrangements are approved.

Illustrative project brief

A public-handbook assistant evaluation pack

Prototype or design an assistant using a short fictional handbook and sample questions. Keep the material non-sensitive and make missing answers explicit.

What you could document

  • A system/data-access diagram
  • A small labelled question set including unanswerable cases
  • A prototype or application-flow description
  • An evaluation report with failures, changes and limitations

What makes the explanation useful?

A reviewer should be able to distinguish retrieved evidence from a generated claim and reproduce why a case passed or failed. Fluency alone is not the success criterion.

The learning plan determines actual activities and assessment. These deliverables are examples, not contractual curriculum outcomes.

Improve the system through evidence

Compare a small baseline with a changed retrieval rule or prompt using the same cases. Document both improvements and regressions. A single successful example is not evidence that every future question will work. Include a way for a person to review a result and understand its limitations.

Deeper directions can involve applied AI development, machine-learning engineering or platform operation, depending on foundations and scope. Discuss your programming and data experience with TWA. AI Engineering has enquiry-based fees; it is not automatically covered by the fixed data or cloud engineering prices.

TWA learning direction / Confirm your starting point

Discuss a suitable starting point.

Programming and data experience help; the starting point is agreed around your existing skills. Ask about Python/API readiness, model access, equipment, usage costs and whether an additional foundation route is needed.

Learners building toward AI development, with a starting level agreed around their programming and data experience.

Our physical centre is at No. 7 Nkpokiti Road, Ogui, Enugu, opposite Flamingo Mall. Learners elsewhere in Southeast Nigeria, across Nigeria and internationally can discuss suitable arrangements. Delivery, eligibility and availability need confirmation.

Ask about prerequisites and scope →

Existing TWA learning areas to discuss

  • Python, data handling and machine-learning foundations
  • Model selection, training and evaluation concepts
  • Large language models, APIs and application integration
  • Embeddings, retrieval-augmented generation (RAG) and AI workflows
  • Deployment, monitoring and responsible AI engineering

These are learning directions rather than a fixed syllabus. Confirm the actual tools, activities, equipment, schedule and assessment before committing.

Industry reading

References inform the explanations above. They do not imply a TWA partnership, accreditation or included software licence.

Questions about AI Engineering.

Must I train a model from scratch?

Not every AI application requires training a new model. The intended task, data and software constraints guide that decision.

Does RAG remove hallucinations?

No. Retrieval can provide material, but relevance, access, generation and evaluation still need attention.

Which models and usage costs are included?

Those details are not confirmed here. Ask TWA about the actual platform, access, scope and any costs before enrolling.

Training options & enquiries

Understand your options.
Plan your next step.

Discuss programme scope and fees, or request a personalised private quotation for international training. Availability is confirmed with TWA.

Choose the training arrangement you want to discuss. TWA will confirm eligibility, learning needs and delivery arrangements with you.

Nigerian learners: discuss scope and fees

This programme has enquiry-based pricing. The approved fixed-fee matrix does not automatically apply to AI Engineering. Describe your experience, goals and preferred arrangement so TWA can confirm the scope, fee and availability.

No fixed three-level syllabus, cohort date or available place is implied. Confirm the actual package and duration with TWA before committing.

International learners / Private training

A private learning plan.
A personalised quotation.

Discuss private training around your current experience, learning objectives, desired specialisation, preferred schedule and time zone, duration, delivery arrangements and individual learning needs. TWA will confirm what can be offered before you commit.

International training uses personalised quotations. Nigerian fees are not applied or converted into another currency. Schedules, duration and delivery must be agreed with TWA; a request does not confirm availability.