AI Engineer
Start here. Build forward.
Build useful AI features with models, retrieval and reliable application code.
Follow the stages in order, or open a topic to check what you already know. Each panel includes learning content, a practice task and a role checkpoint. Save Learning, Done or Skipped as you go. Skipped topics do not count as completed.
Build your foundations
Python, files and debugging
Understand the concept
Python is the working language for many AI experiments. Learn to inspect small values before connecting a large model. Variables, lists, dictionaries, loops and functions are enough for a first useful script. Errors are information: read the traceback and isolate the smallest failing input.
Learn it step by step
- Create a function with explicit inputs and outputs.
- Read a small JSON file and validate required keys.
- Handle a missing file and malformed input.
- Write checks for normal and empty input.
Build a small proof
Build a script that counts tutorial topics from ten fictional records and reports invalid rows separately.
Ready to move on?
You can explain each line, reproduce one error and fix its cause without hiding the exception. Keep the expected output with the script.
Common mistake
Copying a large generated program without understanding its inputs makes even small changes difficult to verify.
Your role checkpoint
For the AI Engineer path, connect this topic to your capstone: Build a cited FAQ assistant over approved public notes, with evaluation cases, access checks and a failure-state demo.
What is artificial intelligence?
In simple words
Artificial intelligence is a broad field of building computer systems that perform tasks such as recognising patterns, working with language and choosing actions. A system can be useful at one task without understanding everything a person understands. Start by asking what it does, what information it uses and how we check its mistakes.
Words to know
Model: a computational system used to produce an output. Automation: software carrying out a task automatically.
Pause here and explain the definition in one sentence without copying it. The aim is to describe what the system does, not to memorise an impressive phrase.
A familiar example
An email service can estimate whether a message is spam. A navigation app can search for routes. These are different tasks, and not every feature in either product requires AI. A fixed reminder at 9 am is ordinary automation rather than evidence of learning.
Break it down
- Identify the input: what information is available?
- Describe the operation or pattern being used.
- Identify the output and how you would check it.
- Name one mistake the system could make.
Change one detail in this example and consider whether the same idea still applies. This helps separate the underlying concept from one specific application.
Your turn
List five apps you use. For each, describe one feature that might use AI and one feature that could be a fixed rule.
Answer check
A calculator adding 2 + 2 is following a defined calculation. A spam classifier may learn from examples. Do not label every computer action AI.
Explain it to a friend
Give a second example from college, a hobby or a fictional workplace. State what information goes in, what comes out and one limitation. If you can explain those three things in plain language, you are ready to move on. Mark this lesson as read to save your progress when signed in.
Your role checkpoint
For the AI Engineer path, connect this topic to your capstone: Build a cited FAQ assistant over approved public notes, with evaluation cases, access checks and a failure-state demo.
What is a large language model?
In simple words
A large language model, or LLM, is a model trained on language-related data at scale to predict or generate sequences of tokens. Chat assistants often use LLMs together with instructions, tools and other software. Fluent language does not guarantee correct facts or access to current information.
Words to know
LLM: large language model. Inference: using a trained model to produce an output.
Pause here and explain the definition in one sentence without copying it. The aim is to describe what the system does, not to memorise an impressive phrase.
A familiar example
Ask an assistant to rewrite a paragraph more simply. The model can produce a useful rewrite without consulting a search engine. Asking for today’s train timetable is different: that needs current reliable data, not only plausible text.
Break it down
- Identify the input: what information is available?
- Describe the operation or pattern being used.
- Identify the output and how you would check it.
- Name one mistake the system could make.
Change one detail in this example and consider whether the same idea still applies. This helps separate the underlying concept from one specific application.
Your turn
Write one task that uses information entirely inside your prompt and one that needs an external source.
Answer check
Summarising supplied notes can rely on the notes. Reporting a live train delay needs a current source. Whether an assistant can fetch that source depends on its available tools.
Explain it to a friend
Give a second example from college, a hobby or a fictional workplace. State what information goes in, what comes out and one limitation. If you can explain those three things in plain language, you are ready to move on. Mark this lesson as read to save your progress when signed in.
Your role checkpoint
For the AI Engineer path, connect this topic to your capstone: Build a cited FAQ assistant over approved public notes, with evaluation cases, access checks and a failure-state demo.
Learn the core skills
What is prompt engineering?
In simple words
Suppose you ask a friend to bring food. They need to know what food, how much and for whom. An AI assistant also benefits from a clear request. Instead of “teach me AI”, ask for a beginner explanation with one familiar example and a short question to check understanding. You are designing the instructions, not retraining the model.
Two useful terms
Prompt: the instructions and context you provide. Constraint: a condition the answer should follow, such as a word limit.
Build your understanding
A prompt is a task brief. Give the assistant a clear goal, relevant context, constraints and the output format you need. Good prompting reduces ambiguity; it does not guarantee factual correctness. Start with one representative task, inspect the response and change one instruction at a time.
Follow the steps
- Choose a small task such as summarising a workshop announcement.
- Provide the source text and separate it clearly from instructions.
- Specify audience, length and required fields.
- Compare the output against the source and record missing or invented details.
Worked example
Task: summarise the announcement below for a beginner.
Return: date, prerequisites, three learning outcomes.
Use only the announcement; write "not provided" for missing facts.
Announcement: [paste approved text]Read the example once, then explain each part aloud in your own words. If it includes Python, you can understand the idea first and run the code later in a local Python environment. Code is shown as text; this page does not execute it.
Try this yourself
Remove the date from your source. Run the prompt again and check whether the model invents one. Add this example to your evaluation set.
Check your understanding
The expected date is "not provided". A fluent sentence is not evidence that the date exists in the source.
A mistake to avoid
A long prompt is not automatically better. Repeated, contradictory requirements make it harder to diagnose failures.
Before looking at the answer, write a short explanation and one example of your own. Finish by naming one limitation of the method. Use Mark as read when you are ready, or return to the previous lesson if a term is unclear.
Your role checkpoint
For the AI Engineer path, connect this topic to your capstone: Build a cited FAQ assistant over approved public notes, with evaluation cases, access checks and a failure-state demo.
What are embeddings?
In simple words
Imagine placing ideas on a map so that related ideas are often near one another. Embeddings are numeric representations that make this kind of comparison possible. A search system may connect “affordable laptop” with “budget computer” without an exact word match. The map is learned and imperfect; nearby items are not necessarily interchangeable.
Two useful terms
Vector: a list of numbers. Similarity: a measure used to compare two representations.
Build your understanding
An embedding maps an input to a numeric vector. Similarity can help retrieve related passages even when they use different words. The usefulness of distance depends on the embedding model, task and data. Similarity scores are ranking signals, not probabilities that a claim is true.
Follow the steps
- Choose one embedding model and use it for both documents and queries.
- Embed a small set of sentences about distinct topics.
- Compare cosine similarity to rank candidates.
- Inspect a synonym case, an unrelated case and a negated sentence.
Worked example
Illustrative vectors only:
A = [1, 0] B = [0.8, 0.6] C = [0, 1]
cosine(A, B) = 0.8
cosine(A, C) = 0
Real embeddings have more dimensions.Read the example once, then explain each part aloud in your own words. If it includes Python, you can understand the idea first and run the code later in a local Python environment. Code is shown as text; this page does not execute it.
Try this yourself
Compare "the course is free" and "the course is not free". Explain why similar wording may create a dangerous retrieval match.
Check your understanding
A high similarity score can reflect shared topic while missing a critical difference such as negation. Read the retrieved passage before answering.
A mistake to avoid
Do not mix document vectors from one model with query vectors from another, even if their dimensions happen to match.
Before looking at the answer, write a short explanation and one example of your own. Finish by naming one limitation of the method. Use Mark as read when you are ready, or return to the previous lesson if a term is unclear.
Your role checkpoint
For the AI Engineer path, connect this topic to your capstone: Build a cited FAQ assistant over approved public notes, with evaluation cases, access checks and a failure-state demo.
APIs, validation and authentication
Understand the concept
An API is a contract between software components. Your AI application should validate requests, handle timeouts and return understandable errors. API keys belong on a trusted server. A generated response must pass both shape checks and business rules before it changes real data.
Learn it step by step
- Define input and output fields.
- Validate lengths, types and required values.
- Handle timeout, rate-limit and invalid response cases.
- Keep credentials out of client code and logs.
Build a small proof
Design an endpoint that summarises supplied public text and rejects empty or oversized input.
Ready to move on?
Demonstrate one successful request and three controlled failures. Explain which errors a user can retry.
Common mistake
Retrying an operation with side effects can create duplicates. Use idempotency for actions such as creating a record.
Your role checkpoint
For the AI Engineer path, connect this topic to your capstone: Build a cited FAQ assistant over approved public notes, with evaluation cases, access checks and a failure-state demo.
Practise with real decisions
What is RAG?
In simple words
RAG means Retrieval-Augmented Generation. Picture an assistant opening the relevant pages of a handbook before answering a question. Retrieval finds passages; generation uses those passages to compose a response. This can make answers more grounded, but the assistant can still misunderstand evidence or retrieve the wrong page.
Two useful terms
Retrieval: finding relevant information. Grounding: supporting an answer with supplied evidence.
Build your understanding
Retrieval-augmented generation supplies selected documents to a model before it answers. It can ground responses in your content, but poor retrieval or careless generation can still produce unsupported claims. Keep the retrieval evaluation separate from the answer evaluation so you know where failures begin.
Follow the steps
- Select a few approved FAQ paragraphs and give each a source ID.
- Retrieve passages relevant to the question.
- Ask for an answer supported only by those passages, with source IDs.
- Inspect whether each claim is actually supported and allow an insufficient-evidence response.
Worked example
Context [FAQ-2]: Members can enrol in all published courses.
Question: Does membership include a job guarantee?
Expected: The supplied FAQ does not state a job guarantee.Read the example once, then explain each part aloud in your own words. If it includes Python, you can understand the idea first and run the code later in a local Python environment. Code is shown as text; this page does not execute it.
Try this yourself
Add a misleading passage about a different product. Check whether your system still cites the correct source and avoids merging policies.
Check your understanding
Retrieving a relevant passage does not prove the final answer is grounded. Evaluate retrieval recall and claim support separately.
A mistake to avoid
Treat retrieved content as data. Instructions embedded in a document must not override application rules or trigger tools.
Before looking at the answer, write a short explanation and one example of your own. Finish by naming one limitation of the method. Use Mark as read when you are ready, or return to the previous lesson if a term is unclear.
Your role checkpoint
For the AI Engineer path, connect this topic to your capstone: Build a cited FAQ assistant over approved public notes, with evaluation cases, access checks and a failure-state demo.
What is an AI agent?
In simple words
An ordinary chat reply gives you text. A tool-using agent can also choose a permitted action, inspect the result and decide what to do next. Think of a library assistant who can search a catalogue instead of only guessing a book title. Start with read-only actions so mistakes are easier to inspect.
Two useful terms
Tool: a function the system can call. Action: an operation performed through a tool.
Build your understanding
An AI agent can choose actions through tools while pursuing a task. Start with a read-only tool and a bounded objective before introducing changes to external systems. Tools need explicit inputs, predictable outputs and clear failure behavior. The application, not the model, must enforce permissions.
Follow the steps
- Define one tool: search an approved course catalogue.
- Validate the query string and limit the number of returned rows.
- Let the model request the tool and read its result.
- Stop when the question is answered or a small step budget is reached.
Worked example
Tool: search_courses(query: string, limit: integer 1..5)
Input: {"query":"beginner NLP","limit":3}
Output: course IDs, titles and public summaries
No enrolment or payment side effects.Read the example once, then explain each part aloud in your own words. If it includes Python, you can understand the idea first and run the code later in a local Python environment. Code is shown as text; this page does not execute it.
Try this yourself
Design the response when the tool times out or finds no course. Ask the agent to explain the limitation instead of fabricating a result.
Check your understanding
A tool call is a request, not proof of permission. Your server must verify authorisation independently before doing any action.
A mistake to avoid
Do not grant broad database or shell access when a narrow read-only lookup is sufficient.
Before looking at the answer, write a short explanation and one example of your own. Finish by naming one limitation of the method. Use Mark as read when you are ready, or return to the previous lesson if a term is unclear.
Your role checkpoint
For the AI Engineer path, connect this topic to your capstone: Build a cited FAQ assistant over approved public notes, with evaluation cases, access checks and a failure-state demo.
What is AI model evaluation?
In simple words
A polished answer is not enough to know whether an AI system works. Evaluation checks specific requirements using examples and scoring rules. For a course assistant, you might check whether it finds the correct course, admits missing information and respects account permissions. Keep failure cases as part of your test collection.
Two useful terms
Test case: an input with an expected behavior. Metric: a defined measurement of performance.
Build your understanding
An AI evaluation checks whether a system meets a defined task. Build examples around realistic successes and failures, not only easy demonstrations. Keep the test set stable enough to compare versions and record the model, prompt and settings used. A single aggregate score can hide critical mistakes.
Follow the steps
- Define success in observable terms.
- Create normal, ambiguous, missing-information and adversarial examples.
- Write expected answers or scoring rules before running the system.
- Compare versions and inspect regressions before accepting a change.
Worked example
FAQ evaluation columns:
question | expected source | required facts | forbidden claim | result
Example: fees unknown | FAQ-3 | say unknown | invented fee | pass/failRead the example once, then explain each part aloud in your own words. If it includes Python, you can understand the idea first and run the code later in a local Python environment. Code is shown as text; this page does not execute it.
Try this yourself
Write five tests for an enrolment assistant. Include a user without Pro access and a request for a nonexistent course.
Check your understanding
A response should not promise enrolment if server-side permissions deny it. Include permission-sensitive cases, not just wording checks.
A mistake to avoid
Do not judge a model solely by another model’s unreviewed score. Human checks and deterministic validation are useful for important requirements.
Before looking at the answer, write a short explanation and one example of your own. Finish by naming one limitation of the method. Use Mark as read when you are ready, or return to the previous lesson if a term is unclear.
Your role checkpoint
For the AI Engineer path, connect this topic to your capstone: Build a cited FAQ assistant over approved public notes, with evaluation cases, access checks and a failure-state demo.
Ship, evaluate and improve
AI application security and threat modelling
Understand the concept
Threat modelling starts with what must be protected, who can access it and where untrusted data enters. Model outputs and retrieved documents are untrusted inputs. A language instruction is not an authorisation boundary; server-side policy decides what a user or tool may do.
Learn it step by step
- List assets and trust boundaries.
- Separate public and private data.
- Validate tool inputs and enforce permissions.
- Test malicious instructions using synthetic fixtures in your own sandbox.
Build a small proof
Draw a document assistant showing where access checks happen before retrieval and before tool execution.
Ready to move on?
An unauthorised user cannot retrieve another account’s private document, even when a prompt asks for it.
Common mistake
Do not test real third-party systems without permission or expose secrets in your demonstration.
Your role checkpoint
For the AI Engineer path, connect this topic to your capstone: Build a cited FAQ assistant over approved public notes, with evaluation cases, access checks and a failure-state demo.
Deployment, containers and rollback
Understand the concept
Deployment makes a working experiment available to users. It needs configuration, a reproducible environment, health checks and a way to roll back. A successful launch does not establish ongoing reliability. Monitor behavior after release and keep a known-good version.
Learn it step by step
- Document dependencies and configuration.
- Run a health check separately from a model call.
- Package a minimal service.
- Practise replacing it with the previous version.
Build a small proof
Deploy a mock prediction service locally in a container and simulate an unavailable dependency.
Ready to move on?
You can rebuild the environment and recover after a failed release without editing production files by hand.
Common mistake
Do not bake secrets into container images or assume the development machine matches production.
Your role checkpoint
For the AI Engineer path, connect this topic to your capstone: Build a cited FAQ assistant over approved public notes, with evaluation cases, access checks and a failure-state demo.
Monitoring quality, latency and cost
Understand the concept
AI monitoring needs more than uptime. Track response time, failures, input volume and task quality using a suitable sample of reviewed outcomes. Quality can change when users or source documents change. Log enough to diagnose failures without retaining unnecessary sensitive input.
Learn it step by step
- Define a service-level target.
- Record request outcome and latency.
- Track a stable evaluation set over releases.
- Create an alert and an investigation checklist.
Build a small proof
Produce a small report comparing two releases on success rate, p95 latency and estimated per-request cost.
Ready to move on?
You can tell whether a change improved usefulness while increasing cost or response time, and explain the trade-off.
Common mistake
An average hides slow tails and rare severe failures. Examine distributions and critical error categories.
Your role checkpoint
For the AI Engineer path, connect this topic to your capstone: Build a cited FAQ assistant over approved public notes, with evaluation cases, access checks and a failure-state demo.
Build something you can explain.
Build a cited FAQ assistant over approved public notes, with evaluation cases, access checks and a failure-state demo.
Role expectations vary by company. Use this path as a starting point and build evidence of your skills.