Skip to content

Applied AI programme

Applied Generative AI Bootcamp

Build, evaluate and ship reliable LLM features: prompting, RAG, agents and safety.

Programme length
Per cohort
Weekly time
Per cohort
4 portfolio projects
9 modules
Part-time · Intermediate
Live online
Request a call back

Curriculum PDF

Applied Generative AI Bootcamp

Get the detailed curriculum

Enter your mobile number and the PDF downloads straight away.

By continuing you agree that ActuateMinds may call or message you about this programme. We never sell your number. See our privacy policy.

Who it's for

Is this programme for you?

The Applied Generative AI Bootcamp is for developers, analysts and product professionals with basic Python who want to build real features on large language models. You will learn how LLMs behave, write and test prompts, build retrieval-augmented generation, use tools and agents, evaluate quality, manage safety and cost, and ship a working AI feature reviewed by practitioners.

A good fit if you are

  • Software engineers who want to add LLM-powered features to products they already build.
  • Data analysts and data scientists who want to apply language models to text-heavy workflows.
  • Product managers with some coding comfort who want hands-on understanding of what AI features can and cannot do.
  • Technical founders prototyping AI products who need a disciplined approach to quality and cost.
  • Recent computer science or engineering graduates who can write basic Python and want applied AI experience.

Probably not if

  • Complete beginners to programming; you should be able to write and run simple Python scripts before starting.
  • People looking to train foundation models from scratch or pursue machine learning research.
  • Anyone wanting a no-code overview of AI tools for general productivity.

Curriculum

What you will learn

9 modules, each ending in a piece of real work you keep for your portfolio.

Curriculum PDF

Applied Generative AI Bootcamp

Get the detailed curriculum

Enter your mobile number and the PDF downloads straight away.

By continuing you agree that ActuateMinds may call or message you about this programme. We never sell your number. See our privacy policy.

  1. Module 1

    How large language models work

    Build an accurate mental model of what LLMs do, so you can predict their strengths and failure modes.

    • Tokens, embeddings and next-token prediction
    • Context windows, temperature and sampling
    • Comparing hosted and open-weight models
    • Hallucination and why it happens
    • Cost, latency and rate limits in practice
  2. Module 2

    Working with model APIs

    Call LLMs from Python reliably, handle errors and get outputs your code can depend on.

    • Chat completion APIs and message roles
    • Streaming responses
    • Structured outputs with JSON schemas
    • Retries, timeouts and error handling
    • Managing API keys and secrets safely

    You'll produce: Command-line assistant that returns validated structured output

  3. Module 3

    Prompt engineering

    Write prompts as engineered artefacts: versioned, tested and improved against evidence.

    • Instructions, context and examples
    • Few-shot prompting and output formatting
    • Breaking tasks into chains of prompts
    • Reasoning prompts and their trade-offs
    • Prompt versioning and regression testing
  4. Module 4

    Evaluating LLM applications

    Measure quality before you ship, so changes to prompts or models are decisions rather than guesses.

    • Building a representative evaluation set
    • Rule-based checks and reference comparisons
    • Using a model as a judge, and its limits
    • Human review and annotation guidelines
    • Tracking quality, cost and latency together

    You'll produce: Evaluation harness for a prompt-based feature

  5. Module 5

    Retrieval-augmented generation

    Ground model answers in your own documents, with citations users can check.

    • Document loading and chunking strategies
    • Embeddings and vector databases
    • Hybrid search and re-ranking
    • Citing sources and handling unanswerable questions
    • Evaluating retrieval and answer quality separately

    You'll produce: RAG assistant over a document collection with source citations

  6. Module 6

    Tool use and agents

    Let models take actions through tools, while keeping their behaviour predictable and bounded.

    • Function calling and tool schemas
    • Planning loops and agent patterns
    • Model Context Protocol and tool integrations
    • Limiting steps, permissions and side effects
    • When a simple workflow beats an agent
  7. Module 7

    Safety, privacy and responsible use

    Protect users and organisations from the specific risks that LLM features introduce.

    • Prompt injection and data exfiltration
    • Handling personal data and India's DPDP Act basics
    • Content moderation and output filtering
    • Bias, fairness and transparency with users
    • Human oversight for high-stakes decisions
  8. Module 8

    Shipping an AI feature

    Move from a notebook to a small service that others can use, monitor and improve.

    • Wrapping a pipeline in a FastAPI service
    • Building a simple interface with Streamlit
    • Logging, tracing and feedback capture
    • Caching and cost control
    • Fallbacks and graceful failure

    You'll produce: Deployed AI application with logging and an evaluation report

  9. Module 9

    AI product thinking

    Decide which problems are suited to generative AI and design experiences that earn user trust.

    • Identifying good and poor use cases
    • Designing for uncertainty and user correction
    • Measuring impact beyond model accuracy
    • Build, buy or prompt: making the call
    • Presenting an AI feature proposal

Schedule

Live class schedule

The live-class schedule is published with each cohort. Your advisor will share it before you enrol.

  • Live sessions

    Interactive classes with practitioners

  • Weekly projects

    Every module ends in a deliverable

  • Mentor feedback

    Written reviews on your work

  • Peer learning

    Critique and study with your cohort

Mentorship

Get personalised feedback from mentors

Each cohort is paired with engineers and practitioners who build LLM applications, and who review your code, evaluation approach and design decisions.

  1. Small-group build sessions where mentors debug pipelines and discuss design choices with you.

  2. Scheduled one-to-one sessions to scope your capstone and plan how to apply AI in your current or target role.

  3. Code reviews on your repositories with specific feedback on reliability, safety and structure.

  4. Capstone reviews that test whether your evaluation results support the claims you make about your feature.

Career support

Get ready for the interview loop

Preparation, not promises — we don’t guarantee jobs; hiring decisions belong to employers.

  • Project portfolio review

    Present your repositories and demos so that reviewers can see what you built, how you tested it and its limits.

  • Resume and LinkedIn review

    Describe your AI projects accurately and specifically, without overstating what they do.

  • Mock technical interviews

    Practise explaining LLM system design, RAG trade-offs and evaluation choices, with feedback.

  • Internal pitch preparation

    For working professionals, prepare a proposal to introduce an AI feature or workflow in your current organisation.

  • Referral readiness

    Prepare a concise summary and demo links so you can respond quickly when a referral opportunity appears.

  • Job board access

    Follow AI and engineering roles on the ActuateMinds job board and plan applications around your project work.

Have more questions or need more information?

Request a call back

Portfolio

What you'll build

Portfolio-ready work, reviewed by mentors.

  • Project 1

    Support ticket triage assistant

    Build a service that classifies incoming support tickets, extracts key fields into a structured format and drafts a first reply. Evaluate accuracy against a labelled set and report where it fails.

    • Prompt engineering
    • Structured outputs
    • LLM evaluation
  • Project 2

    Policy document question-answering

    Create a RAG assistant that answers questions about a set of public policy or HR documents with citations. Measure retrieval quality and handle questions the documents cannot answer.

    • Retrieval-augmented generation
    • Embeddings and vector search
    • LLM evaluation
  • Project 3

    Analyst agent with tool access

    Build an agent that can query a sample database through a safe SQL tool and summarise the result. Restrict its permissions, log every action and test it against prompt injection attempts.

    • Function calling and tool use
    • Agent design
    • AI safety and guardrails
  • Project 4

    Capstone: ship an AI feature

    Identify a real problem in your work or community, build an AI feature to address it and deploy it with logging and evaluation. Present the product case, quality results and known limits to a mentor panel.

    • API development
    • AI product thinking
    • Cost and latency optimisation

See the project showcase

Toolkit

Tools you will learn

  • Python
  • OpenAI API
  • Anthropic Claude API
  • LangChain
  • LlamaIndex
  • Chroma
  • pgvector
  • FastAPI
  • Streamlit
  • Jupyter
Specimen

Certificate of completion

Your Name

has completed the required projects of the Applied Generative AI Bootcamp.

Issued on completing the required projects
Illustrative certificate with a placeholder name

Certificate

Certificate of completion

Awarded once you complete the programme's required projects. The reviewed projects themselves are what you'll show employers.

Timeline

Programme timeline

Module order may be refined between cohorts. Week-by-week dates are shared with each cohort.

  1. Kick-off

    Dates are confirmed per cohort.

  2. Module 1: How large language models work

    Build an accurate mental model of what LLMs do, so you can predict their strengths and failure modes.

  3. Module 2: Working with model APIs

    Produce: Command-line assistant that returns validated structured output

  4. Module 3: Prompt engineering

    Write prompts as engineered artefacts: versioned, tested and improved against evidence.

  5. Module 4: Evaluating LLM applications

    Produce: Evaluation harness for a prompt-based feature

  6. Module 5: Retrieval-augmented generation

    Produce: RAG assistant over a document collection with source citations

  7. Module 6: Tool use and agents

    Let models take actions through tools, while keeping their behaviour predictable and bounded.

  8. Module 7: Safety, privacy and responsible use

    Protect users and organisations from the specific risks that LLM features introduce.

  9. Module 8: Shipping an AI feature

    Produce: Deployed AI application with logging and an evaluation report

  10. Module 9: AI product thinking

    Decide which problems are suited to generative AI and design experiences that earn user trust.

  11. Wrap-up

    Complete the required projects to earn your certificate.

Admissions

Eligibility

  • Able to write and run basic Python: functions, lists, dictionaries and installing packages.
  • Typically suited to engineers, analysts and technical product professionals, as well as recent technical graduates.
  • Comfortable using the command line and Git at a basic level, or willing to learn them in pre-work.
  • A laptop that can run Python locally, plus willingness to set up API accounts with model providers.
  • Able to attend live sessions and build projects alongside work or study.
  1. Apply online

    Tell us about your technical background, current role and what you want to build with generative AI.

  2. Advisor conversation

    Discuss your goals, the schedule and fees with an admissions advisor. Fees are shared during this conversation.

  3. Technical fit check

    Complete a short Python exercise so we can confirm you are ready for the pace of the bootcamp.

  4. Offer and onboarding

    Accept your offer, complete enrolment and work through pre-work covering environment setup and API basics.

FAQs

Frequently asked questions

How much does the Applied Generative AI Bootcamp cost?

Fees are shared during your advisor conversation, where we also explain what is included and any payment options available. We publish fees on this page once they are confirmed for the cohort. Separately, you may incur small usage charges from model providers when you run your projects, and your advisor will explain how to keep these low.

What schedule should I expect?

The bootcamp combines live sessions with hands-on building between them. Session timings and the time commitment you should plan for are confirmed per cohort. Your advisor will go through them with you. Because the work is project-based, expect to spend focused time coding and debugging outside live sessions, not only attending them.

Will I be able to rewatch sessions?

Whether sessions are recorded, and how catch-up material is provided, is confirmed per cohort and explained in your advisor conversation. Live build sessions are where mentors help you debug and reason through design choices, which is hard to get from a recording. We recommend planning to attend live and treating any catch-up material as a backup.

What do I need to know before joining?

You should be able to write and run basic Python scripts, including functions, lists and dictionaries, and install packages. Familiarity with APIs, JSON and Git is helpful. You do not need a machine learning background. If you are new to Python, build that foundation first; the technical fit check helps us confirm you are ready.

Will this help me get an AI engineering job?

It will help you build demonstrable skills and projects, but we do not guarantee jobs or titles. Career support includes portfolio and resume reviews, mock technical interviews, referral readiness and job board access. Many learners use the bootcamp to bring AI into their current role, and mentors can help you plan either path realistically.

Do I get a certificate?

Yes. A certificate of completion is issued when you complete the required projects, including the capstone. For AI roles, a working, well-evaluated project that you can explain in depth usually says more than a certificate, so the bootcamp is designed around building and documenting real applications you can share with employers or your team.

Which models and frameworks will we use?

You will work with hosted model APIs such as those from OpenAI and Anthropic, and frameworks such as LangChain and LlamaIndex, alongside plain Python so you understand what the frameworks do underneath. The field changes quickly, so the curriculum focuses on principles like evaluation, retrieval and safety that remain useful as specific models and libraries change.

What is the refund policy?

Refunds are covered by our published refund policy at /refund-policy, which sets out the conditions and timelines. Please read it before enrolling. If you have questions about how it applies to you, your admissions advisor can explain the details for your cohort so you can make an informed decision before you pay.

Still have questions?

Request a call back for personalised guidance on fit, schedule and fee.

Request a call back

Talk to an advisor

Prefer to talk first?

Leave your details and an advisor will walk you through the schedule, fee and fit. No obligation.

Related resources

From the Journal

More articles →

Applied AI2 min read

Evaluating LLM features before you ship them

Demos are easy; reliable AI features are not. How to build a small evaluation set, choose criteria, and decide whether a feature is ready.

Call backEnrol now