# Agentic AI

**Source**: https://shortcourses.rmit.edu.au/products/fs-agentic-ai-air201u?variant=45120543588547
**Parent**: https://www.rmit.edu.au/online/courses

powered by

# Agentic AI

Get started

[Download brochure](#dynamic-form-section)

Design systems that can plan, decide, and execute. Learn how to build and orchestrate autonomous agents that coordinate tools, data, and tasks across real workflows.

Study mode

Online

Get started

[Download brochure](#dynamic-form-section)

Next start date 

20 Apr 2026

20 Apr 2026

20 Apr 2026

 Prerequisites 

Participants should have experience with Python programming, a basic understanding of large language models (LLMs), and some familiarity working with generative AI tools or APIs.
 Time commitment 

8 weeks (6 - 8 hours per week)

$909.09

Payment options

POWERED BY

Udacity

## Level up your skills and qualifications as a digital native

Teaming up with the best in industry, our Future Skills courses lean into the future of work to deliver the best in structured, mentor-supported, 100% online education.

Why this Course
Who is this course for
What you'll learn
How it works
Prerequisites

Organisations are shifting from isolated AI use cases to end-to-end automation. That means systems that can gather information, decide what to do next, use tools, monitor progress and deliver outcomes with minimal human intervention.

This change is already showing up in the market. Demand for agentic AI capability surged in 2025, particularly across Data Scientist and Software Engineer roles, as organisations move to operationalise AI at scale ([McKinsey, 2025](https://www.mckinsey.com/capabilities/tech-and-ai/our-insights/the-top-trends-in-tech)). At the same time, the business value of agentic AI is expected to double by 2028 [(BCG, 2025)](https://www.bcg.com/publications/2025/are-you-generating-value-from-ai-the-widening-gap).

Agentic AI addresses this gap. It equips you with the capability to build autonomous and semi-autonomous systems that operate across tools, data sources and workflows. Rather than focusing on theory alone, this course is built around applied projects that mirror real implementation challenges faced by engineering teams today.

This Agentic AI course will be delivered to you in partnership with Udacity, meaning you’ll have access to both Udacity’s learning and career services as well as RMIT Online’s course enablement support through our Learner Success Team.  Upon successful completion of the course, you will also receive an RMIT credential which can be uploaded to LinkedIn, verifying your skill mastery in the discipline.

This course is designed for technically proficient professionals who want to build and orchestrate AI agents using Python and LLMs.

It’s suited to early to mid-career professionals who already work in technical or engineering roles and want to deepen their capability in AI driven automation, agent orchestration, and system design.

New to Generative AI or LLMs?

If you’re newer to Generative AI, LLMs, or the fundamentals of prompting, we strongly recommend first completing [Udacity’s Generative AI Nanodegree.](https://shortcourses.rmit.edu.au/products/fs-generative-ai-air116u) This will give you the foundational knowledge needed to get the most out of this program.

By the end of this course, you'll be able to:

- Design, implement and refine system prompts, reasoning prompts, tool definitions, and validated output schemas that enable LLMs to perform complex, multistep tasks reliably and consistently.
- Develop AI agents in Python that integrate tools, APIs, retrieval mechanisms, and short- and long term memory while managing state and interaction flow and error-handling in production-like contexts.
- Build and coordinate agentic workflows and multi agent architectures using chaining, routing, parallelisation, orchestration patterns, and explainable output design to automate end-to-end tasks aligned with defined system requirements.
- Critically evaluate and document the performance, reliability, and risks of agents and workflows using structured testing, dataset preparation, metrics, and evidence-based analysis to inform iterative improvement and system design decisions.

During this course, you’ll have the opportunity to design, build, and orchestrate agentic systems through four applied projects that mirror real-world implementation challenges.

Across the projects, you’ll progress from engineering individual agents that can reason and plan, to building workflow-driven systems that route tasks, integrate tools and APIs, manage state and memory, and coordinate multiple agents working together. Each project is designed to reflect how agentic systems are built and deployed in practice, using Python and large language models.

This program is designed for learners who are ready to build and work hands-on with generative AI systems.

You should have experience with:

- Python programming
- A basic understanding of large language models (LLMs)
- Some familiarity with working with generative AI tools or APIs

Get started

[Download brochure](#dynamic-form-section)

Get started

[Download brochure](#dynamic-form-section)

## Course Overview

Learn more about our Agentic AI course in the video below.

## Get RMIT credentialed

After completing an RMIT Future Skills course, you will earn an RMIT credential which can be validated, recognised and shared on social media platforms.

## Course Structure

Learn more about Agentic AI

Close all sections

### Module 1: Prompting for Effective LLM Reasoning and Planning

**Lesson 1: Introduction to Prompting for Effective LLM Reasoning and Planning**

Introduces the core concepts of Agentic AI, the course structure, prerequisites, and learning environment.

**Lesson 2: The Role of Prompting in Agentic AI with Python and OpenAI**

Learn what AI agents are and how prompting guides them to reason, plan, and act toward goals.

**Lesson 3: Role-Based Prompting**

Explore how roles and personas shape tone, expertise, and behaviour in agent outputs.

**Lesson 4: Implementing Role-Based Prompting with Python**

Practise building role-based prompts to create a believable historical persona.

**Lesson 5: Chain-of-Thought and ReAct Prompting**

Understand frameworks for guided reasoning and action-oriented planning.

**Lesson 6: Applying CoT and ReAct Prompting with Python**

Implement reasoning and action prompts to solve a retail analytics problem.

**Lesson 7: Prompt Instruction Refinement**

Learn systematic approaches to refining prompts across role, task, context, and output.

**Lesson 8: Applying Prompt Instruction Refinement with Python**

Iteratively refine a prompt to transform a generic tool into a structured dietary consultant.

**Lesson 9: Chaining Prompts for Agentic Reasoning**

Design multi-step workflows by chaining prompts with validation checkpoints.

**Lesson 10: Chaining Prompts with Python**

Build a three-stage prompt chain with gate checks to automate insurance claim triage.

**Lesson 11: LLM Feedback Loops**

Design systems where agents improve outputs through iterative feedback.

**Lesson 12: Implementing LLM Feedback Loops with Python**

Create a self-debugging agent that generates and tests Python code.

Project:
AgentsVille Trip Planner: Build a multi-agent travel assistant that coordinates planning, reasoning, and execution.

### Module 2: Agentic Workflows

**Lesson 1: Introduction to Agentic Workflows**

Explore the foundational concepts of agentic workflows and system setup.

**Lesson 2: Understanding Agentic Workflows**

Learn the core components of modern AI agents and workflow types.

**Lesson 3: Agentic Workflow Modeling**

Design and visualise agentic workflows using common agent patterns.

**Lesson 4: Agentic Workflow Implementation**

Translate workflow models into Python code and orchestrate agent interactions.

**Lesson 5: Prompt Chaining Workflow Pattern**

Break down complex tasks into sequential agent workflows.

**Lesson 6: Implementing Prompt Chaining with Python**

Build a multi-agent chain that passes information step by step.

**Lesson 7: Routing Workflow Pattern**

Design routing systems that dispatch tasks to specialised agents.

**Lesson 8: Implementing Routing with Python**

Create a routing agent that classifies requests and orchestrates responses.

**Lesson 9: Parallelisation Workflow Pattern**

Run multiple agent tasks concurrently and aggregate results.

**Lesson 10: Implementing Parallelisation with Python**

Use Python threading to build concurrent agent workflows.

**Lesson 11: Evaluator–Optimiser Workflow Pattern**

Iteratively improve outputs through critique and refinement loops.

**Lesson 12: Implementing Evaluator–Optimiser with Python**

Build a creator–critic system that refines outputs until constraints are met.

**Lesson 13: Orchestrator–Workers Workflow Pattern**

Design systems where a central agent plans and delegates work dynamically.

**Lesson 14: Implementing Orchestrator–Workers with Python**

Build an agentic market analysis system with specialised workers.

Project:
AI-Powered Agentic Workflow for Project Management: Create a reusable agent library and deploy it to manage a technical project.

### Module 3: Building Agents

**Lesson 1: Introduction to Building Agents**

Set up tools and environments for agent development.

**Lesson 2: Extending Agents with Tools**

Integrate tools to enable real-time actions and data access.

**Lesson 3: Building Agents with Tools in Python**

Develop and test tool-enabled agents using the OpenAI SDK.

**Lesson 4: Structured Outputs**

Transform agent responses into validated, machine-readable outputs.

**Lesson 5: Implementing Structured Outputs with Pydantic**

Create validated JSON outputs for reliable automation.

**Lesson 6: Agent State Management**

Design state machines that track context and decisions across workflows.

**Lesson 7: Implementing Agent State with Python**

Build dynamic workflows using Python state machines.

**Lesson 8: Short-Term Agent Memory**

Implement memory strategies to maintain coherence in active sessions.

**Lesson 9: Adding Agent Memory with Python**

Build persona-based agents with session continuity.

**Lesson 10: External Tools and APIs**

Integrate external APIs for real-time data and actions.

**Lesson 11: Integrating External Tools with Python**

Build agents that authenticate and interact with live systems.

**Lesson 12: Web Search Agents**

Enable agents to retrieve and ground responses in real-time information.

**Lesson 13: Creating Web Search Agents with Python**

Build a web-enabled agent using external search APIs.

**Lesson 14: Interacting with Databases**

Connect agents to SQL and vector databases.

**Lesson 15: Building Database Agents with Python**

Translate natural language into database queries.

**Lesson 16: Agentic Retrieval Augmented Generation**

Enhance RAG systems with reflection and retry loops.

**Lesson 17: Agentic RAG with Python**

Build adaptive document retrieval systems.

**Lesson 18: Long-Term Agent Memory**

Design persistent memory strategies for agents.

**Lesson 19: Maintaining Long-Term Memory with Python**

Implement long-term memory using vector databases.

**Lesson 20: Agent Evaluation**

Assess agent performance, quality, and reliability.

**Lesson 21: Evaluating Agents with Python**

Design evaluation frameworks and test cases.

Project:
UdaPlay AI Research Agent : Build a stateful research agent for the video game industry.

### Module 4: Multi-Agent Systems

**Lesson 1: Introduction to Multi-Agent Systems**

Learn the fundamentals of multi-agent architectures.

**Lesson 2: Designing Multi-Agent Architecture**

Design high-level system architectures for agent teams.

**Lesson 3: Implementing Multi-Agent Architecture with Python**

Code multi-agent systems with well-defined interfaces.

**Lesson 4: Orchestrating Agent Activities**

Coordinate agent actions across complex workflows.

**Lesson 5: Implementing Agent Orchestration**

Apply orchestration patterns for multi-step execution.

**Lesson 6: Routing and Data Flow in Agentic Systems**

Manage information flow between agents.

**Lesson 7: Implementing Routing and Data Flow**

Build intelligent routing agents.

**Lesson 8: State Management in Multi-Agent Systems**

Track and update state across agent interactions.

**Lesson 9: Implementing State Management**

Synchronise state across multiple agents.

**Lesson 10: Multi-Agent Orchestration and Coordination**

Resolve conflicts and manage shared resources.

**Lesson 11: Implementing Orchestration and Coordination**

Build concurrent multi-agent systems.

**Lesson 12: Multi-Agent Retrieval Augmented Generation**

Extend RAG systems across agent teams.

**Lesson 13: Implementing Multi-Agent RAG**

Build cooperative retrieval and synthesis agents.

Project:
 The Beaver’s Choice Paper Company Sales Team: Design and implement a complete multi-agent sales system.

Get started

[Download brochure](#dynamic-form-section)

Get started

[Download brochure](#dynamic-form-section)

## Learn with industry experts

Learner success team

RMIT Online

Our learner success team are here to help you with 1:1 coaching, tips on how to successfully study online, and any questions or concerns you may have.

Udacity’s subject matter experts

Udacity

Get personalised feedback on your projects as well as practical tips and industry best practice from Udacity’s mentor team.

## Why choose RMIT

Get a world-class education and transform your career.

### Real world skills

Develop skills that have been validated by industry, while getting credentialed by a world-leading university.

### Industry connected

You'll gain knowledge and practical skills from renowned industry partners who are at the forefront of their field.

### Flexible delivery

Advance your career while you study. RMIT Online courses let you balance work, study and life commitments.

### Supported community

Be guided by a network of industry experts and peers, and supported by our dedicated success team.

## Download a brochure

Register your interest to get a free course guide for Agentic AI.

Are you enquiring for

An individual

A business

First name \*

Last name \*

E-mail \*

Work e-mail \*

Mobile number \*

+61

- Australia (+61)
- Singapore (+65)
- Other

Job title \*

Company name \*

Number of employees \*-- Please select --1 - 2021 - 199200 - 9991000+

When do you anticipate to start learning? \*-- Please select --NowIn around 3 monthsIn around 6 monthsIn around 12 monthsNot sure yet

Expected number of learners \*-- Please select --1 - 910 - 4950 - 99100+

Country of residence \*-- Please select --AfghanistanÅland IslandsAlbaniaAlgeriaAndorraAngolaAnguillaAntigua & BarbudaArgentinaArmeniaArubaAscension IslandAustraliaAustriaAzerbaijanBahamasBahrainBangladeshBarbadosBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia & HerzegovinaBotswanaBrazilBritish Indian Ocean TerritoryBritish Virgin IslandsBruneiBulgariaBurkina FasoBurundiCambodiaCameroonCanadaCape VerdeCaribbean NetherlandsCayman IslandsCentral African RepublicChadChileChinaChristmas IslandCocos (Keeling) IslandsColombiaComorosCongo - BrazzavilleCongo - KinshasaCook IslandsCosta RicaCôte d’IvoireCroatiaCuraçaoCyprusCzechiaDenmarkDjiboutiDominicaDominican RepublicEcuadorEgyptEl SalvadorEquatorial GuineaEritreaEstoniaEswatiniEthiopiaFalkland IslandsFaroe IslandsFijiFinlandFranceFrench GuianaFrench PolynesiaFrench Southern TerritoriesGabonGambiaGeorgiaGermanyGhanaGibraltarGreeceGreenlandGrenadaGuadeloupeGuatemalaGuernseyGuineaGuinea-BissauGuyanaHaitiHondurasHong Kong SARHungaryIcelandIndiaIndonesiaIraqIrelandIsle of ManIsraelItalyJamaicaJapanJerseyJordanKazakhstanKenyaKiribatiKosovoKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyaLiechtensteinLithuaniaLuxembourgMacao SARMadagascarMalawiMalaysiaMaldivesMaliMaltaMartiniqueMauritaniaMauritiusMayotteMexicoMoldovaMonacoMongoliaMontenegroMontserratMoroccoMozambiqueMyanmar (Burma)NamibiaNauruNepalNetherlandsNew CaledoniaNew ZealandNicaraguaNigerNigeriaNiueNorfolk IslandNorth MacedoniaNorwayOmanPakistanPalestinian TerritoriesPanamaPapua New GuineaParaguayPeruPhilippinesPitcairn IslandsPolandPortugalQatarRéunionRomaniaRussiaRwandaSamoaSan MarinoSão Tomé & PríncipeSaudi ArabiaSenegalSerbiaSeychellesSierra LeoneSingaporeSint MaartenSlovakiaSloveniaSolomon IslandsSomaliaSouth AfricaSouth Georgia & South Sandwich IslandsSouth KoreaSouth SudanSpainSri LankaSt. BarthélemySt. HelenaSt. Kitts & NevisSt. LuciaSt. MartinSt. Pierre & MiquelonSt. Vincent & GrenadinesSudanSurinameSvalbard & Jan MayenSwedenSwitzerlandTaiwanTajikistanTanzaniaThailandTimor-LesteTogoTokelauTongaTrinidad & TobagoTristan da CunhaTunisiaTürkiyeTurkmenistanTurks & Caicos IslandsTuvaluU.S. Outlying IslandsUgandaUkraineUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVatican CityVenezuelaVietnamWallis & FutunaWestern SaharaYemenZambiaZimbabwe

State / Territory \*-- Please select --VictoriaACTNew South WalesNorthern TerritoryQueenslandSouth AustraliaTasmaniaWestern AustraliaOther / Not in Australia

Postcode \*

When would you like to start studying? (Optional)-- Please select --NowIn around 3 monthsIn around 6 monthsIn around 12 monthsNot sure yet

By submitting this form, you consent to RMIT contacting you via email, phone, and SMS to provide you with further information about our courses, events, and other updates. You can unsubscribe at any time. For details on how RMIT collects, stores and uses your personal information, see [RMIT's Privacy Statement.](https://shortcourses.rmit.edu.au/policies/privacy-policy) \*

I would like to receive information about RMIT, including course information, event invitations, and other updates via email, SMS and phone.

I acknowledge that I have read and understood [RMIT's Privacy Statement](https://shortcourses.rmit.edu.au/policies/privacy-policy). \*

Submit