Agentic AI Engineering with Python — Build Autonomous Agents Training Course
This course imparts practical engineering methodologies for designing, constructing, testing, and deploying agentic (autonomous) systems using Python. It explores the agent loop, tool integrations, memory and state management, orchestration patterns, safety controls, and production-related considerations.
This instructor-led, live training (available online or onsite) targets intermediate to advanced-level ML engineers, AI developers, and software engineers who aim to build robust, production-ready autonomous agents using Python.
Upon completion of this training, participants will be able to:
- Design and implement the agent loop and decision-making workflows.
- Integrate external tools and APIs to extend agent capabilities.
- Implement short-term and long-term memory architectures for agents.
- Coordinate multi-step orchestrations and agent composability.
- Apply safety, access control, and observability best practices for deployed agents.
Format of the Course
- Interactive lecture and discussion.
- Hands-on labs building agents with Python and popular SDKs.
- Project-based exercises that produce deployable prototypes.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Course Outline
Fundamentals of Agentic AI
- What is an autonomous agent: definitions and taxonomy
- Agent loop: perceive, decide, act, observe cycle
- Design patterns for agent responsibilities and scope
Python Tooling and Agent SDKs
- Using LangChain and similar SDKs to bootstrap agents
- Async programming, task queues, and subprocess management
- Packaging, virtual environments, and reproducible development workflows
Integrating External Tools and APIs
- Designing tool interfaces and safe tool invocation patterns
- Connecting to web APIs, databases, and internal services
- Managing credentials, secrets, and least-privilege access
Memory, State, and Context Management
- Short-term context windows and prompt engineering techniques
- Long-term memory architectures: Redis, vector stores, retrieval augmentation
- Consistency, caching strategies, and memory hygiene
Orchestration, Planning, and Multi-Step Workflows
- Chaining actions, subagents, and task decomposition
- Planning algorithms vs heuristic orchestration
- Handling failures, retries, and compensating actions
Safety, Testing, and Observability
- Threat models, red-teaming, and input/output sanitization
- Unit, integration, and end-to-end testing for agents
- Logging, metrics, tracing, and alerting for agent behavior
Deployment, Scaling, and MLOps for Agents
- Containerization, CI/CD pipelines, and rollout strategies
- Cost control, rate limiting, and resource optimization
- Monitoring, governance, and operational playbooks
Summary and Next Steps
Requirements
- An understanding of Python programming
- Experience with REST APIs and asynchronous I/O
- Familiarity with machine learning concepts and pretrained LLMs
Audience
- ML engineers
- AI developers
- Software engineers
Need help picking the right course?
southafrica@nobleprog.co.za or +27 (0)10 005 5793
Agentic AI Engineering with Python — Build Autonomous Agents Training Course - Enquiry
Upcoming Courses
Related Courses
Agentic Development with Gemini 3 and Google Antigravity
21 HoursGoogle Antigravity is an agentic development environment engineered to create autonomous agents capable of planning, reasoning, coding, and acting through the multimodal capabilities of Gemini 3.
This instructor-led, live training (available online or on-site) is targeted at advanced technical professionals who wish to design, build, and deploy autonomous agents using Gemini 3 and the Antigravity environment.
Upon completing this training, participants will be equipped to:
- Build autonomous workflows that leverage Gemini 3 for reasoning, planning, and execution.
- Develop agents in Antigravity that can analyse tasks, write code, and interact with tools.
- Integrate Gemini-driven agents with enterprise systems and APIs.
- Optimise agent behaviour, safety, and reliability in complex environments.
Course Format
- Expert demonstrations combined with interactive discussions.
- Hands-on experimentation with autonomous agent development.
- Practical implementation using Antigravity, Gemini 3, and supporting cloud tools.
Course Customisation Options
- If your team requires domain-specific agent behaviours or custom integrations, please contact us to tailor the programme.
Advanced Antigravity: Feedback Loops, Learning & Long-Term Agent Memory
14 HoursGoogle Antigravity serves as a sophisticated framework for exploring long-lived agents and the emergence of interactive behaviours.
This instructor-led, live training, available online or onsite, targets advanced professionals seeking to design, analyse, and optimise agents that retain memories, improve through feedback, and evolve across extended operational periods.
Upon completion of this course, participants will acquire the following capabilities:
- Designing long-term memory structures to ensure agent persistence.
- Implementing effective feedback loops to guide agent behaviour.
- Evaluating learning trajectories and monitoring model drift.
- Integrating memory mechanisms within complex multi-agent ecosystems.
Course Format
- Expert-led discussions combined with technical demonstrations.
- Hands-on exploration via structured design challenges.
- Application of concepts within simulated agent environments.
Course Customization Options
Antigravity for Developers: Building Agent-First Applications
21 HoursAntigravity is a development platform designed to build AI-driven, agent-first applications.
This instructor-led, live training (online or onsite) is aimed at intermediate-level developers who wish to create real-world applications using autonomous AI agents within the Antigravity environment.
After completing this training, participants will be equipped to:
- Develop applications that rely on autonomous and coordinated AI agents.
- Use the Antigravity IDE, editor, terminal, and browser for end-to-end development.
- Manage multi-agent workflows with the Agent Manager.
- Integrate agent capabilities into production-grade software systems.
Format of the Course
- Blended presentations with in-depth demonstrations.
- Extensive hands-on practice and guided exercises.
- Real implementation work inside the Antigravity live environment.
Course Customization Options
- For tailored content aligned with your development stack, please contact us to arrange a customized version of this training.
Getting Started with Antigravity: An Introduction to Agent-First IDEs
14 HoursGoogle Antigravity is an agent-first development environment designed to streamline engineering workflows through intelligent automation.
This instructor-led, live training (online or onsite) is aimed at beginner-level practitioners who wish to explore the fundamentals of Antigravity and understand how agent-driven coding environments enhance productivity.
Upon completion of this training, participants will be able to:
- Install and configure Google Antigravity.
- Navigate and understand both the Editor View and Manager View.
- Work effectively with agents to automate simple development tasks.
- Use Antigravity to generate, refine, and manage project files.
Format of the Course
- Instructor explanations supported by real-time demonstrations.
- Guided exercises focused on hands-on use of agents.
- Practical exploration of core Antigravity features in a controlled lab environment.
Course Customisation Options
- If you require a tailored version of this training, please contact us to arrange a customised programme.
Antigravity for Web Automation & Browser-Based Tasks
21 HoursGoogle Antigravity serves as a platform for constructing agents capable of interacting with web applications, browser environments, and multi-surface workflows.
This instructor-led, live training (available online or onsite) targets intermediate-level professionals seeking to build, automate, and test browser-based workflows using Google Antigravity.
Upon completion of the training, participants will be able to:
- Create agents that interact with web applications in a browser surface.
- Automate end-to-end workflows across browser contexts.
- Validate and troubleshoot agent behavior in UI-driven environments.
- Implement cross-surface automation strategies using Antigravity.
Format of the Course
- Guided instruction supported by demonstrations.
- Practical, hands-on activities and scenario-based exercises.
- Implementation of agent workflows in an interactive lab environment.
Course Customization Options
- For customized training requirements, please contact us to tailor the course to your objectives.
Governance and Security Patterns for WrenAI in the Enterprise
14 HoursWrenAI is an AI-driven analytics platform engineered to connect data, model insights, and generate dashboards. In enterprise environments, robust governance and security are critical to ensuring safe and compliant adoption.
This instructor-led, live training (online or onsite) is aimed at advanced-level enterprise professionals who wish to implement governance, compliance, and security patterns for WrenAI at scale.
By the end of this training, participants will be able to:
- Design and implement permissioning models in WrenAI.
- Apply auditability and monitoring practices for compliance.
- Set up secure environments with enterprise-level controls.
- Roll out WrenAI safely across large organisations.
Format of the Course
- Interactive lecture and discussion.
- Hands-on labs with governance and security configurations.
- Practical exercises simulating enterprise rollout scenarios.
Course Customization Options
- To request a customised training for this course, please contact us to arrange.
Modernizing Legacy BI with WrenAI: Adoption, Migration, and Change Management
14 HoursWrenAI empowers organisations to move beyond static dashboards towards conversational analytics and embedded generative BI. This transition demands careful adoption planning, asset migration, and robust change management practices.
This instructor-led, live training (available online or onsite) is designed for intermediate-level BI and data platform professionals seeking to modernise their legacy BI systems using WrenAI.
By the conclusion of this training, participants will be equipped to:
- Evaluate legacy BI environments and identify opportunities for modernisation.
- Plan and execute migrations from static dashboards to WrenAI.
- Adopt conversational analytics and embedded GenBI capabilities.
- Lead organisational change management for BI modernisation.
Format of the Course
- Interactive lecture and discussion.
- Hands-on exercises with migration and adoption planning.
- Practical labs on conversational analytics and embedded GenBI.
Course Customisation Options
- To request a customised training for this course, please contact us to arrange.
Quality and Observability for WrenAI: Evaluation, Prompt Tuning, and Monitoring
14 HoursWrenAI facilitates the conversion of natural language into SQL queries and provides AI-driven analytics, streamlining and simplifying data access. For enterprise-grade deployments, robust quality assurance and observability practices are critical to guarantee accuracy, reliability, and regulatory compliance.
This instructor-led, live training session (available online or on-site) targets advanced data and analytics professionals seeking to assess query accuracy, apply prompt tuning strategies, and implement observability frameworks to monitor WrenAI in production environments.
Upon completion of this training, participants will be capable of:
- Assessing the accuracy and reliability of Natural Language to SQL outputs.
- Utilising prompt tuning techniques to enhance system performance.
- Monitoring data drift and query behaviour over time.
- Integrating WrenAI with logging and observability frameworks.
Course Format
- Interactive lectures and group discussions.
- Practical exercises focused on evaluation and tuning techniques.
- Hands-on labs covering observability and monitoring integrations.
Course Customisation Options
- To request a customised training session for this course, please contact us to arrange.
Building with the WrenAI API: Applications, Charts, and NL to SQL
14 HoursThe WrenAI API serves as a robust interface for converting natural language into SQL queries, constructing bespoke applications, and embedding charts within internal platforms.
This instructor-led live training, available either online or onsite, is designed for intermediate-level engineers seeking to leverage the WrenAI API for practical implementations, such as SQL generation, data visualisation, and application integration.
Upon completion of this training, participants will be equipped to:
- Authenticate applications and establish connections with the WrenAI API.
- Generate SQL queries from natural language inputs.
- Create and embed charts using specific API endpoints.
- Integrate WrenAI into backend systems and internal tooling.
Course Format
- Interactive lectures and discussions.
- Practical exercises involving API calls and integrations.
- Hands-on projects linking applications, charts, and data pipelines.
Customisation Options
- To request a tailored training session for this course, please contact us to arrange.
WrenAI Cloud Essentials: From Data Sources to Dashboards
14 HoursWrenAI Cloud serves as a contemporary platform designed to link data sources, structure data models, and construct interactive dashboards.
This instructor-led, live training session, available either online or onsite, targets beginner to intermediate data professionals eager to master the setup of WrenAI Cloud, data modelling, and dashboard-based visualisation of insights.
Upon completion of this training, participants will be equipped to:
- Set up and configure WrenAI Cloud environments.
- Link WrenAI Cloud to various data sources.
- Model data and define relationships for analytics.
- Create interactive dashboards for business insights.
Format of the Course
- Interactive lecture and discussion.
- Hands-on cloud platform configuration and data modelling.
- Practical exercises in dashboard building and visualisation.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
WrenAI for Financial Analytics: KPI Modeling and Regulatory-Aware Dashboards
14 HoursWrenAI empowers finance teams to model Key Performance Indicators (KPIs), integrate standardised metrics, and craft dashboards that adhere to regulatory requirements and audit standards.
This instructor-led, live training session (available online or onsite) is designed for intermediate to advanced finance professionals who wish to leverage WrenAI to build compliant financial data models and dashboards that support informed decision-making and effective risk management.
By the conclusion of this training, participants will be able to:
- Model financial KPIs and metrics within WrenAI.
- Construct dashboards that align with regulatory and audit mandates.
- Integrate WrenAI with finance data sources to enable real-time reporting.
- Apply industry best practices for financial analytics and risk monitoring.
Course Format
- Interactive lectures and discussions.
- Hands-on exercises involving financial data models.
- Practical labs focused on dashboard design and compliance reporting.
Course Customisation Options
- To arrange tailored training for this course, please contact us to discuss your needs.
WrenAI OSS Deep Dive: Semantic Modeling, Text to SQL, and Guardrails
21 HoursWrenAI is an open-source generative business intelligence (BI) tool designed for natural language to SQL conversion and semantic data modelling.
This instructor-led, live training (available online or onsite) is tailored for advanced data engineers, analytics engineers, and machine learning engineers who wish to construct robust semantic layers, refine prompts, and guarantee reliable SQL generation.
By the end of this training, participants will be able to:
- Implement semantic models for consistent metric definitions across teams.
- Optimize text-to-SQL performance for accuracy and scalability.
- Configure and enforce guardrails to avoid invalid or risky queries.
- Integrate WrenAI OSS into data pipelines and analytics workflows.
Format of the Course
- Interactive lecture and discussion.
- Lots of exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
WrenAI for Product Teams: Conversational Analytics and Self-Service BI
14 HoursWrenAI serves as a conversational analytics platform that converts natural-language queries into dependable analytical results, empowering non-technical teams to generate insights swiftly and consistently.
This instructor-led, live training (available online or on-site) is tailored for intermediate-level product managers, analysts, and data champions looking to adopt conversational analytics and develop self-service BI capabilities using WrenAI.
Upon completion of this training, participants will be able to:
- Design conversational analytics workflows that deliver reliable product insights.
- Create and maintain a standardised metrics layer to ensure consistent reporting.
- Effectively utilise natural-language to SQL features to address product-related questions.
- Integrate WrenAI-driven self-service dashboards and guardrails into product workflows.
Course Format
- Interactive lectures and discussions.
- Practical labs utilising Wren AI and sample datasets.
- Workshop: Construct a self-service dashboard and set of conversational queries.
Course Customisation Options
- To request customised training for this course, please contact us to arrange.
Deploying WrenAI for SaaS: Embedded GenBI in Customer-Facing Products
14 HoursWrenAI empowers SaaS providers to integrate generative business intelligence (GenBI) directly into their customer-facing offerings. This course equips SaaS teams with the expertise to seamlessly integrate Wren AI via its Embedded API, configure white-label analytics solutions, and manage multi-tenant deployments effectively.
This instructor-led live training (available online or onsite) is designed for intermediate to advanced-level SaaS product leaders, data engineers, and full-stack developers who aim to deploy WrenAI as an embedded analytics solution within SaaS environments.
By the conclusion of this training, participants will be able to:
- Integrate WrenAI using the Embedded API for customer-facing applications.
- Implement white-label conversational BI with tailored branding and customization.
- Design secure and scalable multi-tenant deployments.
- Monitor usage, optimize performance, and ensure compliance within SaaS environments.
Course Format
- Interactive lectures and discussions.
- Hands-on labs utilising the WrenAI Embedded API.
- Workshop: Design and deploy a white-label analytics feature for a specific SaaS use case.
Course Customisation Options
- To request a customised training programme for this course, please contact us to arrange.
Operational Analytics with WrenAI Spreadsheets and Metrics Library
14 HoursWrenAI Spreadsheets and the Metrics Library facilitate rapid reporting by combining AI-driven spreadsheet workflows with a repository of pre-built, cross-platform business metrics.
This instructor-led live training, available online or on-site, is designed for operations professionals at beginner to intermediate levels who wish to expedite their reporting and analysis processes using WrenAI Spreadsheets and the Metrics Library.
Upon completing this training, participants will be able to:
- Construct AI-enabled spreadsheets for data analysis and reporting.
- Utilise the WrenAI Metrics Library for standardised KPIs.
- Link spreadsheets to various data sources to ensure live data updates.
- Establish automated workflows to streamline operational reporting.
Format of the Course
- Interactive lectures and discussions.
- Practical, hands-on spreadsheet creation using WrenAI.
- Practical exercises focused on metrics and KPI reporting.
Course Customization Options
- To request a bespoke training session for this course, please contact us to arrange.