Practical Development with Pi Coding Agent Training Course

Google Antigravity serves as an agentic development environment, purpose-built for creating autonomous agents that leverage the multimodal capabilities of Gemini 3 to plan, reason, code, and take action.

Delivered by expert instructors, this live training—available either online or on-site—is tailored for advanced technical professionals seeking to design, build, and deploy autonomous agents using Gemini 3 within the Antigravity ecosystem.

By the end of this program, participants will be equipped to:

• Construct autonomous workflows that leverage Gemini 3 for reasoning, planning, and execution.
• Develop agents within Antigravity capable of analyzing tasks, writing code, and interacting with external tools.
• Integrate Gemini-driven agents seamlessly with enterprise systems and APIs.
• Optimize agent behavior, ensuring safety and reliability in complex operational environments.

Course Format

• Expert-led demonstrations paired with interactive discussions.
• Hands-on experimentation focused on autonomous agent development.
• Practical implementation utilizing Antigravity, Gemini 3, and complementary cloud tools.

Course Customization

• If your team requires specific domain behaviors or custom integrations, please contact us to tailor the program to your needs.

Google Antigravity is a sophisticated framework designed for experimenting with long-lived agents and their emergent interactive capabilities.

This live, instructor-led training—available both online and on-site—is tailored for advanced-level professionals looking to design, analyse, and optimise agents that can retain memories, learn from feedback, and evolve across extended operational periods.

By the end of this course, participants will be equipped with the skills to:

• Design long-term memory structures to ensure agent persistence.
• Implement effective feedback loops to guide and shape agent behaviour.
• Evaluate learning trajectories and monitor model drift.
• Integrate memory mechanisms into complex multi-agent ecosystems.

Course Format

• Expert-led discussions accompanied by technical demonstrations.
• Hands-on exploration through structured design challenges.
• Practical application of concepts within simulated agent environments.

Customisation Options

• If your organisation requires specific content or case-study examples, please contact us to tailor this training to your needs.

Mastra serves as a framework enabling deep integration between AI agents, APIs, enterprise applications, and external data systems.

This instructor-led live training, available both online and on-site, is designed for intermediate-level engineers aiming to construct reliable, secure, and scalable integrations between Mastra agents and the wider enterprise ecosystem.

Upon completion of this training, participants will be equipped to:

• Implement API-driven integrations connecting Mastra agents with external services.
• Link enterprise data systems and tools to automated agent workflows.
• Apply best practices for secure data exchange and authentication.
• Design integration layers that are scalable, maintainable, and ready for production.

Course Format

• Interactive lectures and discussions.
• Practical exercises in integration engineering and APIs.
• Live-lab implementation using real-world enterprise scenarios.

Customization Options

• Custom API scenarios, enterprise system mappings, or data-integration workshops can be arranged upon request.

AgentCore offers memory persistence, a secure code interpreter, and a browser tool, allowing AI agents to provide interactive, dynamic, and context-aware experiences.

This instructor-led live training, available online or onsite, is tailored for intermediate to advanced technical professionals seeking to design and deploy AI agents with capabilities for long-term context retention, real-time computation, and direct interaction with web interfaces.

Upon completing this training, participants will be equipped to:

• Implement AgentCore memory for stateful, context-aware workflows.
• Utilize the secure code interpreter for dynamic calculations and transformations.
• Integrate the browser tool for real-time data acquisition and UI interaction.
• Design interactive agents for analytics, customer support, and research applications.

Course Format

• Interactive lectures and group discussions.
• Practical lab exercises focusing on AgentCore memory and tools.
• Case studies covering analytics, automation, and customer support scenarios.

Course Customization

• Contact us to request a tailored training program for this course.

AgentCore Runtime & Gateway is an AWS service pairing for packaging, deploying, and securely exposing AI agents with streamlined integrations to external systems.

This instructor-led, live training (online or onsite) is aimed at intermediate-level engineering teams who wish to move from agent prototypes to production by mastering the AgentCore Runtime for deployment and the Gateway for secure connectivity and API integration.

By the end of this training, participants will be able to:

• Stand up AgentCore Runtime environments and package agents for deployment.
• Expose agents through Gateway with authenticated, rate-limited endpoints.
• Integrate external tools and APIs into agent workflows using stable contracts.
• Instrument observability, logging, and usage monitoring for production operation.

Format of the Course

• Interactive lecture and discussion.
• Hands-on labs with Runtime deployments and Gateway integrations.
• Practical exercises focused on reliability, security, and rollout.

Course Customization Options

• To request a customized training for this course, please contact us to arrange.

Antigravity serves as a robust development platform specifically engineered for the creation of AI-powered, agent-centric applications.

Delivered by an instructor, this live training (available online or onsite) targets intermediate-level developers seeking to engineer practical, real-world solutions by leveraging autonomous AI agents within the Antigravity ecosystem.

Upon successful completion, participants will be fully capable of:

• Engineering applications that depend on autonomous and orchestrated AI agents.
• Utilising the Antigravity IDE, editor, terminal, and browser for comprehensive end-to-end development.
• Overseeing multi-agent workflows via the Agent Manager.
• Embedding agent capabilities into production-quality software systems.

Delivery Method

• A blend of theoretical presentations and detailed demonstrations.
• Substantial hands-on practice alongside guided practical exercises.
• Practical implementation work conducted directly within the live Antigravity environment.

Customisation Options

• For content tailored to your specific development stack, please reach out to arrange a personalised version of this training.

Google Antigravity represents a new paradigm in agent-first development environments, specifically engineered to optimise engineering workflows through intelligent automation.

This live, instructor-led training—available either online or on-site—caters to entry-level professionals seeking to grasp the foundational principles of Antigravity and appreciate how agent-driven coding environments can significantly boost productivity.

By the end of this programme, learners will have acquired the ability to:

• Perform the installation and configuration of Google Antigravity.
• Effectively navigate and interpret both the Editor View and Manager View.
• Collaborate efficiently with agents to automate routine development tasks.
• Leverage Antigravity to generate, refine, and oversee project files.

Course Format

• Instructor-led explanations complemented by live demonstrations.
• Structured, guided exercises emphasising practical agent application.
• Hands-on investigation of core Antigravity capabilities within a supervised lab setting.

Tailoring Options

• Should you require a bespoke iteration of this training, please reach out to discuss arranging a customised programme.

Google Antigravity serves as a robust platform for developing agents that can interact with web applications, browser environments, and complex multi-surface workflows.

This live, instructor-led training, available either online or onsite, is designed for intermediate-level professionals seeking to build, automate, and test browser-based workflows using Google Antigravity.

By the end of the course, participants will be equipped to:

• Develop agents capable of interacting with web applications within a browser surface.
• Automate end-to-end workflows across various browser contexts.
• Validate and troubleshoot agent behavior within UI-driven environments.
• Implement cross-surface automation strategies leveraging Antigravity.

Course Format

• Guided instruction reinforced by live demonstrations.
• Practical, hands-on activities and scenario-based exercises.
• Implementation of agent workflows within an interactive lab environment.

Customization Options

• Please contact us to tailor the course to your specific training requirements and objectives.

AgentCore streamlines the development, refinement, and oversight of fully managed AI agents by offering a cohesive suite of services designed for large-scale deployment.

This instructor-led live training, available online or on-site, is tailored for practitioners ranging from beginner to intermediate level who seek practical experience in developing production-ready AI agents using AgentCore.

Upon completion, participants will be equipped to:

• Grasp the fundamental capabilities of AgentCore in AI agent creation.
• Architect and configure straightforward AI agents leveraging managed services.
• Combine workflows to augment agent functionalities.
• Deploy and oversee AI agents within production environments.

Course Structure

• Engaging lectures and facilitated discussions.
• Practical labs focused on AgentCore services.
• Step-by-step exercises guiding the process from agent conception to deployment.

Tailored Learning Options

• Interested in a customized training plan? Please reach out to us to coordinate arrangements.

This live, instructor-led training (available online or onsite) is tailored for mid-level software developers and engineering teams looking to construct scalable, observable AI systems with Mastra.

Upon completion of this program, participants will be equipped to:

• Grasp Mastra’s architectural design and its integration with LLMs and external APIs.
• Architect and build AI agents and workflows using TypeScript.
• Leverage Mastra’s observability and memory utilities to oversee and enhance agent performance.
• Launch production-grade AI applications by capitalising on Mastra’s framework capabilities.

Mastra is a framework offering structured tools for evaluating, debugging, and ensuring the reliability of AI agents within complex workflows.

This instructor-led live training (available online or onsite) targets intermediate-level practitioners seeking to rigorously test agent behavior, enhance reliability, and implement measurable evaluation processes.

Upon completion of this training, participants will be able to confidently:

• Apply debugging techniques to identify and rectify issues in agent behavior.
• Evaluate agents using structured metrics, benchmarks, and quality scores.
• Implement tooling and workflows that track reliability, drift, and hallucinations.
• Design QA strategies to ensure consistent and predictable agent performance.

Course Format

• Interactive lecture and discussion.
• Hands-on debugging and evaluation exercises.
• Live-lab analysis of agent behaviors using observability tools.

Customization Options

• Customized reliability testing scenarios and industry-specific QA methods can be arranged upon request.

Mastra serves as an operational framework designed to streamline the deployment, scaling, and lifecycle management of AI agents within production environments.

This instructor-led live training, available both online and onsite, targets intermediate to advanced technical professionals seeking to reliably and efficiently operationalize AI agents across production systems.

Upon completing this training, attendees will be able to:

• Deploy Mastra-based AI agents into controlled, production-grade environments.
• Scale agents horizontally and vertically utilizing platform-native primitives.
• Implement observability pipelines to monitor agent behaviour and performance.
• Optimize runtime configurations to reduce latency, costs, and operational risks.

Course Format

• Interactive lectures and discussions.
• Hands-on exercises centred on real-world deployment scenarios.
• Live-lab implementation within containerized and orchestrated environments.

Course Customization Options

• Customization of topics, hands-on labs, or industry-specific scenarios is available upon request.

Mastra is a framework designed to facilitate sophisticated workflow automation and coordination among multiple AI agents operating within distributed systems.

This instructor-led live training, available either online or onsite, is tailored for intermediate-level practitioners seeking to design, orchestrate, and manage multi-agent workflows at scale.

Upon completing this training, participants will acquire the skills to:

• Design complex workflows leveraging Mastra’s orchestration capabilities.
• Coordinate multiple agents executing tasks either in parallel or with dependencies.
• Implement monitoring and debugging tools to oversee workflow execution.
• Optimize orchestration logic to enhance reliability, throughput, and automation efficiency.

Course Format

• Interactive lectures and discussions.
• Hands-on exercises in workflow design and automation.
• Practical implementation within a containerized live-lab environment.

Course Customization Options

• Custom automation scenarios, enterprise integrations, or workflow patterns can be provided upon request.

Google Antigravity serves as an agent-centric development platform designed to supervise, coordinate, and orchestrate AI-driven automation and coding workflows.

This live, instructor-led training—available online or onsite—is tailored for intermediate professionals seeking to design, manage, and refine multi-agent workflows within the Google Antigravity environment.

By the end of this session, participants will be equipped to:

• Define agent responsibilities and structure orchestration pipelines using the Manager interface.
• Create and analyze Antigravity artifacts, such as task lists, strategic plans, logs, and browser session recordings.
• Apply verification methods that ensure agent actions remain transparent and fully auditable.
• Enhance multi-agent collaboration to address complex development and operational challenges.

Course Structure

• Guided presentations paired with practical demonstrations.
• Scenario-based exercises addressing real-world workflow complexities.
• Live, hands-on experimentation within an active Antigravity workspace.

Customization Possibilities

• For organizations requiring a tailored curriculum, please reach out to discuss specific customization options.

Antigravity serves as a framework for sophisticated, agent-centric development processes.

This live, instructor-led session, available either online or on-site, is designed for intermediate to advanced professionals seeking to validate, verify, and secure the outputs generated by AI agents within Antigravity-based environments.

By the end of this training, participants will be equipped to:

• Evaluate the precision and safety of code artifacts produced by agents.
• Employ structured methodologies to validate tasks executed by agents.
• Analyze browser recordings and trace agent activities effectively.
• Implement QA and security principles to guarantee the reliability of agent workflows.

Course Format

• Instructor-led technical briefings and interactive discussions.
• Practical exercises centered on validating actual agent workflows.
• Hands-on testing and verification within a controlled laboratory setting.

Course Customization Options

• Scenario, workflow, and testing example adaptations can be arranged upon request.