OneRange

AI Agents & Agentic Workflows

Learners understand and design agentic systems that take multi-step actions with tools. The course covers what an agent is, tools and function calling, multi-step and multi-agent designs, MCP and orchestration, and guardrails. Participants finish able to design agents that are useful and safe.

What this course covers

The course runs across 12 topics, each one a short adaptive session rather than a recorded lecture. The tutor explains the idea, works an example, checks understanding, and adjusts the next step to the answer given.

  • Demystifying AI Agents and the ReAct Framework — Understand what defines an agent, contrast agentic workflows with standard LLM generation, and explore the core Reason-Act (ReAct) loop.
  • Tools and Function Calling Foundations — Learn how LLMs interface with the physical world through schemas, tool definitions, and structured JSON generation.
  • Coding Lab: Implementing Function Calling from Scratch — Write Python code to define tool schemas, bind them to an LLM API, and parse the model's tool-call response to execute native code.
  • Multi-Step Agentic Workflows and State Management — Examine how agents maintain memory, manage state transitions, and handle error recovery over complex, multi-turn reasoning paths.
  • Guided Lab: Building a Autonomous ReAct Agent Loop — Follow a step-by-step guide to assemble a complete, runnable agent loop that uses tools iteratively to solve a multi-step math and search problem.
  • Multi-Agent Architectures and Collaboration Patterns — Analyze design patterns for multi-agent systems, including supervisor-worker, hierarchical routing, and peer-to-peer collaboration.
  • Coding Lab: Building a Two-Agent Collaborative Team — Code a multi-agent system where a researcher agent and a writer agent pass messages and state back and forth to produce a cohesive report.
  • Model Context Protocol (MCP) and Standardized Integration — Explore the Model Context Protocol (MCP) architecture, understanding how it standardizes client-server connections for context, prompts, and tools.
  • Orchestration Frameworks: LangGraph, AutoGen, and CrewAI — Compare top orchestration frameworks, evaluating when to use graph-based state management versus conversational agent frameworks.
  • Guided Lab: Orchestrating State with LangGraph — Build a stateful agentic workflow using LangGraph, mapping nodes, conditional edges, and compiled state machines to solve a complex coding task.
  • Guardrails, Safety, and Human-in-the-Loop — Study security risks unique to agents, such as prompt injection via tools, and learn strategies for output validation and human approval gates.
  • Coding Lab: Implementing Guardrails and Human-in-the-Loop Gates — Incorporate input/output guardrail checks and build an interactive terminal-based human approval step before an agent executes a destructive tool action.

Skills you build

Results are measured against named skills in the OneRange taxonomy of more than 10,000 skills, so a manager sees proficiency per skill rather than a completion tick. This course maps to LangChain, Large Language Models (LLMs), AI Agent Development, AI Safety, AI Engineering.

  • LangChain
  • Large Language Models (LLMs)
  • AI Agent Development
  • AI Safety
  • AI Engineering

Who it is for

Builders, engineers, technical PMs. The material is pitched at advanced level, and takes roughly 180 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

It sits in the Category: Agents track of the Vero AI Catalog, and can be assigned to one person, a team, or the whole company.

How it is delivered and assessed

Delivery is conversational and interactive, including code lab, guided lab exercises. There is no video to sit through and no slide deck to click past.

Understanding is checked with a code assessment of 5 items, with a pass mark of 70%.

Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Also in this track

  • All AI Agents training courses →
  • Computer-Use & Browser Agents — This course covers agents that operate software the way people do - clicking, typing, browsing. Learners build a supervised computer-use workflow and learn where the reliability boundary really sits.
  • Agent Memory & State — A design course on giving AI systems usable memory: architectures for persistence, what to store versus retrieve, and handling privacy and staleness. Learners add durable memory to a working agent.
  • Orchestration Frameworks — A judgment-heavy course on orchestration tooling (LangChain/LlamaIndex-class): what it solves, what it obscures, and when plain code is better. Learners build the same workflow twice and compare.
  • Zapier & Make: Advanced — An advanced automation course for Zapier and Make: multi-step workflows with AI reasoning steps, branching logic, and robust error handling. Learners ship an automation reliable enough to run unattended.
  • n8n Workflow Automation — This advanced course teaches builders to create sophisticated AI automations and agents in n8n. Learners work with nodes and workflows, AI agent nodes, APIs and webhooks, self-hosting, and debugging. They leave able to ship reliable, production-grade automations.
  • AI Automation Assessment — AI Automation Assessment: designing and running a reliable workflow.
  • Production AI Engineering — Take AI from prototype to reliable production
  • AI Automation Specialist — Connect AI into real workflows and systems

Related

Frequently asked questions

How long does this course take?

It runs roughly 180 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

How is it assigned to a team?

An administrator assigns it from the Vero dashboard to one person, a team, a department or the whole company, and sees progress and results per person and per skill.

Can we customise it with our own documents and terminology?

Yes. Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Course code CAT-AGT.