Design tool-using AI agents, orchestrate multi-step reasoning and monitor workflows built with modern agent frameworks. 1. Who can join
Suitable for: Python developers, automation engineers and technical professionals Mandatory prerequisites: Working Python, APIs, JSON and basic LLM application development 2. Duration
44 live hours • Approximately 8 weeks at 6 hours per week; actual timetable to be confirmed. 3. Mode
Classroom - Thaiyur / Kelambakkam, OMR Chennai (subject to schedule)
Live Online (subject to schedule) 4. Syllabus — five modules Module 1: Agentic Fundamentals: ReAct Framework, Tools & Memory Architectures Learning outcome: Design an agent loop with tools, memory and stop conditions. Module 2: Multi-Agent Systems with AutoGen & CrewAI Learning outcome: Build cooperating agent roles using a supported multi-agent framework. Module 3: Advanced Flow Control & State Management using LangGraph Learning outcome: Model state transitions and recovery paths using a graph workflow. Module 4: Tool Calling, Web Search Integration & API Automation Learning outcome: Connect safe API and web tools with input validation and rate limits. Module 5: Enterprise Deployment, Debugging & Performance Monitoring Learning outcome: Log agent executions, test failure paths and deploy a demonstration service. 5. Practical project
Source capstone title: Develop an Autonomous Market Research Agent with Multi-Agent Review Flow Student deliverable: A market-research agent that gathers permitted public information, hands findings to a second agent for review and produces a traceable summary report. 6. What is included Live trainer-led sessions Practical assignments Sample code or templates, as applicable Project feedback Learning assessment Perizona course-completion certificate subject to assessment 7. Upcoming batch
Start date: To be announced. Students can register interest; dates are shared only after confirmation.
