Building Agentic AI Applications in Python: From Prompts to Autonomous Workflows #367
Description
Talk title
Building Agentic AI Applications in Python: From Prompts to Autonomous Workflows
Short talk description
Agentic AI is the next major shift in Generative AI—where LLMs don’t just respond, but observe, reason, decide, and take actions using tools, APIs, and autonomous workflows. In this hands-on session, we’ll build a real-life Agentic AI application in Python that uses an LLM to plan tasks, call external tools, retrieve knowledge, and make decisions. Attendees will learn how to combine Python, LLMs, and frameworks like LangChain to create AI agents that actually do things, not just chat. Participants will walk away with a working project they can extend in their own real-world use cases.
Long talk description
Generative AI has evolved from simple prompt-response models to Agentic AI systems capable of autonomous reasoning, tool usage, data retrieval, state management, and multi-step decision making. Agentic AI enables a new era of applications that can handle complex workflows such as travel planning, customer onboarding, automated research, support ticket resolution, and operational automation.
This workshop introduces Python developers to building fully working AI Agents using open-source frameworks (LangChain / LlamaIndex) and LLMs (Llama, Gemini, or OpenAI). Through a live hands-on demonstration, we will develop a real Agentic AI application that can break down goals, call APIs, search documents, generate responses, and take next-step actions.
Key concepts covered:
What makes an AI “agent”
Planner-Executor architecture
Tool calling and structured reasoning
Memory, context, and long-horizon tasks
Using Python with LangChain to orchestrate agents
Connecting an LLM to external tools (REST APIs, local functions, RAG retrievers)
Safe and responsible agent behavior (guardrails, evaluation)
By the end of this session, participants will leave with:
A working Agentic AI Python project
Understanding of how to extend it for real-life business use-cases
Best practices for scaling agent workflows in production
This workshop is ideal for Python developers, data professionals, and AI enthusiasts who want to move beyond “chatbots” and start building autonomous AI applications with real business value.
What format do you have in mind?
Workshop (45-60 minutes, hands-on)
Talk outline / Agenda
- Introduction to Agentic AI (5 mins)
- Core concepts: Planning, tools, memory (10 mins)
- Live coding: Building an AI Agent in Python with LangChain (20 mins)
- Adding tool-calling + RAG + real-life workflow (15 mins)
- Guardrails, safety, best practices (5 mins)
- Q&A (5 mins)
Key takeaways
- Key Takeaways
- Understanding of Agentic AI fundamentals
- Practical skills to build Python-based AI agents
- How to integrate tools, APIs, and RAG into agents
- Best practices and common pitfalls
- A complete open-source project to continue learning
What domain would you say your talk falls under?
Data Science and Machine Learning
Duration (including Q&A)
60 minutes (45 minutes workshop + 15 minutes Q&A)
Prerequisites and preparation
- Basic Python knowledge
- Laptop with Python + virtual environment
- (Optional) OpenAI / Gemini API key for hands-on
Resources and references
https://python.langchain.com
https://github.com/hwchase17/langchain
https://huggingface.co
Link to slides/demos (if available)
No response
Twitter/X handle (optional)
No response
LinkedIn profile (optional)
https://www.linkedin.com/in/anuj-saini-23666211/
Profile picture URL (optional)
No response
Speaker bio
Anuj Saini is an AI professional with 17+ years of experience in Machine Learning and Generative AI, helping enterprises build end-to-end AI solutions. He has led multiple AI initiatives across domains and conducts workshops on LLMs, RAG, Agentic AI, and responsible AI practices.
Availability
08/11/2025
Accessibility & special requirements
No response
Speaker checklist
- I have read and understood the PyDelhi guidelines for submitting proposals and giving talks
- I will make my talk accessible to all attendees and will proactively ask for any accommodations or special requirements I might need
- I agree to share slides, code snippets, and other materials used during the talk with the community
- I will follow PyDelhi's Code of Conduct and maintain a welcoming, inclusive environment throughout my participation
- I understand that PyDelhi meetups are community-centric events focused on learning, knowledge sharing, and networking, and I will respect this ethos by not using this platform for self-promotion or hiring pitches during my presentation, unless explicitly invited to do so by means of a sponsorship or similar arrangement
- If the talk is recorded by the PyDelhi team, I grant permission to release the video on PyDelhi's YouTube channel under the CC-BY-4.0 license, or a different license of my choosing if I am specifying it in my proposal or with the materials I share
Additional comments
No response