Building Modern AI Applications with RAG, Agents & Memory (Talk Proposal)

[Devgr72]

Talk title

Building Modern AI Applications with RAG, Agents & Memory

Short talk description

This talk explores how modern AI systems are evolving beyond simple chatbots into production-ready AI applications powered by RAG (Retrieval-Augmented Generation), AI agents, memory systems, and tool calling.

The session is designed for students, developers, and AI enthusiasts who want to understand what technologies are actually being used in the industry today. Through practical examples, architecture breakdowns, and a lightweight live demo, attendees will learn how modern GenAI systems work and how to start building their own AI-powered applications using tools like LangChain, vector databases, and LLM APIs.

The talk also covers current AI engineering roles, project ideas, and a practical roadmap for getting started in the AI ecosystem.

Long talk description

Over the last two years, the AI ecosystem has rapidly shifted from simple prompt-based chatbots to fully capable AI systems that can retrieve information, use tools, remember users, and complete tasks autonomously.

This session introduces attendees to the modern AI stack through a practical and beginner-friendly approach. Starting with the limitations of plain LLMs, the talk explains why techniques like Retrieval-Augmented Generation (RAG) became essential for building reliable AI applications. It then explores how the ecosystem evolved further into Agentic AI systems capable of reasoning, tool usage, and persistent memory.

The session covers:

• Core concepts behind RAG and vector databases
• How modern retrieval systems work in production
• Agentic AI workflows and tool calling
• AI memory systems and contextual personalization
• Emerging trends such as Hybrid RAG, Graph RAG, and Multimodal RAG
• Practical project ideas students can build immediately
• The current AI engineering landscape and career opportunities

Alongside conceptual explanations, the talk also includes a lightweight live coding/demo section showing how a simple RAG pipeline can be built using Python, LangChain, ChromaDB, and LLM APIs.

The goal of the session is to make modern AI concepts approachable, practical, and actionable for developers who want to move from “using AI tools” to actually building AI-powered systems.

What format do you have in mind?

Talk (20-25 minutes + Q&A)

Talk outline / Agenda

• Introduction: The evolution of modern AI systems (5 mins)

• Why plain LLMs fail in real-world applications (5 mins)

• Understanding RAG and vector databases (10 mins)

• Modern RAG architectures:

• Hybrid RAG
• Graph RAG
• Multimodal RAG
• Agentic RAG (10 mins)

• AI agents, memory systems, and tool calling (10 mins)

• Live demo:
Building a simple RAG pipeline using LangChain + ChromaDB (10 mins)

• AI engineering roadmap, projects, and career guidance (5 mins)

• Q&A and discussion (10 mins)

Key takeaways

• Understanding the limitations of plain LLMs and why RAG matters

• Practical knowledge of how modern RAG pipelines work

• Introduction to AI agents, memory systems, and tool calling

• Awareness of production AI architectures used in industry today

• Beginner-friendly roadmap and project ideas for entering AI engineering

What domain would you say your talk falls under?

Artificial Intelligence & Deep Learning

Duration (including Q&A)

30 minutes

Prerequisites and preparation

• Basic programming knowledge is helpful

• Familiarity with Python is recommended but not mandatory

• No prior experience with RAG, AI agents, or LLM frameworks is required

• Attendees interested in AI engineering, GenAI applications, or developer tooling will benefit most from the session

• The live demo will use Python, LangChain, vector databases, and LLM APIs

Resources and references

• LangChain Documentation
• LlamaIndex Documentation
• ChromaDB Documentation
• OpenAI API Documentation
• LangGraph Documentation
• RAGAS Framework
• GitHub repositories and demo resources will be shared during the session

Link to slides/demos (if available)

No response

Twitter/X handle (optional)

No response

LinkedIn profile (optional)

https://www.linkedin.com/in/dev-grover-619a24319/

Profile picture URL (optional)

No response

Speaker bio

Dev is a Software Engineer at ISF focused on Full-Stack Development, AI systems, and DevSecOps. He works on projects involving RAG pipelines, AI agents, memory systems, and secure AI infrastructure.

He has contributed to AI-focused community initiatives and enjoys simplifying complex AI concepts into practical, beginner-friendly learning experiences. His interests include Generative AI, AI security, developer tooling, and real-world AI applications.

Through workshops, community sessions, and hands-on demos, he aims to help students and developers move from consuming AI tools to building production-ready AI systems.

Availability

second and third saturday of every month

Accessibility & special requirements

• No special AV requirements beyond standard projector/audio setup

• Slides will use readable fonts and accessible contrast

• Demo content will be explained verbally alongside code walkthroughs

• Happy to coordinate beforehand for any accessibility accommodations required by attendees

Speaker checklist

• I have read and understood the PyDelhi guidelines for submitting proposals and giving talks
• I have read and acknowledged the PyDelhi accessibility guidelines and will ensure my presentation materials (slides, videos, demos) follow these recommendations
• 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

This session is designed to be highly interactive and beginner-friendly while still introducing modern AI engineering concepts used in production systems today.

I’m also happy to adapt the depth of the content depending on the audience profile (students, early-career developers, or experienced engineers).

[github-actions]

Thank you for submitting your proposal! 🎉

Hi @Devgr72! Thank you for taking the time to share your learnings with the PyDelhi community! 👋

The PyDelhi volunteer team (@pydelhi/reviewers) has been notified of your submission and will review it as soon as possible. We appreciate your patience during this process.

What happens next?

1. Review process: The team will review your proposal as soon as possible.
2. Feedback: Reviewers may reach out to seek clarifications or suggestions to help strengthen your proposal, to ensure it aligns with our guidelines, and to make it more engaging for the audience. Please keep an eye on your notifications!
3. Confirmation: Once your proposal is formally accepted, the event logistics will be coordinated with you, including scheduling and any necessary preparations.
4. Support: First-time speakers can seek mentorship and practice sessions if needed, subject to the availability of the team. Please let us know!

Important reminders

• Please make sure you have read and understood the guidelines for submitting proposals and delivering talks, as well as our accessibility guidelines.
• All talks/sessions are licensed under a Creative Commons Attribution-Non Commercial-ShareAlike 4.0 International License, unless you state otherwise in your proposal above. This means that your talk can be shared and adapted for non-commercial purposes, as long as appropriate credit is given and any derivative works are shared under the same license.
• Please follow PyDelhi's Code of Conduct and maintain a welcoming, inclusive environment throughout your participation.

Questions?

Feel free to:

• Join the PyDelhi WhatsApp community
• Join the PyDelhi Telegram group
• Send us an email at contact@pydelhi.org
• Write to us in a comment below this message! :)

Thank you again for contributing to the Python community in Delhi! 🐍❤️

---

Improve this questionnaire: Did you find a bug, or do you have suggestions? Please feel free to add them as a comment below or open a separate issue as you prefer. We welcome contributions to improve this proposal form and the overall process!

This is an automated message. The review team will be with you shortly!

This proposal form was inspired by and enhanced with ideas from BangPypers. Thank you to the BangPypers community for sharing best practices!

[kybrdbnd]

hi @Devgr72 , thank you for the proposal. This talk seems to be aligned with the Introductory Understanding of RAG AI, is this what you are intending to do? Can you please share the slide deck for the review.

Thank you

[Devgr72]

Hi @kybrdbnd — thanks for picking this up! Yes, you've read it right: it's an introductory, practically-oriented session on RAG, AI agents and memory. The aim is to take folks from "using AI tools" to understanding how modern AI apps are actually built, with a lightweight live RAG demo (LangChain + ChromaDB) along the way.

I've attached the slide deck for review. Quick overview of the flow:

Kept it beginner friendly and accessible per the guidelines, and I'm happy to dial the depth up or down based on the expected audience. Open to any feedback on scope or pacing and I can trim/expand sections to fit the slot. Code + demo repo will be shared with attendees after the talk. Thanks again for reviewing! 🙏

PyDelhi RAG Agents Memory.pptx