From Prompt to Production: Building Real LLM Apps with RAG & Agents

[anujsainimca]

Talk title

From Prompt to Production: Building Real LLM Apps with RAG & Agents

Short talk description

This talk focuses on how to move beyond simple prompts and build real-world LLM-powered applications using Retrieval-Augmented Generation (RAG) and agentic workflows. We will explore how LLMs interact with external data, tools, and memory to solve practical problems. Through a live demo, attendees will learn how to build a document Q&A system and extend it into a simple agent capable of multi-step reasoning. This session is designed for Python developers and data enthusiasts looking to understand how modern AI systems are actually built and deployed in production.

Long talk description

Large Language Models are powerful, but real-world applications require more than just prompting. This talk bridges the gap between experimentation and production by introducing two key paradigms: Retrieval-Augmented Generation (RAG) and agent-based systems.

We will begin by understanding the limitations of standalone LLMs, including hallucinations and lack of real-time knowledge. From there, we introduce RAG — a technique that connects LLMs with external data sources using embeddings and vector databases, enabling accurate and context-aware responses.

Next, we explore agentic systems, where LLMs can reason, plan, and use tools to complete multi-step tasks. We will discuss how agents differ from simple pipelines and when to use them effectively.

The session includes a live coding demo where we:

Build a document-based Q&A system using RAG
Extend it into a simple agent that can perform multi-step tasks

By the end, attendees will have a clear understanding of how to design, build, and extend LLM applications for real-world use cases.

What format do you have in mind?

Workshop (45-60 minutes, hands-on)

Talk outline / Agenda

• Introduction: From prompts to real applications (5 mins)
• Limitations of plain LLMs (hallucination, no memory) (5 mins)
• RAG fundamentals (embeddings, retrieval, generation) (10 mins)
• Live Demo: Build a document Q&A system (10 mins)
• Introduction to agents (tools, planning, workflows) (10 mins)
• Live Demo: Simple agent with multi-step reasoning (10 mins)
• Best practices + pitfalls (5 mins)
• Q&A (5–10 mins)

Key takeaways

• Understanding of how RAG improves LLM accuracy using external data
• Practical knowledge of building a document Q&A system in Python
• Clear distinction between pipelines and agent-based systems
• Best practices for designing scalable LLM applications
• Awareness of common pitfalls like hallucination and poor retrieval

What domain would you say your talk falls under?

Data Science and Machine Learning

Duration (including Q&A)

45 minutes (35 min talk + 10 min Q&A)

Prerequisites and preparation

• Basic Python knowledge
• Familiarity with APIs (helpful but not required)
• No prior experience with LLMs required

Resources and references

No response

Link to slides/demos (if available)

No response

Twitter/X handle (optional)

No response

LinkedIn profile (optional)

No response

Profile picture URL (optional)

No response

Speaker bio

I am an AI practitioner with 15+ years of experience working across machine learning, NLP, and large-scale data systems. I have been actively working on Generative AI applications, including LLM-based systems, RAG pipelines, and agentic workflows. I enjoy mentoring students and professionals in building practical, production-ready AI solutions. I have also conducted multiple sessions and workshops focused on applied AI and real-world problem solving.

Availability

09/

Accessibility & special requirements

No response

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

No response

[github-actions]

Thank you for submitting your proposal! 🎉

Hi @anujsainimca! 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!

[vaibhavjain-in]

Hi @anujsainimca

Thanks for your proposal. The proposal is the quintessential "AI 101" talk that has become oversaturated in the tech community over the last two years. While the title uses the word "Production," the content—covering hallucinations, basic RAG, and "what is an agent"—suggests a beginner-level walkthrough that most intermediate developers have already seen multiple times. RAG fundamentals (embeddings/retrieval) are now considered "common knowledge" in the Python ecosystem.
This content may be better suited for a student-led track