GDG London x Prompt Engineering Conference – Pre-Conference Meetup

Name: GDG London x Prompt Engineering Conference – Pre-Conference Meetup
Start: 2025-09-30T18:00:00+01:00
End: 2025-09-30T19:30:00+01:00

GDG London

Before the world’s first Prompt Engineering Conference lands in London on October 16, we’re giving the community an exclusive sneak preview!

Sep 30, 5:00 – 6:30 PM (UTC)

78 RSVP'd

Key Themes

About this event

GDG London is thrilled to invite you to a free online pre-event meetup on September 30th, where our conference speakers will deliver their sessions — live, interactive, and free of charge.
✨ What you’ll get:
A front-row look at cutting-edge prompt engineering techniques
Insights from world-class experts shaping the future of AI development
The chance to ask questions, connect, and get inspired alongside fellow developers
Whether you’re already experimenting with AI coding assistants or just curious how prompt engineering can boost your career, this is the perfect starting point.
👉 Reserve your free spot now and be part of the London AI developer community leading the way!
 🎉 Community Bonus: Get 30% off the full Prompt Engineering Conference ticket (London, October 16) with our special GDG London discount code: https://lu.ma/2025-q4-london-prompt-engineering-conference?coupon=GDG30

When

Tuesday, September 30, 2025
5:00 PM – 6:30 PM (UTC)

Agenda

5:00 PM	Welcome remarks
5:15 PM	From Prompt to Production with Firebase Studio & Gemini Code Assist by Muhammad Ahsan Ayaz	How many great ideas have died on your machine, forever trapped in the "localhost graveyard"? For many developers, the excitement of a new project is quickly buried by the mountain of setup, boilerplate, dependency management, and CI/CD configuration required to go live. We spend more time on the how than the what, and innovation suffers for it. What if we could skip the boring parts and focus purely on creation? This session introduces a revolutionary new workflow that takes you from a single natural language prompt to a fully deployed, production-ready application. Join me for a live, end-to-end demonstration of Firebase Studio, an integrated, agentic workspace powered by Gemini. We will start with a simple idea for an app and watch as the AI: - Collaborates on the app's features and architecture. - Generates the full-stack codebase (frontend, backend, and database rules). - Provisions a complete, pre-configured development environment. - Detects runtime errors in its own code and autonomously proposes fixes. - Iteratively adds complex features through conversational prompts. - Manages the entire deployment process, publishing the app to a live, public URL. By the end of this talk, you will not only understand how this new generation of AI tools works but also be inspired to finally resurrect your own side projects and ship them to the world.
5:45 PM	Logic Meets Automation: How DSPy and Prolog-Style Reasoning Boosted GPT-3.5 Accuracy by 19.5% by Meenatchi Sundari	Large Language Models (LLMs) often fail not because they lack capability, but because the prompts guiding them are inefficient. Manual prompt engineering is slow, inconsistent, and nearly impossible to scale. In this talk, I’ll share how I tackled this in my open-source project, prompt-eng-gsm8k-gpt3.5-dspy, where I used DSPy to automate prompt creation and tuning for the GSM8K mathematical reasoning benchmark. By defining tasks declaratively in DSPy and letting its compiler handle generation and refinement, I compared zero-shot (55.0%), few-shot (60.5%), chain-of-thought (68.0%), self-consistency (72.5%), Prolog-style (71.0%), and my Enhanced Prolog method — which achieved 74.5% accuracy, a 19.5% gain over zero-shot and 6.5% over CoT, while using less time and tokens than self-consistency. This Enhanced Prolog approach structures the LLM’s reasoning as logical facts and inference rules, making outputs: • More accurate by avoiding reasoning leaps • Debuggable via traceable steps • Machine-verifiable through logical consistency checks Attendees will learn: 1. How DSPy automates and scales prompt optimization. 2. When to use zero-shot, CoT, few-shot, self-consistency, or logic-based prompting. 3. How Prolog-style reasoning improves reliability and explainability. 4. Setting up A/B testing pipelines for prompt evaluation. 5. Debugging workflows for more trustworthy LLM outputs. Packed with real metrics, open-source code, and a reproducible workflow, this talk moves you from guesswork to data-driven prompt engineering that’s explainable, efficient, and production-ready.
6:15 PM	Closing remarks

Speakers

Meenatchi Sundari

Royal Holloway, University of London

Muhammad Ahsan Ayaz

Scania

Software Architect, Award winning Educator, Google Developer Expert, Speaker, Author

Organizers

Renuka Kelkar

techpowergirls

GDG Organizer

See bio

Sumith Damodaran

sitecore

PM / GDG Organizer

See bio

Chris Bouloumpasis

GDG Organizer

See bio

Goran Minov

Okta

Regional Technical Strategist | GDG Organizer

See bio

Inès Rigaud

GDG Organizer

See bio

Mihaela Peneva

GDG Organizer

See bio

Stefan Cornea

01founders

GDG Organizer

See bio

Sara Mita Gabriel

Organiser

See bio

Contact Us

GDG London x Prompt Engineering Conference – Pre-Conference Meetup

Sep 30, 5:00 – 6:30 PM (UTC)

Key Themes

About this event

When

Agenda

Speakers

Meenatchi Sundari

Muhammad Ahsan Ayaz

Organizers

Renuka Kelkar

Sumith Damodaran

Chris Bouloumpasis

Goran Minov

Inès Rigaud

Mihaela Peneva

Stefan Cornea

Sara Mita Gabriel

Sep 30, 5:00 – 6:30 PM (UTC)