The Friendly Data Meetup London

HACKATHON - Agent Eval Harness (by the Friendly Data Meetup)

Wed, Nov 4 · 5:30 PM GMT

230 Blackfriars Road, 230 Blackfriars Rd, London SE1 8NW, UK, London, GB

SIGN UP HERE TO ATTEND 👉 https://luma.com/h8zer2ek

______________________________________________

Hi new friends and old!

The Friendly Data Meetup Hackathon is back by popular demand! 🎉

After the brilliant turnout (and the even more brilliant demos) at our first hackathon in January, we simply had to do it again.

👩‍💻 This evening is all about learning, building, and having fun with friendly faces. No pressure, no pitch decks, just inquisitive minds making cool things with data. With perhaps a slight competitive edge for those seeking glory 😉

📍 We're very grateful to Quantspark for kindly hosting us at their venue for the evening!

💡 The challenge: Judge the Agent ⚖️
Dawdle Deliveries' shiny new AI customer support bot goes live next week. Is it actually ready? Your job is to find out, with evidence instead of vibes!
AI agents are moving into production, and everyone is asking the same question: how do you know it works? Together, we'll find out by building an evaluation harness from scratch:

• 🧪 Write the tests: a set of realistic (and sneaky) customer questions
• ✅ Build the checks: automatic pass/fail checks, plus an AI judge that marks every answer
• 🔧 Fix it and prove it: improve the bot, then show a before/after scorecard proving your fix worked (without breaking anything else!)

The challenge is split into levels, so every team can work at its own pace, and there are bonus rounds (tracing, red-teaming, model shoot-outs) for the speedy ones. We'll finish with quick 3-minute demos: your scorecard, your most interesting failure, and the big question: do you trust your judge? 🤔

Teams of 2-4 will be formed on the night, so don't worry if you're coming solo

✅ Pre-flight checklist
This hackathon is very hands-on, so it's best suited to people who already write code and/or have some working knowledge with data and AI. You'll get the most out of the evening if you:

• Have decent working experience writing code
• Are very comfortable with git, Docker and Python environments
• Are happy to dig in and figure things out with your team (organisers will be around to help, but there won't be step-by-step hand-holding)

🎒 Please bring

• A laptop (charged!) and charger; preinstalled with:
• Docker
• uv
• An LLM of your choice to work with, either:
• your own API key for a hosted provider of your choice, or
• free local models running via Ollama in Docker (no key needed, but allow around 10 GB of free disk space)
• Curiosity and a willingness to collaborate

🌄 On that evening
When you arrive at the venue, show your Luma QR code, and say you're going to Quantspark for the Hackathon.

17:30 - Doors open
18:00 - Hackathon begins
21:00 - Hackathon ends, and building management cut off time
21:01 - Nearby pub!

📶 Wi-Fi will be provided at the venue.

We'll share the starter kit with registered participants before the event, so please download everything (especially the local models) in advance. They're a few GB, and the Wi-Fi is no match for a whole room pulling them at once! 😅

📒IMPORTANT NOTE

To take part in the hackathon, please sign up on the Luma link above. You will be required to show your QR code at the reception. RSVP on Meetup does not count as registration for this event, so sign up on Luma now to secure your place!

Many thanks for your enthusiasm and participation! We can't wait to build with you 😄

Fireside: AI with Prod Data - Hype vs Reality

Thu, Nov 26 · 7:00 PM GMT

230 Blackfriars Road, 230 Blackfriars Rd, London SE1 8NW, UK, London, GB

SIGN UP HERE TO ATTEND 👉 https://luma.com/7kqyiejv

***

Hi new friends and old!

Pull up a chair, it's fireside chat time! 🔥

Everyone's building with AI, but what actually happens once it leaves the demo and meets real users? We've gathered three seasoned folks who've been there to tell us honestly: the wins, the war stories, and the things they wish they'd known sooner.

📍 We're very grateful to Quantspark for kindly hosting us at their venue for the evening!

🎙️ AI with Production Data: Hype vs Reality
A relaxed, honest conversation (no slides, no sales pitches!) covering:

• 🚀 Getting it live: what it really takes to go from prototype to production
• 💥 When it breaks: surprising failures, and how they caught them
• 📏 Knowing it works: testing, evaluation and keeping quality up over time
• 💷 Worth it?: costs, trade-offs, and when not to use AI at all

Then it's over to you: bring your burning questions for the Q&A! 🙋

👥 Meet the speakers

Constantin Petrescu PhD, Machine Learning Engineer Lead at Hurdle
Currently developing an AI-powered Health Insights Engine for healthcare companies to autonomously review personalised health risk scores for patients and prevent diseases.

Nnamdi Odozi, Actuarial AI Strategist at AvE Consulting Works where actuarial science meets machine learning. Has built and deployed AI-driven actuarial, investment and risk models for pension schemes and insurers.

Troy Culley, Data & Analytics Manager at FMCG
Pricing and experimentation specialist. Has built demand-forecasting models, dynamic pricing and large-scale A/B testing programmes that delivered multi-million-pound revenue gains.

Hosted by DL Lim, Founder and Organiser of The Friendly Data Meetup
During the day, DL specialises in deploying production-grade data platforms, agentic AI and analytics solutions specifically for actuarial applications in the insurance industry, through his independent consultancy, Lunox Group.

Who it’s for
Anyone working with AI or Data who wants the honest story behind getting it into production. That includes engineers, data scientists, product managers and team leads. You don’t need to have shipped an AI product yourself, but you’ll get the most out of it if you’ve worked on data or software projects and want to know what really happens once the demo is over.

🌄 On that evening
🕖 7:00pm
📅 26th November 2026
📍 230 Blackfriars Road, London SE1 8NW

When you arrive at the venue, show your Luma QR code, and say you're going to Quantspark for the Friendly Data Meetup.

7:00pm - Doors open, grab a drink and say hello
7:15pm - Fireside chat begins
8:15pm - Audience Q&A
8:35pm - Mingle with the speakers and each other
9:00pm - Building closes, and on to a nearby pub!

📒IMPORTANT NOTE
To attend, please sign up on the Luma link above. You will be required to show your Luma QR code at the reception. RSVP on Meetup does not count as registration for this event, so sign up on Luma now to secure your place!

See you by the fire*! 🔥

*no physical fires are present throughout the event for the health and safety of the organisers and participants of the event.

***

🤝 Code of Conduct:
The Friendly Data Meetup welcomes all genders, nationalities, ethnicities, backgrounds, identities etc. There is a strict no discrimination policy in adherence to our code of conduct and our guiding principles. We maintain a zero-tolerance policy for hateful or antisocial behaviour.
In short, be kind to others. Do not insult or put down others. Behave professionally, don't make others feel uncomfortable. Remember that harassment and sexist, racist, or exclusionary jokes are not appropriate for The Friendly Data Meetup.

🌱 Donations, Volunteers and Patrons Welcome:
The Friendly Data Meetup is completely volunteer run and not for profit.
Donations and ideas are very welcome to fund more exciting activities!
Buy us a coffee or come and chat with us.
Support us: https://friendlymeetup.com/support-us