ClickHouse Singapore August 2026 Edition
We're back with another exciting meetup in Singapore for 2026! Come join us for an evening of learning from database experts, and great conversations with the ClickHouse and Women in Tech SG community, hosted at IMDA office.
🗓️ AGENDA:
6:00 PM: Registration, Dinner & Chitchat
7:00 PM: Welcome and Introductions
7:10 PM: Talk 1 - The Model Gets the Headlines. The Database Wins the Race by Siddhant Agarwal, Senior Developer Relations Advocate @ ClickHouse
7:40 PM: Talk 2 - From Prompt to PASS/FAIL: Production LLM Certification on Langfuse + ClickHouse by Yisam Lee, Senior Support Engineer @ ClickHouse
8:10 PM: Talk 3: Everything Is a Language Problem Now by Uli Hitzel, AI Strategist @ naida
8:25 PM: Wrap-up and Networking
👉🏼 RSVP to secure your spot!
Interested in sharing a talk at this meetup or future events? Complete this CFP form and we’ll be in touch.
🎤 Session Details: The Model Gets the Headlines. The Database Wins the Race
Everyone is arguing about which model is best. Almost nobody is talking about the system underneath it. In F1, the driver gets the trophy, but the car decides who is on the podium. Production AI works the same way: the model is the part users see, while the data layer decides whether your product feels instant or unusable. This talk maps the F1 grid onto a production AI system: models as drivers, data as fuel, observability as telemetry. Then it shows the full loop live: natural language questions over F1 race data through LibreChat, an agent querying ClickHouse via MCP, and every request traced in Langfuse, with latency, tokens, and cost queryable as plain SQL. You'll leave knowing how to instrument your AI system like a race engineer, and why the teams that win are the ones that build the whole car.
Speaker: Siddhant Agarwal, Senior Developer Relations Advocate, APAC, ClickHouse
Siddhant Agarwal leads Developer Communities for APAC at ClickHouse. Prior to ClickHouse, Sid was with Neo4j and Google. He is passionate about tech communities and has built India’s first fintech developer community at Open Financial Technologies and worked with Google Developer Relations programmes including GDSC, TFUG, GDG, and GDE. He has nearly a decade of experience building developer and startup communities globally and is among ACM’s Distinguished Speakers (one of 200+ worldwide, 20+ in India).
🎤 Session Details: From Prompt to PASS/FAIL: Production LLM Certification on Langfuse + ClickHouse
Every team shipping LLM features into production hits the same wall around month three: the model works in eval notebooks but nobody can prove what it's doing in production. Evals tell you the model "scored 87% on a held-out set last Tuesday." Certification gives you a PASS/FAIL artifact, item-level lineage, and a queryable audit trail that survives the engineer who built it leaving the company. Different deliverables. Different audiences. Most teams confuse the two and ship the wrong one.
This session walks through a working open-source pipeline that produces certifications, not just scores. It's built on Langfuse for tracing and prompt management, and on ClickHouse for everything analytical
Speaker: Yisam Lee, Senior Support Engineer @ ClickHouse
🎤 Session Details: Everything Is a Language Problem Now
In this session, we talk about what happens when the way into a system is a well-written sentence. Every guardrail written in English can be argued with in English, which means the security of the thing now rests on a skill nobody in the engineering team was hired for, and the colleagues who do have it are usually nowhere near the build. To see why this works, you have to give up on the idea that you are dealing with software. These models behave more like cats, or like something genuinely alien: capable of graduate-level reasoning one moment and unable to count the letters in a word the next, responsive to tone and framing in ways nobody designed and nobody can fully account for. Words are the only lever you have on that, which is why they cut both ways.
Speaker: Uli Hitzel, AI Strategist @ naida
Uli Hitzel is a hands-on AI technologist and ecosystem builder working at the intersection of artificial intelligence, business transformation, and human creativity. He helps enterprises and startups build with AI rather than just buy it, guiding teams through practical implementation while exploring how AI augments human capabilities across industries. His work spans digital manufacturing at Dyson, GenAI adoption at Heineken, and pandemic-response infrastructure at Raffles Medical, building on two decades in technology at Microsoft, IBM, and others. He has been teaching AI at the National University of Singapore for six years, and founded Electric Minds to connect builders, thinkers, and the perpetually curious across the region.