BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Palaner//palaner Single Event//EN
METHOD:PUBLISH
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:meetup-6f63ee14d5@palaner.app
DTSTAMP:20260802T151348Z
DTSTART:20260804T100000Z
DTEND:20260804T113000Z
SUMMARY:ClickHouse Singapore August 2026 Edition
LOCATION:IMDA Singapore
DESCRIPTION:Saved in Palaner as: saved\n\nPalaner match: 25% · why: lots of
  people going\n\nWe'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\, h
 osted at IMDA office.\n\n🗓️ AGENDA:\n\n6:00 PM: Registration\, Dinner & Ch
 itchat\n7:00 PM: Welcome and Introductions\n7:10 PM: Talk 1 - The Model Ge
 ts the Headlines. The Database Wins the Race by Siddhant Agarwal\, Senior 
 Developer Relations Advocate @ ClickHouse\n7:40 PM: Talk 2 - From Prompt t
 o PASS/FAIL: Production LLM Certification on Langfuse + ClickHouse by Yisa
 m Lee\, Senior Support Engineer @ ClickHouse\n8:10 PM: Q&A & Networking\n\
 n👉🏼 RSVP to secure your spot!\n\nInterested in sharing a talk at this meet
 up or future events? Complete this CFP form and we’ll be in touch.\n\n\n🎤 
 Session Details: The Model Gets the Headlines. The Database Wins the Race\
 nEveryone is arguing about which model is best. Almost nobody is talking a
 bout the system underneath it. In F1\, the driver gets the trophy\, but th
 e 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 pr
 oduct feels instant or unusable. This talk maps the F1 grid onto a product
 ion AI system: models as drivers\, data as fuel\, observability as telemet
 ry. Then it shows the full loop live: natural language questions over F1 r
 ace data through LibreChat\, an agent querying ClickHouse via MCP\, and ev
 ery request traced in Langfuse\, with latency\, tokens\, and cost queryabl
 e 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.\nSpeaker: Siddhant Agarwal\, Senior Developer Relations Advocat
 e\, APAC\, ClickHouse\nSiddhant Agarwal leads Developer Communities for AP
 AC at ClickHouse. Prior to ClickHouse\, Sid was with Neo4j and Google. He 
 is passionate about tech communities and has built India’s first fintech d
 eveloper community at Open Financial Technologies and worked with Google D
 eveloper Relations programmes including GDSC\, TFUG\, GDG\, and GDE. He ha
 s 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).\n\n🎤 Session Details: From Prompt to PASS/FAIL: Producti
 on LLM Certification on Langfuse + ClickHouse\nEvery team shipping LLM fea
 tures into production hits the same wall around month three: the model wor
 ks in eval notebooks but nobody can prove what it's doing in production. E
 vals tell you the model "scored 87% on a held-out set last Tuesday." Certi
 fication gives you a PASS/FAIL artifact\, item-level lineage\, and a query
 able audit trail that survives the engineer who built it leaving the compa
 ny. Different deliverables. Different audiences. Most teams confuse the tw
 o and ship the wrong one.\nThis session walks through a working open-sourc
 e pipeline that produces certifications\, not just scores. It's built on L
 angfuse for tracing and prompt management\, and on ClickHouse for everythi
 ng analytical\nSpeaker: Yisam Lee\, Senior Support Engineer @ ClickHouse
URL:https://www.meetup.com/clickhouse-singapore-meetup-group/events/3155887
 08/
CATEGORIES:palaner,saved
STATUS:TENTATIVE
END:VEVENT
END:VCALENDAR
