BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/London
X-WR-TIMEZONE:Europe/London
BEGIN:VEVENT
UID:1891@siliconbrighton.com
DTSTART;TZID=Europe/London:20261125T174500
DTEND;TZID=Europe/London:20261125T194500
DTSTAMP:20261118T170604Z
URL:https://siliconbrighton.com/events/the-ai-data-team-brighton-data-foru
 m/
SUMMARY:The AI Data Team – Brighton Data Forum
DESCRIPTION:This month\, returning presenter and long-time supporter of the
  forum Mark Rittman\, CEO at Rittman Analytics will tell us about "Teachin
 g AI to Work Like a World-Class Data Team"\nCoding agents such as Claude C
 ode can now build data pipelines\, write SQL transformations and create da
 shboards in minutes. But speed is not the same as getting it right. Left t
 o themselves\, they guess at requirements\, skip tests and produce work th
 at is hard to review or maintain.\nAt Rittman Analytics we hit these probl
 ems early. Our answer was Wire\, a framework that gives AI agents the stru
 cture we give a new consultant: defined project stages\, agreed standards 
 for data models and code\, automated checks at each step and a person who 
 approves the output. It runs inside the AI tools we already use and draws 
 on a shared registry of our delivery processes. It has since grown into ho
 sted agents that join our project teams\, each with its own access to GitH
 ub\, Jira\, Slack and the client’s cloud data platform.\nThis talk walks
  through how Wire works\, using examples from real projects on BigQuery\, 
 dbt and Looker. We cover what improved\, what went wrong and which decisio
 ns we still keep with people."\nFor reference\, here's the docs and the Cl
 aude Code plugin and a few blog posts that describe what I'll be talking a
 bout.\nWe will be warmed up by our own Ashley Oldershaw\, who is talking a
 bout IoT sensor data.\nHave you ever built something assuming that a low-f
 requency annoying chore will barely ever happen\, only for it to immediate
 ly happen twice? That's what happened as soon as I finished our migration 
 from InfluxDB to BigQuery for our IoT data at Naked Energy\, and we found 
 out a sensor had been misconfigured and we had to correct its historical d
 ata.\nWe are a small team covering a lot of ground\, so data pipelines tha
 t work only get touched when we have a really good reason to. This means t
 hat making a recoverable tool is absolutely crucial so it doesn't distract
  us while we are working on other stuff.\nWe went from a transform-on-read
  setup that coupled our data storage to our Django instance\, to a transfo
 rm-on-write setup that meant we could use BigQuery independently. We immed
 iately got buyer's remorse when we had to correct a bunch of historical re
 adings twice\, and I was staring the solution in the face while teaching m
 edallion architecture and dbt at Silicon Brighton's EVOLVE [26].\nAfter th
 is talk you'll have an idea of how to build a data pipeline with BigQuery 
 and dbt with minimal setup\, excellent recoverability and the knowledge yo
 u won't be making the same mistakes as me.\nIf you are stretched thin or s
 tarting a big migration\, or just like hearing stories\, this talk is for 
 you.\nPlease be punctual\, the event starts with networking and refreshmen
 ts at 17:45\, with the talks and live stream starting at 18:20.\nThe event
  is hosted by our loyal hosts at Barclay's Eagle Labs in their Platf9rm of
 fices.\nThe Brighton data forum is supported by Silicon Brighton and spons
 ored by Rittman Analytics.
ATTACH;FMTTYPE=image/jpeg:https://siliconbrighton.com/wp-content/uploads/2
 026/11/all-newsletter-images-3.png
CATEGORIES:Brighton Data Forum,Silicon Brighton Event
LOCATION:PLATF9RM Brighton\, Tower Point\, 44 North Road\, Brighton\, BN1 1
 YR\, United Kingdom
GEO:50.825635;-0.141572
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Tower Point\, 44 North Road
 \, Brighton\, BN1 1YR\, United Kingdom;X-APPLE-RADIUS=100;X-TITLE=PLATF9RM
  Brighton:geo:50.825635,-0.141572
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/London
X-LIC-LOCATION:Europe/London
BEGIN:STANDARD
DTSTART:20261025T010000
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
END:STANDARD
END:VTIMEZONE
END:VCALENDAR