~/talk

Building complex data visualisations using ChatGPT

name:Greg Nash
links:none on file
slides:none on file

Uses ChatGPT plus Vega-Lite inside Power BI via Deneb to generate JSON specs iteratively, turning raw daily temperature and rainfall tables into a layered visualization with day-by-day min/max columns, an all-time min/max background band, an all-time average line and a cumulative rainfall subplot. Workflow relies on many small iterative prompts rather than one huge prompt, deals with context forgetting, and produces the finished custom visual in about 3 hours of back-and-forth.

AI-written summary · about

  1. 0:00Introduction to session
  2. 3:32Tools for visualization
  3. 10:11Iterative prompting strategy
  4. 16:34Starting with simple visuals
  5. 27:47Iterating to final result
  6. 31:56Tips and best practices
  7. 34:23Q&A and closing
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.