~/talk

Building AI Apps That Don't Break: Architecture Lessons from HappyFox

name:Barath C
links:none on file
name:Anand KS
links:none on file
slides:none on file

HappyFox describes concrete engineering choices: a production AI suite (chatbot, copilot chat, writing assistant, ticket summary, KB draft) used by ~12,000 customers and built to preserve factuality and speed. Architecture moves from simple RAG to an agentic multi-agent workflow that decomposes tasks, uses smaller models (switched to Claude 3 / 3.5 Haiku from Sonnet/Opus) to cut latency and cost, adds metadata-based search during ingestion to avoid wrong retrievals, and implements prompt caching, role-based tool access, and redaction/anonymization for PII.

AI-written summary · about

  1. 0:00Introduction and HappyFox overview
  2. 3:11HappyFox AI platform workflow
  3. 9:44Architectural lessons from AI features
  4. 17:45Designing AI apps for scale
  5. 31:15Q&A and closing remarks
~/search
type to search 6,518 conferences, 143,918 speakers and 192,133 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
← →
on a talk: 5 seconds back / forward
0–9
on a talk: jump to 0%–90% of the recording
?
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.