~/panel

Panel Discussion: Agents in the Wild: Real-World Deployments and Lessons Learned

on YouTube 44m
Panelat Open Agent Summit 2025 · on Tuesday, 2025-10-21· [large-language-models]

speakers

name:Yujian Tang
links:none on file
name:Raji Rajagopalan
links:none on file
name:Diamond Bishop
website:https://ageof.diamonds
name:Mahdi Ghodsi
links:none on file
name:Andrew Hoh
links:none on file

resources

video:https://youtu.be/V0yXMSPm3LU
slides:none on file

summary

Hosts describe concrete deployments: a hosted MCP agent platform, AMD running models via Lemonate and CPU/GPU choices, and Microsoft building observability tools and red teaming. Successful use cases are productivity and coding assistants, audits and customer relation bots, and background ambient agents. Lessons are to run task specific evals, design for non deterministic model failure, add human in the loop and guardrails, and beware runaway costs — one loop costed $40,000 over 11 days.

AI-written summary · about

chapters (9)

  1. 0:00Panelist introductions
  2. 1:45Lessons from AI agent deployments
  3. 7:49Real-world AI agent use cases
  4. 14:07Multi-agent systems and MCP/A2A
  5. 21:25Enterprise AI adoption barriers
  6. 29:14Lightning advice for AI production
  7. 33:38Q&A on agent adoption
  8. 38:14Why AI agents lag adoption
  9. 40:21Edge hardware optimization

related talks

~/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.