~/talk

Boundaries of Multi Agent Systems

slides:none on file

An open-source testing agent called TestZeus Hercules executes plain-English tests end-to-end using a multi-agent architecture: a centralized planner agent that produces step-by-step plans, specialized agents (browser nav using Playwright, API, SQL, security via Nuclei, accessibility via axe-core), a chat-manager coordinator, and short‑/long‑term memory to combat context rot. The repo shows 36,000+ installs and 200+ community members, enforces single-responsibility and one-tool-at-a-time rules, includes a CAPTCHA solver and extra tools inventory, and uses eval-style test suites to verify capabilities.

AI-written summary · about

  1. 0:00Introduction and setup
  2. 1:25Audience interaction and maturity check
  3. 4:46Open source testing agent demo
  4. 8:53Multi-agent architecture and planning
  5. 13:32Memory and context management
  6. 17:32Agent tools and system prompts
  7. 19:44Use cases and future potential
  8. 21:31Q&A session
~/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.