Recent activity
Panels, talks & launches
Hosting a panel on enterprise AI agents in San Francisco
I moderated and gave the keynote for a panel with leaders from ServiceNow, TikTok, Tencent, and VeloDB on enterprise AI agents, agent safety, governance, and how frontier labs and traditional enterprises differ on AI.
Read more →Open-sourced AgentX-Trace-Eval
The trust layer for AI agents on any platform: trace and evaluate agent runs with OpenTelemetry-compatible spans, run golden-dataset and online evals, and score with LLM-as-judge.
Read more →
▶ VideoAgentX evaluation framework hit #1 on Product Hunt
We launched the AgentX evaluation framework on Product Hunt and finished #1 Product of the Day. Evaluate AI agents before they fail: test suites, evals, AI-driven root cause analysis, and multi-LLM simulation, like CI/CD for AI agents.
Read more →
▶ VideoAgentX 2.0 launched on Product Hunt: #3 of the day, #2 of the week
We launched AgentX 2.0, a multi-agent build platform, on Product Hunt and finished #3 Product of the Day and #2 Product of the Week. Build different AI agents and watch them collaborate, across every major LLM, with 1000+ tools and MCPs.
Read more →