PandaProbe Cloud
Agent Engineering, Fully Managed.
694 followers
Agent Engineering, Fully Managed.
694 followers
PandaProbe Cloud gives your team full-stack tracing, evals, and monitoring for agents with zero infrastructure to manage. Ship better agents without the ops overhead.
How does PandaProbe handle tracing for long running agents that might operate over hours or days and does it maintain trace continuity when an agent is paused, resumed or spawns sub agents mid execution?
@carlos_leonardo1 PandaProbe handles this by flushing spans after each step execution — so no matter how long an agent runs, whether it's minutes, hours, or days, every step is captured incrementally as it happens. You're not waiting for the agent to complete before data shows up.
For pause and resume scenarios, as long as the session ID is carried through the instrumentation wrapper, trace continuity is maintained automatically when the agent picks back up. Same goes for spawned sub-agents — they get attached to the parent session timeline as long as the session context propagates through.
Long-running agents are exactly the use case PandaProbe is built for — the session model was designed with this in mind from the start 🙏
Just curios how is it different from langfuse/smith?
@naor_sabag Great question — LangSmith and Langfuse are built around the trace as the unit of analysis. They're great at showing what happened inside individual LLM calls. PandaProbe is built around the session — the full agent lifecycle — as the unit of analysis.
That distinction matters for long-running, multi-step agents. A trace tells you one step went wrong. A session tells you whether the agent was reliable across the entire trajectory — and our eval metrics, grounded in peer-reviewed research, are purpose-built to catch that. (TRACER, ICML 2026 → https://arxiv.org/abs/2602.11409)
But honestly, tracing and evals are just the foundation. We're building towards something bigger — a complete agent engineering platform that gives teams everything they need to develop, evaluate, and continuously improve agents in production. This launch is the first chapter of that vision. 🙏
The managed eval scheduler stands out here. For agent teams, continuously checking production behavior feels more useful than only debugging after something breaks. Do teams usually start with live traffic or replayed traces?
An idea for future development: instead of only evaluating responses, as most tools do, you could also add automatic benchmarking against other popular models. That would be extremely useful. We'd definitely use something like that ourselves.
looks solid . one question, purely from the security pov. are you gdpr compliant and what about usage data that you store
I like the focus on making agent debugging and monitoring easier. As agent workflows become more complex, having better visibility into what's happening behind the scenes is incredibly valuable.
The fully managed approach is a big plus too.
@gabriella_anjani Thank you, really appreciate that! 🙏
You nailed the core of it — as agent workflows get more complex, visibility isn't a nice-to-have anymore, it's what separates teams that can iterate confidently from those flying blind.
Would love to hear what you're building if you ever want to share — always happy to chat and see how PandaProbe can help.
This is so cool, congrats!
@nafis_amiri Thanks for your support Nafis 🙏