Tencent EdgeOne
Deliver Fastest and Most Secure Performance at the Edge
Start new thread

Tencent EdgeOne Makers - Ship AI agents like web apps, in minutes.

by•
Tencent EdgeOne Makers is an edge platform for modern web apps and AI agents. Build with your preferred frameworks and deploy through familiar CLI, Git, and CI/CD workflows. Get built-in agent runtime, sandboxed tools, memory, observability, model gateway support, serverless functions, and storage—without stitching together complex infrastructure. Add AI agents to existing products or launch new AI applications in minutes. Deploy AI agents like web apps.

Add a comment

Replies

Best
Since it supports multi-agent setups like CrewAI, how detailed is the built-in observability when tracing complex, multi-turn agent loops at the edge? Can we monitor specific tool call latencies directly from your platform?
Maker

   Yes. You can view detailed information about both LLM invocations and tool executions, including execution time, inputs, and outputs.

For more details, please refer to:

Maker

   Just to add on the multi-agent side: CrewAI is auto-instrumented, so sub-agent handoffs and node transitions get traced with zero code changes — each run becomes a full trace tree, not flattened logs.

For tool latency, every tool span carries its own timing, inputs, and outputs, and you can filter by conversation_id to follow a whole multi-turn session.

Going from a prototype my team is excited about to something customers can actually use has always been the slow part. This looks like it shortens that a lot.

Maker

 Thanks — that’s exactly the gap we’ve been focused on.Getting a prototype running is usually the easy part; making it usable in real customer scenarios is where things tend to slow down.😊

Maker

   That stretch — from "the team loves the prototype" to "customers are actually using it" — is exactly where momentum usually dies. Shortening it is the whole reason we built this, so it means a lot to hear it reads that way. Hope it feels just as fast when you put it to work.

As we scale, "does it stay reliable under load" matters more than features. Glad to see that treated as a first-class concern here.

Maker

Thanks, that’s exactly how we think about it.Reliability usually becomes the real focus once systems start seeing real load.❤️

Maker

     Couldn't agree more — past a certain point, one more feature doesn't matter if the thing falls over under load. Reliability isn't a checkbox we added late; it's the part the whole platform is built around. Hope it earns your trust when you push it hard.

Congrats on shipping this! between the build, the copy, the visuals, and then actually getting eyes on it... it's a grind most people don't see. Been in the trenches myself with a similar kind of launch recently, so I know exactly how much went into this. Wishing you success🚀
Maker

 Thank you, this genuinely means a lot — and yeah, you nailed it, the "getting eyes on it" part is its own grind on top of building the thing. Respect to anyone who's been in those trenches. Hope your recent launch is going well too — rooting for you 🚀

Maker

 Really appreciate this! The part nobody sees is exactly the part that takes the most out of you. Knowing it's coming from someone who just went through the same trenches makes it land even more.

First
Previous
•••
345