For those working with AI agents, what tools are you using to log and monitor usage?

I m looking for something that can help:

1. Track which LLM calls or system prompts are failing

2. Identify where the agent logic went wrong

3. Provide analytics for improving the agent s performance

Do you rely on existing tools (would love names + pros/cons), or do you build in-house logging/monitoring solutions?

I ve seen more devs jumping on it lately, but curious how is it actually benefiting you?

Here s my current flow:

1 Plan the feature

2 Build with @Cursor

Hi everyone!

I'm Arnold, a mobile developer turned founder, and I m building FinalRun with my cofounder Ashish @droidash , who previously worked at SmartBeings, a startup that built Alexa-like smart home devices back in 2017.

Over the years, we ve both felt the pain of writing and maintaining mobile UI tests that constantly break, especially when relying on fragile selectors, slow execution, and complex setups.

That s why we re building FinalRun from the ground up not just another test framework, but a rethink of how testing should work in the age of AI.

Today marks my 500th day in a row on Product Hunt, and I wanted to share a few reflections from this journey, in case it sparks ideas or conversation with others in the community.