Loading video...

Video Failed to Load

Go Home

Finally rolling out the full Agent Session Explorer OSS next week 👀 Visualize every coding agent trace Identify root cause errors Feed it back to your coding agents to improve with every agent trace

35,326 views • 16 days ago •via X (Twitter)

20 Comments

Eshwar Prasad Yaddanapudi's profile picture
Eshwar Prasad Yaddanapudi16 days ago

@VaraadDurgaay

maxi.me's profile picture
maxi.me15 days ago

I’d love to see this applied to browser and workflow agents too. Anthropic’s latest report shows why. When an agent submits a real form or bypasses an access restriction, understanding the exact sequence of actions becomes pretty important. Especially when the final output looks perfectly normal

我与梦想有个约会's profile picture
我与梦想有个约会15 days ago

cool

Aranđel's profile picture
Aranđel15 days ago

events box, fix height 🙏

Simon Loewen's profile picture
Simon Loewen16 days ago

the feed it back to your coding agents part is what I'm curious about. when an agent reads its own trace, does it go after the real root cause or just blame whatever step threw the error last? that's where mine usually get it wrong, I think. will look for the OSS drop next week.

Aiswarya Sankar's profile picture
Aiswarya Sankar15 days ago

We cross check against pr review errors

Chen's profile picture
Chen16 days ago

feeding agent traces back to fix errors is such a smart closed loop. excited to see the oss drop next week.

Vera Ai | Tools & Updates's profile picture
Vera Ai | Tools & Updates16 days ago

Open-source visibility into agent traces could make debugging so much easier

Kevin Rajan's profile picture
Kevin Rajan15 days ago

bruh...pls anchor the heights of the rows in the last column im about to have a seizure 😭😂 overall looks super cool tho!

Aiswarya Sankar's profile picture
Aiswarya Sankar15 days ago

😅 ok ok

CryptoFro's profile picture
CryptoFro15 days ago

This is the interface very frontier labs has to peek into everyone’s chat

Sujal's profile picture
Sujal16 days ago

feeding traces back to the agent closes the loop most teams leave open

Edgar Arakelyan's profile picture
Edgar Arakelyan15 days ago

Would be nice to have something like this for every agentenv agent It seems possible to support through our usage of a2a

BitAres's profile picture
BitAres15 days ago

Can I jump from a failed tool call straight to its inputs and result?

Pavel Kerbel's profile picture
Pavel Kerbel15 days ago

How will feedback move from a trace into lasting repo context? I'd keep the trace as evidence and propose a narrow lesson for review, ideally with a regression test, so one failed run doesn't become a rule every later agent inherits.

Aiswarya Sankar's profile picture
Aiswarya Sankar15 days ago

Sessions are mined in mass and in doing so several repeat patterns show up

Benedikt Sanftl's profile picture
Benedikt Sanftl15 days ago

we already closed the loop, hillclimbing to the max

D's profile picture
D15 days ago

Looks amazing, well done!

Caelan C's profile picture
Caelan C16 days ago

Crazy

Zan's profile picture
Zan15 days ago

These look cool but are useless for humans to understand like so many of these tools that pop up with millions of data points.

Related Videos