Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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

20,960 görüntüleme • 10 gün önce •via X (Twitter)

20 Yorum

Eshwar Prasad Yaddanapudi profil fotoğrafı
Eshwar Prasad Yaddanapudi10 gün önce

@VaraadDurgaay

maxi.me profil fotoğrafı
maxi.me10 gün önce

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 profil fotoğrafı
我与梦想有个约会10 gün önce

cool

Aranđel profil fotoğrafı
Aranđel9 gün önce

events box, fix height 🙏

Simon Loewen profil fotoğrafı
Simon Loewen10 gün önce

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 profil fotoğrafı
Aiswarya Sankar9 gün önce

We cross check against pr review errors

Chen profil fotoğrafı
Chen10 gün önce

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 profil fotoğrafı
Vera Ai | Tools & Updates10 gün önce

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

Kevin Rajan profil fotoğrafı
Kevin Rajan9 gün önce

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 profil fotoğrafı
Aiswarya Sankar9 gün önce

😅 ok ok

CryptoFro profil fotoğrafı
CryptoFro9 gün önce

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

Sujal profil fotoğrafı
Sujal10 gün önce

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

Edgar Arakelyan profil fotoğrafı
Edgar Arakelyan9 gün önce

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

BitAres profil fotoğrafı
BitAres9 gün önce

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

Pavel Kerbel profil fotoğrafı
Pavel Kerbel10 gün önce

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 profil fotoğrafı
Aiswarya Sankar9 gün önce

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

Benedikt Sanftl profil fotoğrafı
Benedikt Sanftl9 gün önce

we already closed the loop, hillclimbing to the max

D profil fotoğrafı
D9 gün önce

Looks amazing, well done!

Caelan C profil fotoğrafı
Caelan C10 gün önce

Crazy

Zan profil fotoğrafı
Zan9 gün önce

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

Benzer Videolar