@lukerramsden This is 🔥
If you want Devin to watch sessions recordings that are directly connected to the issue, I think you'll like @subtextdev - it's a new session capture product and set of MCP tools our team just launched built for this exactly background agent SRE use case.
We created @subtextdev because every coding agent needs to ground their reasoning in real user experiences. Looking at the codebase and logs simply isn't enough.
If you're an engineer/builder/pm/designer, you already know that. You have spent hours watching user sessions (replays) to truly understand bugs, diagnose root cause, and discover how your users actually experience the features you ship.
If that's you, it's time to let your coding agent do the work.
We shipped a simple but powerful addition to the Subtext MCP tools this week: https://t.co/N6YdQ9l7cV
Now your agent can easily find a specific user's most recent product session (say from a support ticket, @intercom chat, or @SlackHQ message) and automatically review the experience, triage the issue, and draft a fix/PR.
When you capture everything, your agent can be "always-on, 24/7". No need for legacy bug reporting like jam dev
@karpathy 1. This is awesome. 2. “they can't easily audit their work because they aren't able to efficiently and natively perceive” exactly why my team built @subtextdev
@subtextdev is officially in the @OpenAI Codex plugin marketplace!
For everyone building apps, it’s so convenient to have Codex (or Claude, Cursor, Linear, etc) review a user’s recent session and give you a detailed summary or root cause analysis for a bug report.
Go try it free today!
Having fun today vibing out a https://t.co/WaWTTOCWzf bug reporter clone to add to @subtextdev.
Do folks here use Jam? If so what do you like about it? What do you wish was better?
Subtext is live in the Linear directory.
Issues feed the Loop a session link and it runs the investigation. The agent gets tools to zoom into screenshots, network calls and console errors, root cause posted as a comment before an engineer or coding agent opens the issue.
https://t.co/baSzMcy89L
Most important thing for self-driving cars is a solid vision and LIDAR system. Same is true for AI agents. This is exactly why we built @subtextdev, which you can plug into any agent (including Posthog's).
What's the difference between good ol' human Session Replay (HSR) and Agentic Session Review (ASR)? HSR is pretty much Netflix. Hit play and watch. Rewind if you miss something.
ASR is different. Agents don't hit play. They ask a question, get a map of the whole visit, then zoom into just the part that answers it. No rewinding through 42 seconds to find the one moment that mattered.
In this post, @who_cayres and @jgw spell it out better than I ever could. Enjoy.
https://t.co/fByLti5DHV
I had a lot of fun working on the brand identity and mark for @subtextdev this week. It's the first time I've scratched that itch in a while and I'm pretty happy with where I landed.
I'd love to hear what you think.
Congrats to the Fullstory team on launching Subtext! Try it out in the playground, which uses a Managed Deep Agent to review and analyze your live session on their site!
Sign up for our waitlist to ship your own Managed Deep Agents: https://t.co/l95kThyxN6
i've been kicking the tires on subtext, a new tool which lets you figure out what happened in your app leading up to some event, very useful for finding the repro for a bug or error. definitely worth checking out if you're building app reliability tooling