Steph Johnson

1.1K posts

Steph Johnson banner
Steph Johnson

Steph Johnson

@BkStephJ1

CEO @trymultiplayer, the debugging agent for developers. Ex- @mongodb and @digitalocean.

No sleep til Bklyn Katılım Aralık 2009
337 Takip Edilen362 Takipçiler
Sabitlenmiş Tweet
Steph Johnson
Steph Johnson@BkStephJ1·
Give your AI tool the data it needs to automatically fix bugs. APMs sample heavily and miss critical content. Multiplayer captures unsampled, full-stack session data and feeds your agent exactly the runtime context it needs. Confident fixes start with complete runtime data.
Multiplayer@trymultiplayer

Multiplayer: the debugging agent for developers. We connect your favorite coding agent to prod to fix application bugs automatically. Run us locally and eliminate PR slop.

English
1
0
2
58
Steph Johnson
Steph Johnson@BkStephJ1·
That moment when a user gets it never gets old. Walked someone through our live demo today. The CLI wizard had everything set up in under a minute. They came in skeptical, but by the time the first issue surfaced automatically, they just watched the agent work.
English
0
0
1
42
Steph Johnson
Steph Johnson@BkStephJ1·
That's a different question, and it leads to different decisions: about what data agents work from, about how issues get deduplicated before they reach a reviewer, about what a merge-ready PR actually means.
English
0
0
0
12
Steph Johnson
Steph Johnson@BkStephJ1·
Team efficiency is a different goal than individual velocity. The developers I find most interesting right now don’t ask 'how do I ship more with AI?', instead they ask 'how do I make sure what we ship is worth keeping?'
English
1
1
2
500
Steph Johnson
Steph Johnson@BkStephJ1·
Full disclosure: those of you who know me will appreciate that I set this up myself. VS Code, npm install, the whole thing. The wizard did most of the heavy lifting, which is exactly the point. 😆
English
0
0
0
16
Steph Johnson
Steph Johnson@BkStephJ1·
I could tell you the debugging agent catches and fixes bugs on its own. Or you could just watch it happen.👇
Steph Johnson tweet media
English
1
0
1
66
Steph Johnson
Steph Johnson@BkStephJ1·
Taking full advantage of agents means redesigning workflows that were built for humans. And that redesign starts with the data you feed them.
English
1
0
0
6
Steph Johnson
Steph Johnson@BkStephJ1·
David Fowler nails something that gets glossed over in most AI productivity discussions: 👇 Everyone is celebrating the speed of shipping. Fewer people are asking what happens to the codebase six months later when nobody fully understood what they shipped.
Steph Johnson tweet mediaSteph Johnson tweet media
English
1
0
0
18
Steph Johnson
Steph Johnson@BkStephJ1·
I’m very grateful to our team and early users who got us here. 💜
English
0
0
0
2
Steph Johnson
Steph Johnson@BkStephJ1·
Better tooling for agents produces better code, in production debugging and in open source contributions. Getting Multiplayer into more developers' hands is the most direct way to ensure higher quality PRs (and software).
English
1
0
0
7
Steph Johnson
Steph Johnson@BkStephJ1·
We just open sourced Multiplayer. Some may think this is the worst possible time for that decision: maintainers drowning in AI-generated PR slop, projects folding, and dramatic declarations that 'open source is dead.' 🧵 👉 github.com/multiplayer-ap…
English
1
0
0
20
Steph Johnson
Steph Johnson@BkStephJ1·
Give your AI tool the data it needs to automatically fix bugs. APMs sample heavily and miss critical content. Multiplayer captures unsampled, full-stack session data and feeds your agent exactly the runtime context it needs. Confident fixes start with complete runtime data.
Multiplayer@trymultiplayer

Multiplayer: the debugging agent for developers. We connect your favorite coding agent to prod to fix application bugs automatically. Run us locally and eliminate PR slop.

English
1
0
2
58
Steph Johnson
Steph Johnson@BkStephJ1·
Raw output was never the real bottleneck. System design, infrastructure decisions, architectural judgment: that's what compounds or creates drag over time. AI still struggles to get those right.
English
1
0
0
3
Steph Johnson
Steph Johnson@BkStephJ1·
The 10x engineer has never been the person who coded the fastest. This is now more true than ever. And, it should reframe how you think about AI productivity.
Steph Johnson tweet media
English
1
0
0
15
Steph Johnson
Steph Johnson@BkStephJ1·
Automatic capture and correlation of every piece of data from a user's session plus the corresponding system behavior.
English
0
0
0
5
Steph Johnson
Steph Johnson@BkStephJ1·
The problem: AI generates code faster than teams can review (and debug) it. The constraint: AI tools need complete visibility into runtime context, not sampled fragments, to more accurately generate code or assist with debugging. The solution: 👇
English
1
0
1
10