The debugging agent for developers.
Joined January 2023
- Tweets 1,351
- Following 47
- Followers 141
- Likes 632
407 Photos and videos
Pinned Tweet
May 27
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.
1
4
205
Jun 11
With Multiplayer there’s no proprietary agent lock-in, no bloated telemetry bills, just the runtime data your coding agent needs.
1
1
Jun 10
Wouldn’t it be nice to never have to worry about this again? This is the exact type of problem we built the debugging agent to solve. 👀
Jun 10
Who wants to review this PR? 👇😅
PR reviews were already a known weak point in software development before AI coding agents arrived.
They just made it impossible to ignore.
1
7
Jun 10
Yes, there's a lot going on under the hood. No, you don't have to care about any of it.
One copy/paste in your terminal and Multiplayer handles the rest: data gathering, triage, deduplication, coding agent prompting, PR creation.
You just review and merge.
2
Jun 9
AI agents generate code that breaks in prod. Use Multiplayer with your favorite coding agent to fix application bugs automatically with full-stack, unsampled runtime data.
12
Jun 8
Session-based runtime data collection for coding agents.
One copy/paste in your terminal, and you're done.
15
Jun 4
Multiplayer produces fewer, better PRs: local-first, full-stack, deduplicated, un-sampled, … better data for any coding agent (or developer).
1
11
Jun 3
Multiplayer captures the actual runtime context you (and your coding agent) need to understand your system and fix bugs:
• User interactions and clicks
• Session metadata
• Network requests
• Console messages
• Error rate metrics and errors per user (not sampled!)
• Stack traces, spans, and logs (not sampled!)
• Request/response headers and content from deep within your system
9
Jun 1
Watching the debugging agent fix bugs in real-time.
(One copy/paste line in your terminal, and you can too 👀)
25
May 29
One line.
That’s it.
All you need to start saving hours of debugging time.
1
1
40
May 28
Install the Multiplayer debugging agent in your console. Run it locally. No source code access required.
10
May 25
To go from bug identified to bug fixed, agents need runtime data that observability tools weren't designed to provide. This talk explores that 👀 👇
May 25
Minneapolis last week. New York on June 9-10.
I'll be speaking at @DevWeekNYC a talk I've been wanting to give for a while: From Alert to Action: Redesigning Your Observability Stack for Agentic AI.
1
16
Multiplayer retweeted
May 21
I'm attending the Cloud Native Computing Foundation (CNCF) Observability Summit today in 📍Minneapolis, Minnesota.
If anyone is interesting in discussing agentic coding, debugging, or just have a coffee, find me and @BkStephJ1 ☕️
Hot take for a room full of observability practitioners:
Logs, traces, and metrics were designed for a world where humans wrote and reviewed every line of code. That world is gone.
I'm speaking at @CloudNativeFdn's Observability Summit North America in Minneapolis on May 21–22.
1
1
64
May 18
Proud to see our Director of Community and DevRel and on stage at Cloud Native Days Italy 2026.
The cognitive cost of too much choice is something we think about a lot at Multiplayer. It's part of why we built our debugging agent to run locally, right next to your coding agent: less context switching, less decision fatigue, more fixing.
Great talk. 💜
Today I had the privilege of delivering a keynote at Cloud-Native Days Italy 2026 and I'm still processing how much fun it was. 🤩
If you're curious about the research behind the talk, here are the slides with all the sources linked: lnkd.in/dgmq6Ujk
18
May 14
The boundary of 'what AI can do' is moving.
The debugging agent is a useful case study. The first generation of coding agents tried to fit into existing manual debugging workflows, using the same observability data humans relied on. The result was PR slop: fixes generated from sampled, aggregated, and missing data that looked plausible and failed in production.
The next generation is being built differently: session-based, full-stack, pre-correlated runtime data, with issues deduplicated before they ever reach the coding agent.
That's the workflow being redesigned around what machines actually need, and not retrofitted into what humans used to do.
May 14
There's a story economists love to tell about ATMs and bank tellers.
If you're a developer, you've probably heard it cited in relation to AI tools: the technology won't replace you, it will assist you.
1
31
May 13
Partial data frustrates human debuggers. It breaks AI ones.
AI agents need full runtime context (unsampled, correlated, complete) to understand what actually went wrong. Especially in distributed systems, where the failure rarely lives where the symptom shows up.
May 13
Most engineering teams are using AI to write code faster than ever. But they are also shipping bugs with equal speed. Ultimately, the root cause is a data problem.
1
28