We're growing very rapidly. So honestly, standup meetings now became the most important meeting and "definitely not a standup". A lot of product/customer things are decided during the call, engineers, PMs, and everyone really demos what they've worked on and questions are asked and answered during that call.
Code reviews are gone. We review the coding session itself instead. Everyone shares their coding sessions with whoever is going to review and the reviewer engages with the CLI to ask questions.
I'm 100% fully in the cloud and strongly recommend it to others. I'm building (AQ.dev) so I'm obviously biased, but almost every single one of our customers ends up bringing their own VMs to the platform instead of using the Managed solution. There's definitely a pull in that direction in my opinion.
We still create a ton of end-to-end tests and run them a lot. What changed for us is the review process. While our whole team uses agents to do reviews, we also ask other team members to review the coding session itself rather than the diff. That team member can ask the coding session questions about the architecture decisions, scalability, edge cases, ..etc.
Disclosure: I'm building AQ (aq.dev), which is partly why I'm deep in this. We wrote up the session-review practice here: https://aq.dev/guides/how-to-review-an-ai-coding-session/. The practice works with any agents too, nothing tool-specific about it.
Microsoft just shipped something literally called the Agent Framework Harness, plus a "build your own agent harness" tutorial series. The harness is officially a product category now.
Their harness is the loop around the model: tools, memory, approvals, the plan/execute cycle. Necessary. And still single-player.
The part no SDK ships: where that loop runs and who can see it. A coding agent session your whole team can open, watch, and steer is a different layer entirely.
Disclosure: That is the layer we build at AQ (aq.dev): the multiplayer coding harness. Fun watching the vocabulary catch up.
I'm not against open source. However, if I were to guess, I think less than 1% of people actually review, let alone modify the open source projects they use. I don't really buy this argument.
I think we're seeing a new modality of openness now with open weights, or being able to modify agents with md files, skills, and so forth.
Before LLMs the barrier to modifying software was much higher - in skill and time investment required.
Now we're getting to the point where any user can say "Claude, I don't like that. Please fix" and have it fixed. Configurability/extensibility can work in some cases, but having source code makes it much more powerful.
The hardest problem in multiplayer agents, at least for us, has not been the agent loop. It is scoping and QM's per-person scopes plus shared rooms is a sane answer for a company-wide assistant.
I build in the adjacent lane, AQ (aq.dev), a multiplayer coding harness where teams run Claude Code and Codex together), so seeing YC ship "a multiplayer agent harness for work" is validating and a little surreal.
It hurts my eyes looking at this haha .. but that's different than the actual harness as we know it tho! Given their ecosystem, they'll always control the CI/CD part of it, which is fine. It's just painful to use XCode to get anything done anymore.
Agreed. I had to solve this at the harness layer myself. It just makes more sense to me this way. We basically created hooks around these operations and you can configure what happens at these calls.
Disclosure: I'm building AQ (aq.dev) a multiplayer coding harness.
We're growing very rapidly. So honestly, standup meetings now became the most important meeting and "definitely not a standup". A lot of product/customer things are decided during the call, engineers, PMs, and everyone really demos what they've worked on and questions are asked and answered during that call.
Code reviews are gone. We review the coding session itself instead. Everyone shares their coding sessions with whoever is going to review and the reviewer engages with the CLI to ask questions.
Disclosure: I'm building AQ (aq.dev) around exactly this workflow, so I'm biased. Longer write-up of the review approach: https://aq.dev/guides/reviewing-pull-requests-from-ai-agents...