Running multiple Claude Code sessions in parallel allows for independent contexts and memory, enabling users to work on different projects without interference. Boris Cherny typically runs five sessions at once, using numbered tabs and system notifications to stay organized.
Scrum has a bad reputation in some organizations. In many cases, this is because teams did something they called Scrum, it didn't work, and Scrum took the blame. To counter this, when working with organizations, we like to define a small set of rules a team must follow if they want to say they're doing Scrum. Enforcing this policy helps prevent Scrum from being blamed for Scrum-like failures.
AI made producing software cheap, but understanding it is still expensive. The Manifesto optimizes for the former. This addendum shifts the emphasis toward the latter. Four updated values, three refined principles, with reasoning for each.
"I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become available over the last ~year and a failure to claim the boost feels decidedly like skill issue."
The real cost of poor observability isn't just downtime; it's lost trust, wasted engineering hours, and the strain of constant firefighting. But most teams are still working across fragmented monitoring tools, juggling endless alerts, dashboards, and escalation systems that barely talk to one another, which acts like chaos disguised as control. The result is alert storms without context, slow incident response times, and engineers burned out from reacting instead of improving.
Software engineering didn't adopt AI agents faster because engineers are more adventurous, or the use case was better. They adopted them more quickly because they already had Git. Long before AI arrived, software development had normalized version control, branching, structured approvals, reproducibility, and diff-based accountability. These weren't conveniences. They were the infrastructure that made collaboration possible. When AI agents appeared, they fit naturally into a discipline that already knew how to absorb change without losing control.
We build production platforms with AI every day, and we work with teams doing the same with their own stack -Cursor, Claude Code, Copilot. The difference shows up fast. By day two, some codebases are already harder to change than they were yesterday. Others keep getting easier. The difference is never the model. It's what the code lands in. The teams we work with that hit a wall? It's always the same story.
