The Joining Tax: A Year of Governing Claude Code
In January 2026 Anthropic published a retrospective on multi-agent systems that described what I'd been running for a year, and described it as the mistake. Their wording, near enough: teams build elaborate multi-agent systems with separate agents for planning, execution, review and iteration, only to discover that they suffered from lost context at each handoff and spent more tokens coordinating than executing. This is the same company whose earlier post reported a multi-agent setup beating a single agent by 90%, so the retrospective reads as a walk-back. And an April 2026 preprint goes further still: hold the reasoning-token budget constant and a single agent matches or beats the multi-agent setups, and it argues the reported multi-agent wins were mostly extra computation nobody was counting.
I have a lead, a business analyst, an architect, a developer, QA, two reviewers who argue opposite positions, and a doc updater. They've been running against...
Copyright of this story solely belongs to hackernoon.com. To see the full text click HERE
