(Inspired by Martin Fowler)

Some pieces from https://www.thoughtworks.com/en-de/radar (Volume 34 - April 2026)

Measuring collaboration quality with coding agents

Metrics such as first-pass acceptance rate, iteration cycles per task, post-merge rework, failed builds and review burden provide more meaningful signals than speed alone. Teams using Claude Code can use the /insights command to generate reports reflecting on successes and challenges from agent sessions. Our teams have also experimented with tracking first-pass acceptance of a customized /review command.

Agent instruction bloat

Context files such as AGENTS.md and CLAUDE.md tend to accumulate over time as teams add codebase overviews, architectural explanations, conventions and rules. While each addition is useful in isolation, this often leads to agent instruction bloat. Instructions become long and sometimes conflict with each other. Models tend to attend less to content buried in the middle of long contexts, so guidance deep in a long conversation history can be missed. As instructions grow, the likelihood increases that important rules are ignored.

AI-accelerated shadow IT

AI continues to lower the barriers for noncoders to build complex systems. While this enables experimentation and early validation of requirements, it also introduces the risk of AI-accelerated shadow IT. In addition to no-code workflow platforms integrating AI APIs (e.g., OpenAI or Anthropic), more agentic tools are becoming available to noncoders, such as Claude Cowork. When the spreadsheet that quietly runs the business evolves into customized agentic workflows that lack governance, it introduces significant security risks and a proliferation of competing solutions to similar problems. Distinguishing between disposable, one-off workflows and critical processes that require durable, production-ready implementation is key to balancing experimentation with control. Organizations should prioritize governance as part of their AI adoption strategy by facilitating experimentation within controlled environments.

Codebase cognitive debt

Codebase cognitive debt is the growing gap between a system’s implementation and a team’s shared understanding of how and why it works. As AI increases change velocity, especially with multiple contributors or Coding Agent Swarms, teams can lose track of design intent and hidden coupling. This, combined with rising technical debt, creates a reinforcing loop that makes systems progressively harder to reason about. Weaker system understanding also reduces developers’ ability to guide AI effectively, making it harder to anticipate edge cases and steer agents away from architectural pitfalls. Left unmanaged, teams reach a tipping point where small changes trigger unexpected failures, fixes introduce regressions and cleanup efforts increase risk instead of reducing it.