(Inspired by Martin Fowler)

Some pieces from Tech 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.

Feedback sensors for coding agents

To make coding agents more effective and reduce the load on human reviewers, teams need feedback loops that agents can directly access. These feedback sensors for coding agents act as a form of feedback backpressure, increasing trust in generated results. Developers have long relied on deterministic quality gates such as compilers, linters, structural tests and test suites; here, they’re wired into agentic workflows so that failures trigger timely self-correction. These checks reduce routine steering work for the human in the loop. Teams can implement them in different ways, such as introducing a reviewer agent responsible for running checks and triggering corrections, or by exposing the checks through a companion process that runs in parallel that agents can query efficiently. Coding agents also make it cheaper to build custom linters and structural tests, further strengthening these feedback loops. Whenever possible, these sensors should run during the coding session and report clean results before a commit is made, rather than relying on post-commit checks.

Complacency with AI-generated code

As AI coding assistants and agents gain traction, so does the body of data and research highlighting concerns about complacency with AI-generated code. While there’s ample evidence these tools can accelerate development — especially for prototyping and greenfield projects — studies show that code quality can decline over time. GitClear’s 2024 research found that duplicate code and code churn have risen more than expected, while refactoring activity in commit histories has dropped. Reflecting a similar trend, Microsoft research on knowledge workers shows that AI-driven confidence often comes at the expense of critical thinking — a pattern we’ve observed as complacency sets in with prolonged use of coding assistants. The rise of coding agents further amplifies these risks, since AI now generates larger change sets that are harder to review. As with any system, speeding up one part of the workflow increases pressure on the others. Our teams are finding that using AI effectively in production requires renewed focus on code quality. We recommend reinforcing established practices such as TDD and static analysis, and embedding them directly into coding workflows, for example through curated shared instructions for software teams.