Skip to content
AI Radar by Wagner Solution
CS
Menu
worth noting AI agents

Simon Willison: the key skill with coding agents is giving instructions and verifying results, not reading every line

only one source so far

Simon Willison argues that a key skill when working with coding agents is being able to give them clear instructions and then verify the correctness of the changes made – and that reading every line of code is not the most effective way to do this.

In a brief comment on his blog, Simon Willison describes what he considers a key skill for working productively with coding agents: the ability to confidently instruct them on how to make changes and then confidently verify that those changes were made correctly.

According to Willison, this sometimes means going through every line of code written, but there are other ways to achieve the same goal of verifying quality. He emphasizes that reviewing every single line of code has never been the most effective way to verify the correctness of a software change.

The text is a short note with no further details on specific alternative verification methods. You can find details in the source article.

What changed

Why it matters

For developers who increasingly rely on coding agents, this represents a shift in which skills are valuable in practice – instead of reviewing code in detail, the key is being able to define a task so that the result can be reliably verified, and having effective ways to check the quality of the output.

Two audiences, two different impacts

What this means

01

For individuals

Developers working with coding agents should develop two specific skills – giving the agent clear instructions and verifying that the changes made match the task – while recognizing that reading every line of code is neither the only nor the most effective way to verify this.

What to do When working with coding agents, emphasize clear instructions and look for effective ways to verify the result, beyond simply reading every line of code.
More practical updates →
02

For a business

For teams deploying coding agents, this suggests that the code quality review process should not be limited to traditional line-by-line review, but should also include other ways of verifying results.

Development
What to decide Assess whether current code review practices for code generated by AI agents include forms of verification other than reading every line.
More business impacts →
agentic engineering code review giving instructions coding agents LLM verification

Check the original

Event sources

only one source so far · 1 publisher, 1 independent. We count feeds from the same owner only once.

1
Simon Willison — AI tag (leading independent LLM commentator) community signal · first detected More than just code review