Haskell for all: Beyond agentic coding
haskellforall.com
February 8, 2026
11 min read
Summary
Agentic coding tools often produce unsatisfactory results, leading to decreased productivity and user comfort with the codebase. Interview candidates using these tools tend to perform worse compared to those who do not.
Key Takeaways
- Agentic coding does not improve productivity and can negatively affect user comfort and familiarity with codebases.
- Research indicates that users of agentic coding tools perform no better and sometimes worse than those who do not use them, particularly in terms of fixed outcomes.
- Effective AI-assisted coding tools should prioritize maintaining a developer's flow state and minimize interruptions.
- Calm technology principles, such as minimizing attention demands and enhancing user calm, can improve the design of coding tools.
Related Articles
Coding assistants are solving the wrong problem
Feb 3, 2026
Why "just prompt better" doesn't work
Feb 10, 2026
Stop Generating, Start Thinking
Feb 8, 2026
Building for an audience of one: starting and finishing side projects with AI
Feb 17, 2026
AI makes the easy part easier and the hard part harder
Feb 8, 2026
Source
haskellforall.com
Published
February 8, 2026
Reading Time
11 minutes
Relevance Score
61/100
Why It Matters
This page is optimized for focused reading: quick context up top, a clean summary block, and a direct path to the original source when you want the full story.