Static analysis
AssessTechniques
Automated code analysis that checks source code for security issues, often using predefined rules.
Why it's here
Placed in Assess: 5 article(s) of evidence from 4 source(s), led by security coverage, with 1 in the last 30 days. Confidence 70%.
Evidence (5)
- 5The New Stack·8/9/2026researchCoding agents can be evaluated by their work
The article argues that coding agents are difficult, but not impossible, to evaluate, and that they should be assessed as whole systems rather than as standalone models. It proposes judging them by executable outcomes, change quality, trajectory, human intervention, cost, and production impact instead of relying only on pass/fail test scores.
- 5Martin Fowler·5/27/2026securityFowler on agentic coding, code cleanup, and UK public repo closures
Martin Fowler summarizes several recent software-development posts and talks, including a discussion with Kent Beck about LLM-augmented programming and the role of junior developers. He also highlights an account of restructuring a legacy Laravel and React codebase with tests, static analysis, and a more agent-driven workflow, plus criticism of the UK NHS closing open-source repositories due to LLM-related security concerns.
- 6Martin Fowler·4/29/2026framework_updateAI Coding Shifts Toward Harness Engineering and Verification
Martin Fowler highlights updated guidance from Chris Parsons and related work on harness engineering, emphasizing small changes, strong guardrails, and automated verification before code is shipped. The discussion also points to tools and techniques such as Claude Code, Codex CLI, static analysis, and tests as central to agentic software development.
- 5OpenAI Blog·3/16/2026securityWhy Codex Security Skips Traditional SAST Reports
OpenAI explains that Codex Security does not depend on conventional static application security testing reports. Instead, it uses AI-driven constraint reasoning and validation to identify real vulnerabilities while reducing false positives.
- 8Anthropic News·2/20/2026securityAnthropic launches Claude Code Security preview for defenders
Anthropic introduced Claude Code Security, a limited research preview built into Claude Code on the web that scans codebases for security vulnerabilities and suggests patches for human review. The company says it is designed to help defenders find subtle issues that rule-based tools often miss, with findings verified, scored by severity, and requiring human approval before fixes are applied.