How I use LLMs as a staff engineer in 2026
3 hours ago
- The author now relies heavily on AI agents for producing entire PRs in familiar areas, starting every change with an agent request and pushing the PR after a single editing pass.
- Agents are used extensively for bug investigation, successfully diagnosing 80% of issues autonomously, though human expertise remains crucial for narrowing down complex bugs.
- The author still writes PR descriptions by hand to signal human review and avoids using AI for Slack messages, ADRs, or blog posts, but uses AI for feedback on drafts.
- Testing and setup tasks are increasingly delegated to agents, including generating test scripts, writing unit tests, and handling local configuration issues.
- The key skill is balancing AI utilization: underuse involves not delegating enough simple tasks, while overuse involves trusting AI with communications or sweeping changes needing careful review.
- Current agents are much more capable than a year ago, moving faster and recovering from mistakes autonomously, changing the author's workflow from line-editing to end-only editing passes.