---
title: "How I use LLMs as a staff engineer in 2026"
url: https://daily.dev/posts/how-i-use-llms-as-a-staff-engineer-in-2026-yhtlilt9r
source_url: https://seangoedecke.com/how-i-use-llms-in-2026
type: article
source: "sean goedecke"
published: 2026-05-16T21:46:23.145Z
updated: 2026-05-16T21:46:46.107Z
tags: ["github", "llm", "ai-agents", "ai-coding"]
reading_time: 10
upvotes: 98
comments: 7
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# How I use LLMs as a staff engineer in 2026

**[sean goedecke](https://daily.dev/sources/seangoedecke)** · 10 min read · 98 upvotes · 7 comments

## Summary

A staff engineer shares how their LLM usage has evolved over the past 15 months. The biggest shift: AI agents are now good enough to draft entire PRs, investigate most bugs autonomously, handle testing, and assist with local setup tasks. The author now starts every code change by asking an agent to solve it first, then does a single editing pass. They still write all public communications (PR descriptions, ADRs, Slack messages) by hand and carefully review all agent-produced code. The key insight is that the core skill is finding the right balance — delegating as much as possible to agents without over-trusting them on things requiring human judgment or communication.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://seangoedecke.com/how-i-use-llms-in-2026>

## Community discussion

Top comments from developers on daily.dev.

**@randy** · 19 upvotes

> I’m a senior engineer and my usage in 2025 was much like Sean’s. And similarly, my usage has changed in 2026. Part of the reason for that is that the company I work for has finally gotten behind the idea and started to pay for a subscription.
>
>
> Another reason is, as Sean points out, LLMs are getting pretty good at stuff! You can probably find comments from me here saying I’d never let an LLM write my tests or write my prod code, etc. Well, that’s changed.
>
>
> I’m still porting legacy functionality and I can saves _days_, if not an entire week, by creating a plan with, and having the work done...

**@johnlowiework** · 5 upvotes

> We might be reviewing "AI teammates" more often than human ones.

**@hardik15** · 5 upvotes

> The last last line is gold in this summary. Finding the right balance!

**@ian67** · 0 upvotes

> Using agents to review PRs, whether human or llm generated, can often surface real issues. Early GitHub reviews were mostly false positives but CLI reviews are pretty good lately, especially if given focus areas and tunes to studio conventions.
>
> Truly a new world.

**@asmui\_ahmad** · 0 upvotes

> uh, oh so AI can replace the dev rn

## Similar posts on daily.dev

- [How I write software with LLMs](https://daily.dev/posts/how-i-write-software-with-llms-jekylkhup) · Hacker News · 2 upvotes · 0 comments

---

Tags: [#github](https://daily.dev/tags/github), [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#ai-coding](https://daily.dev/tags/ai-coding)

[View this post on daily.dev](https://daily.dev/posts/how-i-use-llms-as-a-staff-engineer-in-2026-yhtlilt9r)