At LinkedIn's scale, relying solely on human reviewers or simply putting an off-the-shelf AI reviewer in front of GitHub is not an effective way to manage PRs. To address this, LinkedIn engineers built a multi-agent AI code review platform that understands the organization’s coding context, treats code review as prod…
At LinkedIn's scale, relying solely on human reviewers or simply putting an off-the-shelf AI reviewer in front of GitHub is not an effective way to manage PRs. To address this, LinkedIn engineers built a multi-agent AI code review platform that understands the organization’s coding context, treats code review as prod…
In context
- Topic: Desarrollo con IA — Copilotos y agentes en el ciclo de desarrollo de software.
- Source: InfoQ — IA y datos
- Published: 22/08/2026
Continue reading at the original source →
Excerpt published automatically by the site radar. The full text belongs to its publisher and is linked above.
Why it matters
AI applied to development moved the bottleneck. Writing code stopped being the slow part; now the slow part is reviewing, understanding and maintaining what was written. Any team adopting these tools without adjusting review gets faster in week one and slower by month three.
I look at it from operations, not from the demo. The question is not whether the assistant writes a correct function, but whether the team can maintain what it produced six months later, with different people, without the original context. That is the real test and it almost never appears in the announcements.
What usually goes wrong
Where I see most stumbles is in the conversation with people. The tool gets announced as a productivity improvement without saying what is expected of each person, and everyone fills the silence with their own fear. Adoption does not stall on the technology, it stalls on what was left unsaid.
What to watch
- The effect on people newly joining the team, which is where judgement erodes fastest.
- Whether total time to production drops or only writing time, which is not the same thing.
- What happens to code review: if the assistant produces more, somebody has to read more.
How I read this entry
If I were rolling this out, I would do it with written rules: what can be generated, what always gets human eyes, and what is off limits to an assistant — typically anything handling money, identity or personal data. Rules give freedom, they do not remove it.
This entry is an excerpt from the original source, selected by the site radar. The commentary above is the site's own and does not belong to the cited publisher.
Living through this in your own team?
Open the chat and tell me how you're handling it. I'm interested in comparing notes.
