---
title: "Discussion on \"AI-Driven Development Is a Diagnostic for Your Organization\" | Hashnode"
description: "Discussion on \"AI-Driven Development Is a Diagnostic for Your Organization\". AI made producing faster. In three accounts, the constraint moved to work AI cannot do alone: the objective, the context, and the capacity to verify."
url: "https://hashnode.com/posts/ai-driven-development-is-a-diagnostic-for-your-organization/6ad8710cc077907c524a2e52"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [AI-Driven Development Is a Diagnostic for Your Organization](https://blog.simukappu.com/ai-driven-development-is-a-diagnostic-for-your-organization?utm_source=hashnode&utm_medium=feed)

AI made producing faster. In three accounts, the constraint moved to work AI cannot do alone: the objective, the context, and the capacity to verify.

Oct 21 · 16 min read · blog.simukappu.com  
Updated 2d ago  
Read the article

-   [#ai-driven-development](https://hashnode.com/tag/ai-driven-development)
-   [#developer-experience](https://hashnode.com/tag/developer-experience)
-   [#engineering-management](https://hashnode.com/tag/engineering-management)
-   [#devops](https://hashnode.com/tag/devops)
-   [#software-development](https://hashnode.com/tag/software-development)

## Written by

[Shota Yamazaki](https://hashnode.com/@simukappu)

@simukappu · Kanagawa, Japan

  
[View profile](https://hashnode.com/@simukappu)

Writing about architecture in production, from distributed systems to agentic AI, and the organizations that ship them.

Solutions architecture leader working across cloud architecture, distributed systems, data platforms, and AI. As much in the people and processes as in the technology. OSS author &amp; maintainer. I write about the design decisions behind large-scale production systems. Currently at AWS. All opinions are my own.

## Responses 6

Markdown supported · ⌘↵ to post

[Ascendra Ventures](https://hashnode.com/@ascendra-ventures)

[Oct 22](https://hashnode.com/posts/ai-driven-development-is-a-diagnostic-for-your-organization/6ad8710cc077907c524a2e52/comment/6ad976bb8dc099e1457aaab0)

Treating the speedup as a diagnostic is a useful frame, because it turns a tooling debate into a question about the organization. The three placements line up neatly: the objective before the work, context during it, verification after it.

The ASKUL part stood out most. A team told to restore optimizes differently from a team told to go past where it was, and no stage in AI-DLC can produce that sentence for you. Your suggestion to have two people write the objective separately and compare is cheap and would catch most cases where a team only thinks it agrees.

We see the same pattern at a smaller scale on client builds. When the problem and its finish line are written on a page before anything is generated, verification has something to check against, and the Spotify question about change volume becomes measurable. Without that page, review time goes into working out what was intended. Will the next part look at how LY assigns owners to the refresh triggers?

[Shota Yamazaki](https://hashnode.com/@simukappu)

[Oct 22](https://hashnode.com/posts/ai-driven-development-is-a-diagnostic-for-your-organization/6ad8710cc077907c524a2e52/comment/6ad976bb8dc099e1457aaab0#reply-6ad9bd58b3940b516ff6cfdc)

Thank you for reading it so closely. One clarification on your question. The owner and refresh trigger fields are a general recommendation for teams, not something from LY's talk, so I can't speak for how LY assigns owners. The next article I plan for this series goes further into verification. Your point about writing down the problem and its finish line before anything is generated is close to where it starts, because verification needs something written to check against.

[Abhinav Sharma](https://hashnode.com/@abhinavs1920)

[Oct 21](https://hashnode.com/posts/ai-driven-development-is-a-diagnostic-for-your-organization/6ad8710cc077907c524a2e52/comment/6ad92916efa80f9962d50f8d)

Producing got faster but verifying did not, and the Spotify merge numbers make that concrete. Writing the objective and the price accepted for it before the agent generates anything is a cheap control worth adopting.

[Shota Yamazaki](https://hashnode.com/@simukappu)

[Oct 22](https://hashnode.com/posts/ai-driven-development-is-a-diagnostic-for-your-organization/6ad8710cc077907c524a2e52/comment/6ad92916efa80f9962d50f8d#reply-6ad9bd896ab9d811800bb6af)

Thank you. It is cheap, and it works best when two people write it separately and compare.

[Parsa Mohammadi](https://hashnode.com/@tomosu)

[Oct 21](https://hashnode.com/posts/ai-driven-development-is-a-diagnostic-for-your-organization/6ad8710cc077907c524a2e52/comment/6ad8e3ecbe72bf71319b757a)

Spotify’s two incident questions are the best part. the first one is harder than it looks though, you need to know which change caused the incident, and most teams figure that out by hand. we looked at a Spotify outage from that angle at Tomosu, whether the risk was visible before it shipped. the PR looked reasonable on its own, the risk only showed up in how it interacted with the rest of production. that’s the gap we’re working on [https://tomosu.ai](https://tomosu.ai/)

[Shota Yamazaki](https://hashnode.com/@simukappu)

[Oct 22](https://hashnode.com/posts/ai-driven-development-is-a-diagnostic-for-your-organization/6ad8710cc077907c524a2e52/comment/6ad8e3ecbe72bf71319b757a#reply-6ad9bdbe6ab9d811800bb7b1)

Agreed, the first question is the harder one, because it needs the change behind the incident. The second is easier to start with. A team can ask whether the volume of change put pressure on review, testing, rollout, or observability without pinning the incident on one change.
