# The Conversational SDLC | Joseph Bironas | Medium

<https://josebiro.medium.com/the-conversational-sdlc-a2bd95a9ed34>

- Host: [josebiro.medium.com](https://links.thingelstad.xyz/hosts/josebiro.medium.com/)
- Saved: June 19, 2025 (2025-06-19T17:12:48Z)
- Record: https://links.thingelstad.xyz/links/68941166ba38/
- JSON: https://links.thingelstad.xyz/links/68941166ba38.json

## What Jamie wrote

As we bring LLMs into the product development process it isn't just about the engineers doing things differently. All that context in a discovery session is critical for the LLM. How we write and think about features will need to evolve. This article highlights a first look at what that may look like. 

> The magic isn't the gates; it's the _friction they re-introduce_ in just the right spots, and the context references they produce along the way.
> 
> - **Less ambiguity up front.** Writing the prompt contract feels bureaucratic until the first regen loop flies by unnoticed, and the model starts giving subtle clues that it no longer understands what needs to be done because I forgot to specify the prompt context correctly in the moment.
> - **Interruption-aware iterations.**Cognitive-science studies and developer surveys agree that fragmentation disrupts flow more than interruptions themselves ([blog.stackblitz.com](https://blog.stackblitz.com/posts/flow-state/),[ kjl.name](https://kjl.name/papers/icse24.pdf)). Capping loops keeps the brain in one piece.
> - **Reviewable reasoning.** A reviewer who can read the model's chain-of-thought is far less likely to rubber-stamp copy-paste patterns.
> - **Post-mortem super-powers.** Every production incident becomes replayable: prompts, responses, timestamps. Blameless _and_ searchable.

The big thing I’m seeing repeatedly is including the prompt assets and other inputs into the repository right alongside the code itself. This is probably a very good thing in general.

## Facts

- Kind: [Page](https://links.thingelstad.xyz/kinds/page/)

## Appears in

- [WT324: Weekly Thing 324 / Agents, Shortcuts, Joy](https://weekly.thingelstad.com/archive/324/), Notable

## Saved the same week

- [Building Effective AI Agents Anthropic](https://links.thingelstad.xyz/links/560cdb7361bd/) (anthropic.com, June 19, 2025)
- [Websites Are Tracking You Via Browser Fingerprinting | Texas A&M University Engineering](https://links.thingelstad.xyz/links/b777e4d3226b/) (engineering.tamu.edu, June 19, 2025)
- [Yancey Strickler: Forget hustle culture. Behold the Artist Corporation | TED Talk](https://links.thingelstad.xyz/links/981c54ceb3fc/) (ted.com, June 19, 2025)
- [Coding agents require skilled operators](https://links.thingelstad.xyz/links/8b405227b581/) (simonwillison.net, June 19, 2025)
- [CardStock.run](https://links.thingelstad.xyz/links/a1f8ad37a45f/) (cardstock.run, June 19, 2025)

## Elsewhere

- Wayback Machine: https://web.archive.org/web/*/https://josebiro.medium.com/the-conversational-sdlc-a2bd95a9ed34