# Coding AI without deterministic outcomes

DevFeed: [Coding AI without deterministic outcomes](<https://devfeed.tech/articles/coding-ai-without-deterministic-outcomes-60985.md>)

Original publisher: [Read original article](<https://www.aha.io/engineering/articles/coding-ai-without-deterministic-outcomes>)

Published: 2026-09-28T00:00:00Z

Content type: opinion

Language: en

Sources: [Aha! Engineering Blog](<https://devfeed.tech/sources/aha-engineering-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [coding assistant](<https://devfeed.tech/topics/coding-assistant.md>)

Tags: [coding-ai](<https://devfeed.tech/tags/coding-ai.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [llm](<https://devfeed.tech/tags/llm.md>)

## AI overview

The author contrasts the satisfaction of using AI to complete software work with the uncertainty of building features that use LLMs. Prompting such features can be hard to debug because natural-language instructions do not provide a deterministic way to trace an output back to its input.

## Source excerpt

I recently had a conversation with an engineer on our team about working with AI. He was frustrated with some of the work he had been doing on AI features, and a lot of what he was saying resonated with me. He was putting into words things that I ha