# Running projects for AI features

DevFeed: [Running projects for AI features](<https://devfeed.tech/articles/running-projects-for-ai-features-11980.md>)

Original publisher: [Read original article](<https://incident.io/blog/running-projects-for-ai-features>)

Author: Aaron Sheah

Published: 2024-01-23T13:00:00Z

Content type: article

Language: en

Sources: [The incident.io Blog](<https://devfeed.tech/sources/the-incident-io-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [data](<https://devfeed.tech/topics/data.md>), [dataset](<https://devfeed.tech/topics/dataset.md>), [incident](<https://devfeed.tech/topics/incident.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [article](<https://devfeed.tech/tags/article.md>), [blog](<https://devfeed.tech/tags/blog.md>), [building](<https://devfeed.tech/tags/building.md>), [data](<https://devfeed.tech/tags/data.md>), [dogfooding](<https://devfeed.tech/tags/dogfooding.md>), [experimental](<https://devfeed.tech/tags/experimental.md>), [incident](<https://devfeed.tech/tags/incident.md>), [incident-channel](<https://devfeed.tech/tags/incident-channel.md>), [incident-management](<https://devfeed.tech/tags/incident-management.md>), [incident-response](<https://devfeed.tech/tags/incident-response.md>), [llms](<https://devfeed.tech/tags/llms.md>), [openai](<https://devfeed.tech/tags/openai.md>), [outage](<https://devfeed.tech/tags/outage.md>), [post-mortem](<https://devfeed.tech/tags/post-mortem.md>), [production](<https://devfeed.tech/tags/production.md>), [slack-incident](<https://devfeed.tech/tags/slack-incident.md>), [technical](<https://devfeed.tech/tags/technical.md>)

## AI overview

This article explains how AI feature projects differ from typical software projects. It recommends an experimental process: validate LLM capabilities with proof-of-concepts and historical data, iterate quickly, delay UI work, and then dogfood an early production MVP to gather feedback before investing in the full feature.

## Source excerpt

In this article, Aaron the Technical Lead for the Post-incident team highlights the differences of running projects for AI powered features