# We used GPT-4 during a hackathon--here's what we learned

DevFeed: [We used GPT-4 during a hackathon--here's what we learned](<https://devfeed.tech/articles/we-used-gpt-4-during-a-hackathon-here-s-what-we-learned-11792.md>)

Original publisher: [Read original article](<https://incident.io/blog/gpt4-hackathon>)

Author: Rory Bain

Published: 2023-07-25T19:47:01Z

Content type: opinion

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>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [incident](<https://devfeed.tech/topics/incident.md>), [Prompt Engineering](<https://devfeed.tech/topics/prompt-engineering.md>), [Command-line interface](<https://devfeed.tech/topics/cli.md>), [Slack](<https://devfeed.tech/topics/slack.md>), [For the Love of Code](<https://devfeed.tech/topics/for-the-love-of-code.md>), [dashboards](<https://devfeed.tech/topics/dashboards.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [cli](<https://devfeed.tech/tags/cli.md>), [code](<https://devfeed.tech/tags/code.md>), [command-line](<https://devfeed.tech/tags/command-line.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [hackathon](<https://devfeed.tech/tags/hackathon.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>), [openai](<https://devfeed.tech/tags/openai.md>), [outage](<https://devfeed.tech/tags/outage.md>), [post-mortem](<https://devfeed.tech/tags/post-mortem.md>), [slack](<https://devfeed.tech/tags/slack.md>), [slack-incident](<https://devfeed.tech/tags/slack-incident.md>), [technical](<https://devfeed.tech/tags/technical.md>)

## AI overview

This retrospective describes a two-day hackathon in which the team built 12 demos and explored integrating OpenAI's GPT-4 into its product. Existing work generated incident summaries from incident updates and exposed prompt responses through a CLI. During the hackathon, the team updated that code, experimented with prompts, and explored more detailed, user-specific incident summaries using Slack channel context.

## Source excerpt

We learned a lot about using OpenAI and which things to keep an eye on to decide when it's worth revisiting.