While I can detect that perhaps you don’t feel like this is a useful feature, this is absolutely a legitimate and useful feature. I use it literally every day with Linear. With Linear you can make a ticket in Slack by clicking the … and selecting “make linear ticket”, which gens out a ticket that summarizes the title using AI and pulls in the conversation that you genned it out from, including future updates. The ai autocomplete/title suggestion, while wrong about 25% of the time, removes a huge mental burden around building tickets. If it’s wrong, I just erase the sentence and type my own summary, which takes about 2 extra seconds. But even the wrong summary usually offers good enough context to be able to write the correct one faster.

As an Ops/SRE guy who deals with constant interrupts being able to quickly spawn a ticket and have it pick up the slack conversation saves me literal hours of rote ticketing bullshit every week.

Imo thinking about the title actually helps you to get a clearer view of the problem

What about the dozens of people on the team that don't/won't do that? It's not just engineer/technician who write bug.

Thank you for your validation. Indeed, we have removed the title from the standard issue creation process. We are also actively working to improve it.

I’ll also add, not shilling for you, but only because I think it is valuable boots on the ground information: The product owners in our org don’t ever use this feature. The only people that use this Linear feature are engineers like myself who are more interested in doing work than spending all day writing about work in tickets.

Gotcha thank you :+1

Also since you are thinking in this space, you are probably interested in WHY it’s wrong 25% of the time. It’s because the way slack discussions about issues go is heterogeneous in our org. If you are lucky someone was diligent and made it into thread, at which point the AI is quite good at its job. But often (myself included, because sometimes you’re just lazy and sometimes in an incident things don’t necessarily happen in the cleanest way) no threads are created and you need to gen a ticket off a single sentence. Which if you feed as part of a RAG-like prompt is not going to be very useful in a lot of cases.

Unfortunately there’s no clean obvious way to “guess” what the context is under those conditions, but maybe someone can be clever with heuristics to try to do that where they perhaps feed the last X amount of tokens in from slack and do a Langchain-like approach where first the context is summarized in the initial call and then the title is generated from that summary

Thanks a ton. That's a lot of detailing on the use-case. We will definitely put these thoughts as we improvise.

Bro, work in tickets is half the solution to a problem!

Our goal is to inspire people to provide comprehensive descriptions of the issues they report, without the worry of making them concise. From our experience, while it's easy to describe things, articulating them can be challenging. Hence, we encourage thorough descriptions first and then we'll help refine them into a clear, well-contextualized title.

It will be interesting to see how well this works.

Often people just provide the title of tickets (“It does not work!!”) and don’t even care about proper descriptions.

Your goal was to rip off a good design. Copy/Paste.