[Jach]

Are you able to describe any of those internal tools in more detail? How important are they on average? (For example, at a prior job I spent a bit of time creating a slackbot command "/wtf acronym" which would query our company's giant glossary of acronyms and return the definition. It wasn't very popular (read: not very useful/important) but it saved myself some time at least looking things up (saving more time than it took to create I'm sure). I'd expect modern LLMs to be able to recreate it within a few minutes as a one-shot task.)

[shimman]

It's almost always a CRUD app or dashboard that no one uses while being extremely overkill for their use case.

edit: LOL called it, a bunch of useless garbage that no one really cares about but used to justify corporate jobs programs.

[Daishiman]

If it's useless that's a you problem. I've been building CRUDs that would have taken me a month to get perfectly right in the span of 4-5 days which save an enormous number of human tech support hours.

[shimman]

Sorry man but the software world is littered with CRUD apps, they are called CRUD apps for a reason. They're basically the mass assembled stamped L-bracket of the software world. CRUD apps have also had template generators for like 30 years now too.

Still useless in the sense that if you died tomorrow and your app was forgotten in a week the world will still carry on. As it should. Utterly useless in pushing humanity forward but completely competent at creating busy work that does not matter (much like 99% of CRUD apps and dashboards).

But sure yeah, the dashboard for your SMB is amazing.

[Daishiman]

The software industry's value proposition for the vast majority of businesses running the world lies in CRUD apps that properly capture business requirements. That's infinitely more relevant in insurance, pharma, banking and logistics than any technological breakthrough of the past 25 years.

Your rant just shows you don't understand why people pay for software.

[girvo]

Ah but it looks cool and I can put it on my stack ranking perf eval

[scottyah]

I have one that serves a few functions- Tracks certificates and licenses (you can export certs in any of the majorly requested formats), a dashboard that tells you when licenses and certs are close to expiring, a user count, a notification system for alerts (otherwise it's a mostly buried Teams channel most people miss), a Downtime Tracker that doesn't require people to input easily calculatable fields, a way for teams to reset their service account password and manage permissions, as well as add, remove, switch which project is sponsoring which person, edit points of contact, verify project statuses, and a lot more. It even has some quick charts that pull from our Jira helpdesk queue- charts that people used to run once a week for a meeting are just live now in one place. It also has application statuses and links, and a lot more.

I'd been fighting to make this for two years and kept getting told no. I got claude to make a PoC in a day, then got management support to continue for a couple weeks. It's super beneficial, and targets so many of our pain points that really bog us down.

[CoolThings]

>> a dashboard that tells you when licenses and certs are close to expiring

Or, Excel > Data > Sort > by the Date column. No dashboard needed, no app needed.

[Jach]

A lot of businesses can get by just fine with making it one person's responsibility to maintain a spreadsheet for this. It can be fragile though as the company grows and/or the number of items increases, and you have to make sure it's all still centralized and teams aren't randomly purchasing licenses or subscriptions without telling anyone, it needs to be properly handed off if the person leaves/dies/takes a vacation, backed up if not using a cloud spreadsheet... I've probably seen at least a dozen startups come and go over the years purporting to solve this kind of problem, other businesses integrate it into an existing Salesforce/other deployment... it seems like a fine choice for an internal tool, so long as the tool is running on infrastructure that is no less stable than a spreadsheet on someone's machine.

In the startup world something like "every emailed spreadsheet is a business" used to be a motivating phrase, it must be more rough out there when LLMs can business-ify so many spreadsheet processes (whether it's necessary for the business yet or not). And of course with this sort of tool in particular, more eyes seeing "we're paying $x/mo for this service?" naturally leads to "can't we just use our $y/mo LLM to make our own version?". Not sure I'd want to be in small-time b2b right now.

[jeremyjh]

Or better yet just remember it all, no spreadsheet needed either!

[Daishiman]

Why are you ignoring the fact that grabbing data from heterogeneous sources, combining it and presenting it is generally never a trivial task? This is exactly what LLMs are good for.

[camdenreslink]

If you are using an LLM to actually fetch that data, combine it, and present it to you in an ad hoc way (like you run the same prompt every month or something), I wouldn't trust that at all. It still hallucinates, invents things and takes short cuts too often.

If you are using an LLM to create an application to grab data from heterogeneous sources, combine it and present it, that is much better, but could also basically be the excel spreadsheet they are describing.

[Daishiman]

Your knowledge of LLMs is outdated by at least a year. For the past three months at least my team has been one-shotting complex SQL queries that are as semantically correct as your ability to describe them.

And why do you diminish the skill of good data wrangling as if it weren’t the most valuable skill in the vast majority of computer programming jobs? Your cynicism doesn’t correspond with the current ground truth in LLM usage.

[camdenreslink]

Well, that is still having the LLM write code which is more like my second scenario. I use SOTA LLMs for coding literally every day. I don't think my knowledge is "outdated by at least a year".

[qingcharles]

The ones I can mention.. one that watches a specific web site until an offer that is listed expires and then clicks renew (happens about once a day, but there is no automated way in the system to do it and having the app do it saves it being unlisted for hours and saves someone logging in to do it). Several that download specific combinations of documents from several different portals, where the user would just suck it up previously and right-click on each one to save it (this has a bunch of heuristics because it really required a human before to determine which links to click and in what order, but Claude was able to determine a solid algo for it). Another one that opens PDFs and pulls the titles and dates from the first page of the documents, which again was just done manually before, but now sends the docs via Gemma4 free API on Google to extract the data (the docs are a mess of thousands of different layouts).

[Denzel]

None of these projects sound like weeks worth of scope w/o AI.