Hacker News: alertchecker

New comment by alertchecker in "Show HN: AlertChecker – get emailed when a plain-English statement comes true"

alertchecker — Sun, 16 Aug 2026 08:03:53 +0000

The MCP part: If you're using Claude, ChatGPT, Perplexity etc. and install the connector you can then say "alert me when [...]" directly in a chat and an alert will be created for you - no separate visit to the site needed. Setup instructions here: https://github.com/steve-chambers/alertchecker-mcp

Show HN: AlertChecker – get emailed when a plain-English statement comes true

alertchecker — Sun, 16 Aug 2026 07:48:00 +0000

I built AlertChecker to help address a limitation with AI chatbots - they only respond when you've asked them something. You talk to them and they talk back. I wanted a way for them to tell you something of interest another time, when you're not even in a conversation.

For example, type a statement like "the iPhone 16 Pro is back in stock at apple.com" or "it's going to rain in London tomorrow," and AlertChecker uses AI models with live web search to monitor it periodically. You'll then be emailed when it becomes true. No scraping rules to configure, no specific site integrations to pick, just a sentence in plain English.

It's a Next.js web app with a small Node backend service doing the actual checking in a continuous loop. There's also an MCP server, so if you use Claude or ChatGPT you can create alerts by just asking in a normal conversation instead of opening the site.

The number of checks is currently limited overall while I keep an eye on costs, so it's shared across everyone using it right now rather than a fixed per-account quota. I'll be raising that as I get a better sense of real usage patterns.

Seems like this tool could have a very wide range of applications (given the statement can be literally anything under 4000 characters). Interested to hear about real-world uses beyond stock/price checking or weather alerts.

Comments URL: https://news.ycombinator.com/item?id=49317809

Points: 2

# Comments: 1

New comment by alertchecker in "Is this the end of human code review?"

alertchecker — Sun, 16 Aug 2026 07:46:26 +0000

Think we're pretty close to the point where we'll no longer need to prompt AI to refactor or review the refactoring if it's done within tight constraints i.e. absolutely no change to functionality. But when functionality changes may be acceptable as part of it, it's less clear - in my experience AI isn't at a point yet where it can always be trusted to "understand" what the requirements are (including to what extent they can be allowed to evolve), what is or isn't acceptable in terms of user experience etc. That's where human review is still useful and in many cases, essential.

New comment by alertchecker in "Every fucking website: 2026 edition"

alertchecker — Sat, 15 Aug 2026 16:27:23 +0000

It can't be AI-generated - AI doesn't swear

New comment by alertchecker in "Why does Opus 5 feel worse to work with?"

alertchecker — Sat, 15 Aug 2026 16:25:01 +0000

Agreed, think the first user rule I ever put into Cursor was "Don't write code comments unless absolutely necessary to explain something that couldn't just be inferred"

New comment by alertchecker in "The AI Situation in Software Development"

alertchecker — Sat, 15 Aug 2026 16:20:49 +0000

My personal experience is the larger the task you ask it to do, the less attention it pays to the details - for a very large task it seems more prone to missing test coverage, writing duplicate code, not refactoring where it should etc. So I try to split into smaller tasks where possible (also makes it easier to review).

New comment by alertchecker in "Working with AI Feels More Like Leadership Than Coding"

alertchecker — Sat, 15 Aug 2026 15:51:41 +0000

I've been coding professionally for almost 30 years and it's only really in the last few months I've started to "trust" AI to do a better job than I can within given time constraints - but with a big caveat - as the article points out, the AI needs to be kept on track and questioned about its approach, told about inconsistencies etc. To aid with that it helps to have a lot of Cursor rules that guide the approach - built up over time, mostly based on seeing what AI didn't get right.

Well that's at work - but I've actually taken a different approach for my own personal project and generally now allow AI to do things in its own way - I put my effort into checking the functionality rather than the code itself. This does result in some fairly sprawling code and some bits that are practically now only really maintainable/"understandable" by AI. Functionality is still fine though, which is what really matters there when there's no other team members and understanding every part of the code isn't critical. Guess in future it may just self-refactor it without even being prompted.