Connect with the Product Hunt community

Most websites lose almost everyone who visits. People land, have a question or a doubt, don't find the answer quickly, and leave. A chat widget is the obvious fix, but one that sits in the corner waiting to be clicked usually doesn't do much.
What we've seen work better, working with agencies and shop owners, is treating chat as part of the sales process, not a support add-on:

1. Show up at the right moment. Open the widget when someone's been on the checkout page for a couple of minutes, or sat on a product page without adding anything to the cart. That's usually when a question is stopping the sale (delivery, returns, sizing).

2. Know why they're there. Pass the page, the product or the cart to your n8n workflow with every message, so the agent can answer the actual question and doesn't open with "How can I help?".

3. Ask different questions on different pages. Pricing-page prompts and returns-page prompts shouldn't be the same.

4. Don't lose the people who aren't ready to buy. Capture them as leads into your CRM (HubSpot, Pipedrive, Mailchimp or whatever you use) with consent, so you can follow up.

5. Book the calls. Let the chat book the meeting with Calendly or Cal.com, so a warm visitor doesn't have to wait for an email.

All of that can be wired up with n8n and a bit of JavaScript, and we've put ready-made workflows for the CRM, booking and order-lookup parts at n8nchatui.com/recipes.
What I'd like to know: which of these has actually moved the needle for you or your clients? And what have you tried that didn't work? I'd love real numbers if anyone's willing to share.

I build by directing AI agents. I'm not a developer, so tests are how I know something works. The app has about 3,600 of them. They run three times before anything gets merged. One day a deploy went out before its database migration. The new code went live expecting database changes that hadn't run yet. The app was down for 5.5 hours. Every test had passed. That's the part I keep thinking about. The tests run against development, not production. They check that the code does what it should. Nothing checked the order things shipped in. So a green suite told me the code was fine. It said nothing about the deploy. If you ship with AI agents, what checks the deploy itself? Migrations, order of steps, anything that only exists in production?

iKnowMyMac 1.7 is out, free for every license. What's new:

• Blocking, off until you turn it on: block any connection by app, domain or country, for 5 minutes, an hour or always

• Install Guard and Agent Guard: hold a connection when an install script or a coding agent reaches somewhere new, and explain it before you decide

• A map of where your connections go, 12 months of history per app with a privacy score, tracker and malware blocklists, encrypted DNS

• A Traffic Control window from the menu bar ( T)

What would you block first?

Full notes: https://iknowmymac.com/changelog

A percentage says what's gone. A Lancetta suggestion says what to do about it, and shows the numbers it rests on so you can weigh it. No model is asked: it's plain arithmetic on your Mac.

Slow down: "At this pace Claude stops in 51m, then waits 1h18m for its reset." Both moments, because the gap between them is the time you'd lose.

A few days ago I asked if you track how much you spend on AI...

The answers were gold hehe

Hey makers

A few people asked here how Many Displays tells identical monitors apart, especially behind a dock, so I wrote it up properly. It covers why macOS mixes them up (same EDID serial plus the DisplayPort disconnect on sleep), a Terminal command to see what your own monitors report, and the clues that can still tell them apart: system UUID, physical port, manufacture date and position.
https://manydisplays.com/identic...
If you run the command and your two monitors print the same serial, I'd love to hear what setup you have.

Hi, it's Morse. Thanks for following AgentValley. Since the launch on Saturday I put out 5 small updates, and two of them came from people here and on GitHub.

1. Leo Heo asked if the card could show how long an agent has been waiting, so he could answer the oldest one first. Now there is a red badge next to "needs you" with the time, and the bar in the notch shows the longest wait after a minute.

2. DJ Sipe asked to use it on a bigger screen next to his MacBook. You can pick the screen in Settings > General > Display. If you unplug it, it goes back to the notch.

3. If you have a lot of sessions open, the ALL page now folds them to one line each when they don't fit, so your other project stays on screen. A session that needs you never folds.

4. Sounds are on by default now. Settings > Sounds turns them off.

5. The app should ask you to update on its own, or run brew upgrade --cask agent-valley.

One thing I want to know: if you run more than 3 or 4 sessions at once, does the folding help or get in the way?

Someone spends twenty minutes preparing an import. They click Run and only then learn that their file is too large for the plan.

What should the app do with the work they have already put in?

First, thank you More of you signed up, tried Ownfeed, and wrote to me yesterday than I expected.
Some of you hit a bug within minutes, told me, and came back after I fixed it. I don't take that for granted.

Here's the honest part: I tested every flow, many times, before launch.
Then real users arrived, and in the first hour something broke that had never broken in testing.
A few hours later, a second thing. Both fixed the same night.

What stings isn't the bug. It's that I felt ready, and the thing that broke was the plain part I had stopped looking at, not the hard part I worried about.

A friend sends you an app that might solve one small problem. You open it and the first screen asks you to create an account before you can see what it does. Some apps need an account to save work or sync; for a quick evaluation, that s a real ask.

As someone building Inquir Compute, I m curious about that first step. The difference may be whether you reach a useful moment before sharing an email, or whether signing up is itself part of getting value.

Hi! This is the first post after the launch! I do see a lot of folks started creating their brains and putting it to work by connecting them to their agents!

Here s the back story why i created this:

Hi everyone

Thanks for all the support on Taste Lab. A lot of you used it to pull the visual DNA out of websites you love.

But I kept running into the next problem. Even with the right visual style, an AI-built page can still feel off, because the agent doesn't know what belongs on the page, in what order, or why.

As we want to achieve big things, we have a tendency to downplay our limits, exhaustion, and health.

And we forget that it is time to stop.

I've been managing a dozen narrow agent configs where each file limits tools and picks a specific model like Opus for architecture planning and Sonnet for basic coding.

But assigning heavy models to review tasks gets expensive fast and juggling too many sub-roles makes the delegation chain messy.

If you use subagents in your dev workflow, do you prefer strict tool boundaries for every single task, or just two or three general-purpose agents?

I always try to share some transparent data when I launch on Product Hunt, so I'll share the numbers and updates in this thread.

When you're building a niche SaaS, you want your tool to be clean, focused, and distraction-free. But lately, I've noticed that keeping our product standalone is actually what s driving our workflow churn.

If users have to copy-paste data or manually move between their primary workspace and our tool, it eventually gets abandoned the moment things get busy.

For mature founders: At what point did you realize you needed to stop being an independent destination and start embedding deeply into tools like Slack, Notion, or existing IDEs/CRMs? How did that pivot affect your roadmap?

Copy something, copy something else, and the first thing is gone. In the new update, the Clipboard in your notch is a full clipboard manager. It sorts what you copy, finds it again, and pastes it with one shortcut.

We're applying with Murmell one more time hehe

Got rejected last batch.

Hey folks looks like our launch images and videos are not showing up on launch page. As we wait to hear from PH Team, I am sharing them here to understand what dadan does.

7 updates since our Product Hunt launch on 16 Oct. What's new:

• Browser tabs: which tab uses the most memory, in Chrome, Brave, Edge, Arc, Vivaldi and Safari. Several of you asked for this on launch day; it shipped the next day

• Runtimes: every Node.js, PHP and Go on your Mac checked for security updates, with Fix, Move or Remove for each

• Traffic: which app connects to which server, off until you turn it on

• The app in 10 languages

Coming next in 1.7: Traffic Control. It asks before an install script or a coding agent connects somewhere new, and lets you block any connection by app, domain or country. Free for every license.

JarvisCore agents join a peer-to-peer mesh. They find each other through gossip and message agent to agent, with no orchestrator or broker in between. The same code runs in one process or across machines.

You're welcome to try it out.
For more reads: https://jarviscore.developers.pr...

The one where your inbox stops believing every email about when it was sent. Trust issues, but healthy ones.

Fixed

• Late mail now shows up where new mail belongs: on top. A message that took two days to reach you used to file itself under its two-day-old Date header, deep in last week, quietly keeping the unread counter at "1" while you searched for a ghost. Skim now sorts by when the message actually arrived, like Gmail does. Ghost found, exorcism complete.

• AI provider outages get a human sentence instead of error code: 522. When the provider (or the Cloudflare in front of it) is having a moment, Skim retries once, then tells you in your own language that the provider isn't responding and to try again in a minute. No more raw HTTP codes.

• Opening a just-arrived message no longer starts from scratch. Background prefetch used to abandon a half-downloaded body the moment you clicked, dropping the connection it had paid for, so your click waited for a fresh login. Now a body that's started always finishes, and your click gets the warm connection.

Housekeeping

I have a bunch of updates to products I need to do (and new products ready for release), but I lost access to the Apple ID that I set up about 15 years ago and haven't been using, except it is the owner of my developer account.

I have been going through their process to get my account back multiple times, and each time they have a ten day waiting period after which, for me, nothing happens. This is getting extremely frustrating and there seems to be no way of getting through to anyone that can help me there.

FinderGit 0.55.0 is out Agents now reads more of what Claude Code really loads, and checks more of what it runs.

1. More of what loads