Connect with the Product Hunt community

You find an app that looks simpler or costs less. You try it, like it, then go back to the old one because moving your work feels like another project.

The awkward part might be:

I m getting closer to launching my tool on Product Hunt, hopefully sometime in the second half of this year.

I currently have a 3-phase launch strategy in mind.

Phase 1 Free version

The difference between a tool an agent chooses to call and a step that runs every time is the difference between a suggestion and a guarantee.

Microsoft's Copilot Studio documentation now describes a preview feature called hooks. The definition is plain: a hook runs one of your workflows automatically when something happens in your agent, and you use it "when you need something to happen every time, rather than only when the agent decides it's relevant."

Genie, our AI Analyst, can already tell you what changed in your numbers. It's never been able to tell you why, because the why almost never lives in Databox.

Revenue drops 8%, and the real reason is a stalled deal in HubSpot, a pricing objection buried in a Slack thread, or a support ticket nobody flagged. Right now, finding that out means leaving your dashboard, opening three other tools, and piecing it together yourself. Every time.

Next week, we're launching MCP Connectors. Connect your CRM, Slack, support desk, or any MCP server, and your AI Analyst gets that same context, right inside the conversation. Ask why a number moved, and it points to the actual deal or thread behind it, not just the number.

This week I went through the sign-up flow of ten well-known products, imagining an AI assistant doing it for me. It could read what each product does and what it costs. On almost every one it would stop at the email confirmation or a CAPTCHA. I had never thought of a sign-up form as something software would fill in.

I see three ways to handle it, and I keep going back and forth:

1. Keep sign-up human-only. Safer, and nobody has to think about bots with accounts.

2. Let the agent do everything except one approval step, where the person confirms the email and accepts the terms.

3. Give agents their own path, like an API key or OAuth login, separate from the human form.

Today we shipped JarvisCore v2.1.0 with fast RAG, stable atom life cycle, and better browser automation. Please refer to https://jarviscore.developers.pr... for more details (v.2.0.0 and v2.1.0). Test it out and let me know what breaks.
For more reads:

1. https://jarviscore.developers.pr...

2. https://jarviscore.developers.pr...

3. https://jarviscore.developers.pr...

Hi everyone

Based on some of your recent feedback, I've released a major feature update to track every cloud services deprecation and end-of-support deadline directly inside Cloud Releases.

A countdown for every retirement. The new Deprecations page lists every retirement and end-of-support notice by the day it takes effect, soonest first, with the days left next to each one.

FinderGit 0.56.0 is out: your rankings are charts now!

FinderGit Overview: Largest on disk open as a donut, the biggest repositories as slices, the rest folded into Other and the total in the middle

Everyone has one. "Keep it short." "No emojis, ever." "My dog's name is Biscuit, stop calling him Buddy." The thing you've typed so many times you could say it in your sleep.

Here's the game:

1. Drop yours in the comments, exactly how you'd say it.

I tested on wifi. Fast, reliable, stable. The app worked perfectly.

Then I used it on a train. Spotty connection, switching between towers, occasional dead zones. It fell apart in ways I never saw in testing.

Hey Product Hunt! I'm Kristina, working on marketing, back with another product after some time away.

I know from experience how hard it can be to get back into job hunting and interviews after a long time in one role. It's like learning a new skill.

Hi everyone,

This is a first look at the Autonomous Electronics engineer.

You give it a brief and it builds the board in stages: spec, block diagram, schematic, E-Sketch, layout, route, ECAD. Each stage is its own artifact you can open and inspect.

Our bold vision is for Everyone, regardless of their engineering know-how, to be able to create functional, manufacturable, multidisciplinary products using natural language - electronics, mechanical, controls and software/firmware. The same experience folks enjoy in tools like Lovable for vibe-coding, extended to complex, real-life systems.
We will continuously extend our part libraries for electronics and add specialized functions, like LED chip creation.
Soon we'll start a public PCB/chip library on our website, stay tuned.

I run 10+ products solo and read the support inboxes myself. After a press release for one of them, the contact address got buried in pitches: webinar invites, free whitepapers, agencies wanting to run my ads. Gmail filters didn't hold. Senders change every time, and "thank you for your inquiry" shows up in both auto-replies and real human replies.

The worst ones borrow a platform. Someone shares a pitch as a Google Doc, so the email comes from Google. Or they sign you up for their Zoom webinar, so the invite comes from Zoom. You can't send Google or Zoom to spam.

Jev is what finally fixed it. It doesn't write anything, it just tells you how likely each yes/no answer is, and you decide where the line goes. Per email I ask five yes/no questions in one call: did a person write this, should we reply, are they selling us something, do they want a meeting, are they clearly asking us to stop. A few rules around it:

Ask twice, act only if both agree. Otherwise I look myself.

Alongside today s launch, we ve added a trip planner to Traveler Map, our map for discovering parks and planning outdoor trips.

You can add stops and notes, build a packing checklist, and mark parks as visited along the way. It s still an early version, currently focused on the US, with more features to come.

Hey makers

Today we've shipped multiplayer in JarvisCore.

Most agents are built for one person in one chat. But work happens in teams: people disagree, change their minds, and add "oh, and also " while the work is still running. Multiplayer is built for that.

How it works:

I logged every support ticket for three weeks. 11 total. Six of them were the same problem, phrased six different ways. The users weren't confused about different things. They were confused about the same thing and I had never noticed because they described it differently.

I changed one sentence on the screen where they got stuck. Not the flow. Not the feature. One sentence that explained what would happen next.

Music Dawn 1.2 went live today. This update is about listening back to your ideas.

Play a folder in order or shuffle it. When one song ends, the next one starts, and the mini player keeps going while you move around the app. Playback carries on with the screen locked or in another app, and you can skip a song or favorite it from the Lock Screen.

Every Mac with Apple Silicon has a Neural Engine. More apps use it every month for dictation, transcription, and other AI that runs on the Mac.

Activity Monitor doesn't show it. I had no way to see how busy it was or which app was using it.

Super excited to announce the new Formbold

We first launched Formbold here as a simple form backend for static sites. Point any HTML form at a Formbold endpoint and submissions land in your inbox, with no backend or server code. That's still the core, and it works exactly the same.

Coding agents understand your repository well. They know very little about the machine it runs on.

Ask one to free up disk space and it often reaches for rm -rf. Ask what is using port 3000 and it pipes raw lsof output into the conversation.

If a model can escape, the sandbox was never actually a sandbox. Network policies were too loose, shared services created side channels, privilege boundaries were theater. No amount of prompt engineering fixes a misconfigured egress rule

Spent a lot of time analyzing competitors before launch, but once building started, all those notes became outdated pretty quick.

Tracking everything daily creates useless noise, but waiting months might mean missing major pricing or feature updates. Not sure what's actually worth keeping an eye on long term.

How often do you look at competing products, and what metrics or changes do you totally ignore?

I'm 19 and building Murmell with Gabriel.

Sometimes people are super supportive.

Add and maintain comparison tables inside an existing HTML page with HtmlDrag.

Insert a table, edit cells, manage rows and columns, apply a clear visual emphasis, and configure links. The guide uses an existing writing-course page and keeps the original descriptions available.

Vibesmonitor now runs a daily site audit. It fetches each project the way a crawler does, with no JavaScript, and writes three reports. These are the issues that come up most: