Connect with the Product Hunt community

This could be related to your industry, or even a side project you're working on.

Here are my 5 (I couldn't function without them):

1. Grammarly proofreading my texts, not just posts, but also client communication

2. ChatGPT / Claude mostly brainstorming, help with copy, and summarising

3. Figma I can put the basic graphics together quickly.

4. Translator sounds incredibly old-school, but English is not my mother tongue

5. Gmail and not only for communication, but also for storing ideas and sending myself email reminders for posts

For me, I feel like the hardest part isn't choosing between tools like React, Firebase, Railway, etc, it's really deciding which parts of the stack I should commit most of my time and tokens early and which ones may become painful to replace later.

Do you stick with a familiar stack and avoid overthinking it, design around expected scale from day one, let your coding agent influence the architecture, or start with the cheapest setup and migrate later? Also, curious which early technical choice has saved you the most time, and which one you wish you probably shouldn't have overthinked on.

The one where Skim stops being picky about which AI you talk to, and the whole app goes on a diet at the same time. Efficiency and choice, in one download. You're welcome.

New

• Bring your own AI endpoint (OpenAI-compatible). A third provider joins Anthropic and OpenRouter: point Skim at any OpenAI-compatible API Ollama, LM Studio, vLLM, your homelab gateway, whatever. Just a Base URL and a Model ID; the API key is optional (leave it blank for local servers that don't want one). No key = no Authorization header, so your Ollama box stops complaining. (Closes #12.)

• AI chat that can actually breathe. The command palette (Ctrl+K) can now expand to near-fullscreen for reading long answers one toggle in the corner, only in chat mode. Repeat Ctrl+K flips it open/closed instead of nuking the palette. It remembers your preference, and text stays in a comfy ~760px reading column instead of sprawling edge-to-edge.

Fixed

It doesn't even have to be a big dramatic failures, more the small moments where something clicked and you went from trusting the output by default to double checking everything. For me it was watching an agent confidently rename a function across twelve files, then leave the original function untouched in a thirteenth file it apparently didn't search, with zero indication anything had been missed. It wasn't even a hard case, the file just wasn't in the directory it happened to grep first.
What was your moment? And did it actually change your workflow afterward, or did the trust creep back in after a week like it always seems to for me?

For a while, we were tracking the usual SaaS stuff like signups, pageviews, DAU, WAU, and retention charts. Useful to know, but none of it told us whether people were actually succeeding with Causo. So we started using PostHog properly and built our own dashboards around the things that matter for our product.

Causo now has two sides:

Causo for Fundraising has a database of 1,000+ funds and 17,000+ investors. It helps founders find the right partner at the right firm, understand why that person is relevant, and write outreach specifically for them.

Causo for Sales uses the same technology to research almost any niche live. You describe the companies you want, and it finds them, checks why they fit, identifies the right people, verifies contacts and writes the outreach.

I've been running Claude Code, Cursor, and Codex pretty heavily for the last few months and I keep hitting the same loop:

1. Start a task in one agent

2. Switch to something else (Slack, Twitter, another terminal)

A fair question came up on Vincent s launch thread: layer styles and blending modes are where PSD interchange usually stops being honest.

Vincent s current contract is deliberately narrow. It imports 8-bit RGB/RGBA PSD layers as raster layers and retains names, bounds, blend-mode keys, opacity, and visibility in its session/XMP manifest. It does not reconstruct Photoshop layer styles, smart objects, adjustment layers, editable text/vector structure, or masks as editable masks; raster pixels are the compatibility fallback.

On export, Vincent writes a merged preview and separate rasterized layers from bottom to top, including text, shapes, and images after rasterization. Native layer records are currently Normal, 100% opacity, and visible; preserved values stay in Vincent metadata rather than being rewritten as Photoshop-native properties.

The honest positioning is raster-oriented PSD interchange, not lossless Photoshop document editing.

After building and launching 4 B2C macOS apps, I decided to release one of our internal tools that helps us evaluate and track marketing channels.

Days of preparing for the launch, setting up onboarding, landing page, redesigning the dashboard, testing, and more.

Converting an internal tool built for our needs into a standalone product is not as straightforward as you might think.

When you're a first-time founder/maker, and you're the only person using your own product, you probably overlook important things. That's why you need to test the product with as many people as possible.

The problem is that time is limited. You have to decide not only how many people will test it, but also who those people should be.

You can now collaborate with your teammates in a shared workspace, making it easier to create, manage, and update interactive demos together.

In the month that I've been here, I've been noticing a pattern in a lot of launches - strong demos, polished UI, clear outputs of "what it does."

But when I ask myself "What problem does this solve?" I sometimes have to dig for the answer. (I come by that thinking honestly - I've spent 33 years building and fixing businesses, so this is the lens I can't turn off.)

I've always struggled with promoting my own work. It always felt a little awkward because I grew up in an environment where drawing attention to yourself wasn't really encouraged.

That's not exactly ideal when you're trying to build a business, and even less so when marketing is literally how you make a living. :D

Weather mini 3.6 is now available. This update adds local weather sources in supported regions, makes the app nearly half the size, and brings a series of improvements across Weather mini.

Obviously, both are critical for survival. But which one actually moves the needle?

On one hand, you can prepare an incredible go-to-market strategy, but what good is it if your execution falls flat? If you don't have time to be consistent, your messaging is confusing, and your visuals are boring, nobody stays long enough to care about your plan.

For a long time, social media felt like one big town square.

Now it feels more like a collection of neighborhoods.

As someone who manages social media, I also have to manage what happens in the comments section.

Sometimes it's constructive criticism. Other times it's pure hate.

My Windows build has been in Microsoft's certification queue for three weeks. Three new models shipped in that time, two of them can supposedly do my whole job, and not one of them can get a human at Microsoft to press approve.

What's the longest you've been stuck on something you couldn't code your way out of?

I keep telling myself, Tomorrow I ll finally get uninterrupted focus time.

Tomorrow arrives

and it s another day of PRs, bugs, meetings, helping teammates, and context switching.

Is this just me, or is this the default experience for most software engineers?

For the past 3 months, I ve been building a LinkedIn extension that tracks activity and helps users avoid getting restricted or flagged by LinkedIn by quantifying their actions over time.

It s based on a problem I ve experienced myself, and (as bad as this might sound) I m hoping I m not the only one who has this problem.

Everyone perceives entrepreneurship completely differently, and the weight of certain challenges varies from case to case. You always see things differently depending on the stage of life and business you're in, because your position is different each time.

• When I was a teenager my biggest problem was "What will people think of me when I will start doing this?"

• In my early twenties my biggest problem was "What if I can't figure out accounting, taxes, legal stuff?"

• Now I have a different problem how do I scale something?

Daily reality: Claude Code in one pane, Codex in another, Cursor in a third, plus a few shells. An agent stops and waits for "yes". By the time I find the right pane, 20 min gone.

Just me? What's your setup notifications, layout tricks, or you've accepted the tax?

A big part of my week is spent talking to early-stage founders about how they handle login, access, and identity, and there is a pattern I keep noticing that I want to understand better.

Almost everyone puts auth off at the start, which honestly makes sense when you are still trying to prove the product matters at all.

Two days out. Vercel Day is this Thursday, July 16, and we want to see what you've been building.

The mechanics, one more time:

I realized I probably couldn't stay away from the internet for an entire day. :D

Partly because I want to keep my Product Hunt streak, but also because:

• I try to nurture my community and engage with them every day (essential for growing).

• I handle customer support daily.

• Missing important news from the tech world gives me FOMO.

Hey everyone,

I've been building a labelling tool, a desktop app (PyQt6) for capturing and annotating gesture datasets think of it as a companion tool for gesture recognition pipelines like Gesto, making it easier to collect, label, and export hand landmark data for training models.

I'm at a fork in the road on direction, and I'd love your input:

1. Open source it release it freely (currently GPL-3.0), let the community use it, contribute, and shape where it goes.