if i use claude or codex, i constantly am screen capping to show bad padding / alignment / whatever. is there a defacto way to let claude or codex tool call to see the browser or render a page for themselves?

I've been talking to dozens of PMs over the last few weeks who prototype with Lovable, Bolt, Figma Make, V0, etc. Same frustrations keep surfacing.

• Output looks a bit generic: looks like a demo, not your actual product

• Context loss: explain your product in ChatGPT/Claude, then re-explain in Lovable, then again somewhere else

• No edge case thinking: AI executes prompts literally, doesn't challenge or expand on them

The core issue I keep seeing: these tools are interface builders. They're great when you already know exactly what to build. But the hard part, thinking through the flows, the states, the edge cases, where users will actually get stuck, that's still entirely on you.

https://x.com/airwolfspace/statu...

AI dev tools are moving stupid fast. Every few weeks, there s a new must-use. Some stick. Most don t.

Some vibe coders are developing full products with @ChatGPT by OpenAI+ @Replit. Others swear by @Cursor + @Claude by Anthropic . A few are mixing @Lovable , @v0 by Vercel , and @bolt.new . New and shipping way faster than expected.

I ve been refining my own vibe stack lately.
Building with @Google Antigravity at the core. It keeps the flow clean when things get messy.

Share your current Vibe Stack:

The tax filing season is approaching, and it occurred to me that I haven't come across many AI tools on this platform that would solve this issue.

Maybe for the following reasons (I think):

• diversity/complexity of tax entities and legal forms of business

• international business, accounting cases differ from case to case (taking into account currencies, forms of business, tax laws)

• laws in accounting and finance change very quickly

I keep going back and forth on this, so I m curious how others think about it.

At what point do you start taking non-English markets seriously?

• only after you feel solid PMF in English?

• when inbound users from certain regions show up?

• by picking one market early (Japan, LatAm, etc.) and committing?

• or do you just keep pushing it off to stay focused?

PH builders: what are key lessons you ve learned whether technical or product or GTM from building agents? This is still such a new discipline that it would be great to share amongst this community of builders.

I ll kick off with an experience that had us scratching our heads for months last year

For as long as software has existed, the user has been a person. Someone sitting at a desk, poking at a phone, or calling an API. That assumption was so obvious it was never really a design principle, it was just common sense. Every decision about hierarchy, color, button placement, and error messaging was downstream of a single fact: a human being is going to see this.

With agents, that assumption is starting to fail.

Hey PH

We just sold $300k+ in 60 days with @Pretty Prompt through a lifetime deal on AppSumo.

This shows you can build a company your way.

As users, we all want to try a product before committing. As builders, we want to show real value without over-engineering and investing time 'just for show'. Finding that balance is harder than it looks.

I just shipped my demo for Rewo (https://rewo.app), and intentionally went with a live, real demo:

• Fully functional product (same codebase as prod)

• Uses demo data instead of real integrations

• Some interfacing + sync pieces are disabled

• Auto-resets on a schedule so anyone can jump in fresh

I am seeing this with Lovable, Verdent, Replit: I am clear, RAG my prompts, clean them with Claude Opus 4.6, find that with tough problems, they'll tell me something is fixed or done, and it isn't. Not even close. And I'm burning costly credits, making no progress.
I'd love to learn what others are doing.
I'm building a multi-agent tool that integrates with 25+ LCNC sites and also IDEs, and yes, there are tough problems with the tool's awareness of what a user is doing in a console or fields in a browser window. I'd apprecaite it if the nocode platform simplay told me, "no can do," rather than trying one thing after another, staying stuck, and costling me $100 or more per day to keep failing.
Thanks, in advance, for your suggestions!

I think the biggest AI boom was in 2023-2024, but only now have I noticed improvements that have positively helped many businesses.

If I had to name three things that have had a very positive impact on business, they are:

• Improved image creation using GPT Chat

• Realistic videos through AI, where costs are reduced by hundreds, sometimes thousands of dollars (production video agency vs. a few custom prompts)

• "vibe coding" tools that show me a visual and I can reverse query and learn why the code is written in such a way that I got a certain result.

We won t pretend that the world isn t tense, because relations between countries are increasingly strained. (Coming from a country that never had technological or numerical superiority, we ve mostly become just part of the regime.)

But not everyone is on the same page, and countries are investing in defence.

Hey makers!
I've been deep in prompt engineering lately while building an AI tool, and I'm genuinely curious about how others approach this.
A few questions:
1. Do you save your best prompts somewhere? Notion, text files, dedicated app, or just copy-paste from chat history?
2. How do you iterate? Do you have a systematic approach or just tweak until it works?
3. Different prompts for different models? Or do you use the same prompt for ChatGPT, Claude, Gemini?
4. Text vs image prompts do you treat them completely differently?
I've noticed I was doing the same optimizations over and over (adding role, being more specific, structuring output format), which made me wonder if everyone has their own "prompt formula."
Would love to hear your workflows!

As leaders, we spend most of our time pouring into others. Our families, our friends, our teams. We invest our time, energy, and presence in being there for others. But somewhere along the way, it becomes easy to overlook an important question

Who is pouring into you?

I work closely with product and growth teams, and one challenge I keep running into is explaining user drop-offs to people who aren t deep into analytics.

The data usually shows where users leave, but turning that into a clear, confident explanation without overloading dashboards or making assumptions can be tough. Especially when the audience is leadership or business stakeholders.

I m curious how others handle this in practice:

I ve been experimenting with a CLI workflow that removes the most annoying part of AI-assisted dev:
re-explaining context every single time.

Instead of prompts like:

Integrate Stripe payment gateway with X, Y, Z

I just run:

Just wanted to say a quick thank you to everyone who checked out Cue today.

I launched this morning not expecting much. It's a tool I built over the holidays that turned from a side project into the main project I'm working on. Seeing it hit #3 (so far) is honestly surreal.

I'm Kevin, founder of EnginifyAI. Over the last 12 months I've been working on a prompt engineering tool. I started off using Bolt but quickly I found myself unable to completely use it effectively. I then tried Cursor and was using it early on but maybe I had the wrong settings as I found myself using all my credits in 2 days. So, I switched to Windsurf, and to my surprise credits were a bit more manageable and it took about 2 weeks before my credits were consumed. Keep in mind that I am new to coding so I spent a lot of time asking questions in Windsurf instead of using my paid subscription to Anthropic.
I'm coding using React/Typescript and Supabase. I have learned that coding is a lot of work, a lot of fine-tuning, and a lot of testing and fixing. The one thing I haven't quite figured out completely is how to fix migrations. Early on I was running SQL scripts directly in Supabase without migration scripts because I found it to be faster. But now Windsurf uses very old migration script references and I find myself fixing the same issues because of an old migration script reference. Any idea how to fix this?
I assume that vibecoding is an experience everyone can enjoy but comes with frustrations about asking the right questions, or being very specific about my requests. I am using Claude Sonnet 4, 4.5 and 4.5 thinking. Are these the best coding ai models for Typescript?

So this happened and I'm still processing it lol

We've been launching stuff on Product Hunt since last year, and like everyone else, I hit up old friends asking for support. You know how it goes.

Anyway, I met up with a few of them recently and they started thanking me. I'm sitting there thinking "aw that's sweet, they liked our product!"

But nope. They were thanking me for introducing them to Product Hunt itself. Apparently they've been addicted to it ever since, checking it daily for new AI tools.

I've always been a B2C founder. I've built an app to 100k+ MAU and sold it to a major company. I'm now building a tool called Modu.io to help businesses collect user feedback, taking directly from my own struggles (I got so frustrated with existing tools that I ended up using a single Google form).

I'm not particularly suffering the switch on the building side, I'm actually enjoying it since I'm more interested in using this tool myself, than I was with the B2C one. What I'm finding myself (sort of) uncomfortable at is the distribution/marketing side. I've launched on a bunch of ProductHunt like websites, ended up first on Uneed yesterday (didn't get much traffic-wise honestly), and bought a couple features on some of them as they were relatively cheap.

Over the last year, I ve been experimenting more with local-first patterns , apps that prioritize offline functionality and sync later instead of depending on constant server calls.

What used to feel experimental now feels surprisingly stable. Faster UI, fewer loading states, and a smoother user experience overall.

I rebuilt a small side project recently with a local-first approach, and the difference in responsiveness was noticeable. But it also introduced new challenges around conflict resolution and state consistency.

It makes me wonder:

Hey PH community!

I ve been spending a lot of time thinking about how people actually work with prompts while building a tool in this space, and I realized I have way more questions than answers.

A few I d love to throw out:

LinkedIn officially shared the job titles that started appearing more often, and with the rise of AI, the market is restructuring.

The actual top 10 roles that have seen the biggest rise in listings (in the U.S.) are:

1. AI engineers Engineers developing and implementing AI models that perform complex tasks

2. AI consultants and strategists - Helping organisations plan and implement AI technologies to improve operations

3. New home sales specialists Which sounds like a rebranding or real estate agent

4. Data annotators Labelling and reviewing data for AI projects

5. AI/ML researchers Designing new AI models and systems

6. Healthcare reimbursement specialists Ensuring healthcare providers are getting correct and timely payments

7. Strategic advisors and independent consultants Which seems like a pretty broad-ranging segment

8. Advertising sales specialists You re reading a marketing blog, I assume you know this one

9. Founders Not sure this can be listed as a job title in itself, but LinkedIn s keen to highlight how people are shifting to their own businesses

10. Sales executives

I m curious how far teams have really gone with AI support.

Are you still using chat mainly as a helper alongside tickets - or has AI actually reduced your support volume in a meaningful way?

Would love to hear:

What tools are helpful