Road to 1,000,000 #Votap users Day 55 | Current: 1285

Hello PH community!

I built Frame Localizer because translation usually gets treated like a text problem, when it s really a UI problem.

It s a Figma plugin for testing multilingual UI earlier in the design workflow. The focus is simple: help teams see whether a screen still works after translation, especially when layout, mixed-language content, and UI consistency start to break down.

Hey PH!

We just launched Genie - Databox's AI analyst, and it's live on the leaderboard today.

One thing we kept seeing in user research: teams have dashboards, but still can't get fast answers. "Why are leads down this week?" still takes hours of manual digging. Genie fixes that - you ask in plain language, it finds the right metrics, runs the analysis, and returns an answer with a chart. No SQL, no waiting.

A few things I'm curious to hear from this community:

One recurring issue we ve been seeing with Supabase setups is not the database itself, but how credentials are managed across environments. The common pattern looks something like:

• credentials stored in .env files or secrets managers

• multiple environments (dev, staging, prod)

• manual propagation or duplication across those environments

It works, but over time it seems easy for things to drift:

• a key gets rotated in one environment but not others

• a redeploy misses an env var

• credentials get misconfigured during setup or migration

A huge thanks to everyone who tried Pinnacle, commented, challenged us, and shared thoughtful feedback last week
We were excited to finish as the #4 Product of the Day. More importantly, the launch gave us a clear signal about what resonated most.
For anyone new here: Pinnacle turns your iPhone into an AI performance coach. It uses built-in phone sensors, conversation, and wearable data via Apple Health to help you improve focus, resilience, energy, and performance with science-backed tools.
You can download the app here:
https://apps.apple.com/us/app/pi...
A few things that stood out:
1. People want insight, not just more data
One of the strongest themes in the comments was that raw metrics alone are not enough. People don t want another dashboard full of numbers with no context.
They want to understand:
How am I doing right now?
What is driving it?
What should I do next?
That is a big part of how we think about Pinnacle. The goal is not to flood you with biometrics. The goal is to turn signals from your body and behavior into something actionable in the moment.
2. Low-friction measurement really matters
A lot of people responded to the fact that Pinnacle works from the iPhone you already have, without requiring extra hardware to get started. That convenience matters more than we expected.
Several comments also pushed on an important challenge: accuracy and calibration. They were right to do so.
If you are using phone-based measurement, the system has to adapt to the individual, establish a baseline, and avoid overreacting to noisy signals. That reinforced one of our core beliefs: relative progress from your own baseline is more useful than generic scores.
3. Personalisation has to reflect real life
One of the most useful questions we got was whether brain-performance baselines should account for hormonal cycles. The answer is yes.
If you want to understand focus, energy, and resilience properly, context matters.
Personalisation cannot stop at a single static baseline. It needs to reflect the realities of each user s life, including sleep disruption, parenting, pregnancy, postpartum recovery, and cycle-related changes over time.
This is an area we want to keep improving.
4. Coaching works best when it is personalised to state, not just prompts
Another theme was the difference between Pinnacle and a standard LLM.
People have already tried using general AI as a coach, and the common experience is that it still puts too much burden on the user to know what to ask.
What we are building is different: Pinnacle combines conversation with biometric and behavioral context, then guides the right intervention at the right moment.
That might mean breathwork, reflection, a micro-break, or a focused coaching prompt depending on what the system sees.
5. Trust, privacy, and product feel are part of the product
Some of the best questions were about privacy, camera use, and whether the experience feels helpful rather than intrusive.
Those are not side questions. They are central.
We want Pinnacle to feel like a calm, intelligent coach, not another noisy app demanding attention. That means being thoughtful about privacy, clear about how sensing works, and careful about when the product should guide versus when it should get out of the way.
What we re doubling down on now

• Better baseline calibration and more personalised scoring

• Stronger coaching flows based on both conversation and biometric context

• Continued work on attention measurement and training

• Better support for more diverse stress and recovery patterns across users

• Making the product feel lighter, clearer, and more useful from day one

Launch day was great, but the real value has been seeing which parts of the vision people immediately understood, and which parts we need to explain better.
If you have tried it already, I d love to hear: what clicked for you, and what still feels unclear?

Been noticing how quickly vibe coding has become a real workflow lately.

A few months ago most of us were still writing everything manually or just using AI for small snippets. Now it feels like the process has shifted to describing what you want and iterating with the AI until the product behaves the way you imagine.

Guys, a month ago, Anna, a product designer, reached out to me from the ProblemHunt community. She described her problem in detail in DMs. It was probably the most genuine and sincere description of pain I have ever seen. Anna has this ability to talk about her problems with complete openness and raw emotion for any researcher, it's an absolute gift.

Today she shared a new problem, and I've just posted it now. It's hard for me to convey the tone through text in a post, but trust me, it's genuinely painful. It's that intense fear of a designer becoming obsolete in the era of AI.

Genuinely curious what the community does here.

We've been talking to hundreds of teams building with Cursor, Claude Code, and other agentic tools and the honest answer from most of them is: "We just run it and hope."

Some do a quick manual click-through. Some write a few spot checks. Some just ship and wait for users to find the bugs.

We built TestSprite to solve exactly this autonomous testing that runs from your PRD and codebase but I'm curious what your actual workflow looks like before you merge.

Clarity is re-launching.

What started out as a small idea rattling around in my head has became a fully fledged intelligence system centred around tracking caffeine.

Every time I moved countries, I started from zero with my health story I suddenly had no health past, years of health check ups and trends as well as documented risks were lost.

As a patient advocate across 10 years and 4 countries, and noticed that no matter the system, the issue was always fragmented, messy, and hard to understand health data we have no real control over.

Road to 1,000,000 #Votap users Day 44 | Current: 1147

I don t want Votap to become Instagram.

Had a thought, and I must put it out here:
Over the past year, building with LLMs, I ve noticed that the big change is not necessarily that AI gives us better answers. Change your perspective and think like this: we, humans, are starting to ask better questions. And here's why:
When search engines dominated, we asked:
What is X?
How do I do Y?
Best tools for Z?
With LLMs, the questions are different:
Help me think through this decision.
Challenge my assumptions.
What am I not seeing?
Act as a product strategist and critique this.
Clarify my messy thinking.
That s not getting the information, that s cognitive augmentation.
I feel we re moving from:
Finding knowledge to extending reasoning
And this raises bigger questions for builders:
1. Are we designing AI tools that optimize for answers
or for better thinking?
2. Is the real advantage having a stronger model...
or asking better questions?
3. In a world where everyone has access to GPT-level intelligence,
does leverage come from prompting skill, system design, or taste?
4. What new human skills become valuable when execution becomes cheap?
It feels like we re entering a phase where:
Curiosity > credentials
Clarity > speed
Systems thinking > single outputs
If you re building in AI right now:
What types of questions are your users asking that they couldn t (or wouldn t) ask before?
And are you building for answers or for thinking?
Would love to hear what patterns you're seeing.
______________________
www.zackapp.space
Download Zack from the App Store and soon from Google Play: https://apps.apple.com/us/app/za...

Hot take on AI: The best AI tools will be invisible.

I used to think the best tools were the ones that had lots of features.

But making a tool disappear is more powerful than building endless features.

I d like to share iPhotro v4.0.0, a free and open-source, local-first photo manager that recently gained a set of advanced color grading tools.

This release focuses on giving photographers precise control over color and tone, while keeping a clean, non-destructive workflow and a familiar, macOS-like interface.

Color Grading & Tone Control

Besides the floating shelf inside Finder, Shelfinder is getting an image & PDF optimizer in the next release.

You ll be able to optimize PNG, JPG, and PDF files directly from the app no extra tools, no context switching.