DEV Community: HelixLabs-dev

10 weeks building in public. 95 installs. £0 revenue. Here's the honest update.

HelixLabs-dev — Fri, 24 Apr 2026 08:50:06 +0000

Ten weeks ago I launched Prompt Helix, my first Chrome extension. This week I submitted FocusForge, my second. Here's the honest state of things.

The numbers

Prompt Helix: 95 total installs, 3 signed up users, 1 weekly active user, £0 revenue.

FocusForge: Submitted to Chrome Store, pending review, not yet live.

What I got wrong

I launched Prompt Helix with a free tier that was too generous. OpenAI and Claude completely free with no caps meant there was literally no reason to upgrade. Fixed that in v1.0.2 with a 25 query daily limit, usage counter, and proper upgrade prompts. First real conversion trigger went live April 3rd.

FocusForge launched with proper freemium from day one because I learned that lesson already.

What surprised me

Building the second product was significantly faster than the first. Same Clerk auth, same Stripe setup, same BYOK architecture. The infrastructure was already there. I could focus on the product instead of the plumbing.

FocusForge has a feature I'm genuinely proud of is the Nuclear Option. Total site blocking for 1, 3, or 8 hours with zero escape route. No clicking through, no disabling the extension. Built it because every other focus tool I tried could be bypassed when willpower ran out.

If you're building a Chrome extension and want to swap notes I'm always up for it.

helixlabs.studio

I just shipped my first major update to a Chrome extension. Here's what I changed and why.

HelixLabs-dev — Fri, 03 Apr 2026 08:44:45 +0000

Building in public means being honest about mistakes. Here's one I made with Prompt Helix and how I fixed it in v1.0.2.

Prompt Helix is a Chrome extension that extracts webpage content and sends it directly to your chosen AI. No copy-pasting. No tab switching. Click, ask, get an answer in context. I launched it in February and have been iterating since.

The mistake I made with the free tier.

When I launched I gave away too much for free. OpenAI and Claude completely free with no daily caps. It felt generous and user-friendly. In reality it meant there was no reason to ever create an account or pay. Someone could install it and use it every day forever without seeing a single upgrade prompt. Classic freemium mistake.

I only realised this when I looked at my Clerk dashboard and saw 60 installs but only 1 real signed up user. The extension works fine without an account. So nobody signed up.

What I shipped in v1.0.2.

Daily query limit of 25 for free users. This is the goldilocks number — casual users will never hit it, but someone using the extension as part of their daily workflow will within a week or two. When they hit it they see a friendly message and an upgrade prompt. That's the conversion moment that didn't exist before.

Usage counter shown subtly in the UI. Free users see "X queries remaining today" which turns amber at 10 and red at 5. Transparent, not aggressive. It creates awareness without being annoying.

Key Points moved to the free tier with a 5 per day cap. Previously it was Pro only. Moving it to free with a cap lets people experience the value before hitting a wall. That's a better conversion path than hiding it behind a paywall entirely.

Friendly restricted page message. Previously if you opened the extension on a Chrome Web Store page or new tab it would fail silently. New users thought it was broken and uninstalled. Now it shows "Prompt Helix can't read this page. Navigate to any website and try again." Simple fix, stops unnecessary uninstalls.

First time onboarding screen. Shows once on first install, explains the value before anything else, never shows again. Should improve the install to signup conversion rate.

What I learned from this update?

Freemium only works if there's a genuine wall somewhere. Generous free tiers feel good to build but kill conversion. The wall has to be real enough that power users hit it but gentle enough that casual users never feel restricted.

Silent failures are uninstall triggers. One confusing moment on first use and the extension is gone. Every edge case needs a human message not a blank screen.

Shipping beats perfecting. V1.0.2 still doesn't have PDF support or better extraction for Google Docs. Those are on the roadmap. But the conversion mechanics had to ship first because without them none of the other improvements matter.

If you're building a freemium Chrome extension I'd love to know how you approached the free to paid conversion. What's your query limit or usage cap equivalent?

ANY QUESTIONS OR COMMENTS ABOUT PROMPT HELIX PLEASE ASK. I READ ALL COMMENTS TO MY POSTS. HELP ME HELP YOU. HELIXLABS IS FOR THE COMMUNITY. FOR THE AI WORLD.

Check out Prompt Helix: chromewebstore.google.com/detail/prompt-helix/ffjppocigpeamhokbpnknlplkbccjpin

Website: helixlabs.studio

I built my first Chrome extension as a CS student. Here's what actually surprised me.

HelixLabs-dev — Tue, 24 Mar 2026 15:06:09 +0000

I've been building web apps for a while. I thought a Chrome extension would be a weekend project.

It was not a weekend project.

I'm a CS student and I recently shipped Prompt Helix — a page-aware AI assistant that sits on any webpage. Building it taught me things that no tutorial really prepared me for. So here's the honest version.
Manifest V3 is a different world

If you're learning from tutorials, half of them are still using Manifest V2. The migration to V3 changed how background scripts work fundamentally service workers replace background pages, and service workers don't persist the way background pages did. This means you can't store state the way you're used to. I lost a solid few days figuring out why my extension kept losing context between actions.

If you're starting a Chrome extension today, go straight to the official V3 docs and ignore any tutorial older than 2023.

Content script isolation is genuinely weird
Your content script runs in the page's context but is isolated from the page's JavaScript. This sounds simple until you're trying to extract content from a dynamically rendered page and wondering why your script can see the DOM but not the data you actually want. Some pages load content after the initial render via JavaScript and your content script fires before that content exists. I handle this with truncation currently which isn't ideal but it works well enough for most pages.

Multi-provider API abstraction is harder than it sounds
Prompt Helix supports OpenAI, Anthropic, Gemini and Mistral. Each provider has different API structures, different error formats, different rate limiting behaviour, and different ways of handling streaming responses. Building a clean abstraction layer that handles all four consistently and fails gracefully took longer than the entire UI. If you're building something multi-provider, design the abstraction layer first before writing a single API call.

BYOK was the right call but adds complexity
I made the decision early to keep API keys local stored in Chrome's storage, never transmitted to my servers. This was the right privacy decision and users respond well to it. But it means every API call goes directly from the extension to the provider, which means error handling has to be airtight on the client side. There's no server layer to catch mistakes. Every edge case is the user's problem if you don't handle it properly.

The Chrome Web Store review process is opaque
You submit, you wait, you get approved or rejected with minimal explanation. I just got rejected last week for a privacy policy issue — my policy didn't explicitly cover the extension's data handling even though it covered the SaaS product. One extra section later and we're resubmitting. Build time into your launch plan for review cycles. Don't assume it's a rubber stamp.

What I'd tell myself at the start
Start with Manifest V3 documentation not tutorials. Design your abstraction layers before writing API calls. Handle errors like a paranoid person. Write your privacy policy to explicitly cover the extension not just your website. And accept that the Chrome Store review is a variable you can't fully control.

If you're thinking about building a Chrome extension, do it. It's a genuinely different development experience from web apps and the distribution through the Chrome Store. even with its quirks is real. People find your extension through search without you doing anything.
Happy to answer questions from anyone building their first extension. The rabbit holes are real but worth it.

Any reviews from the community will help me as a dev greatly, any support will help!!

HelixLabs-dev — Tue, 17 Mar 2026 11:15:58 +0000

I built a Chrome extension that eliminates copy-pasting into ChatGPT

HelixLabs-dev ・ Mar 12

#ai #chatgpt #productivity #showdev

I built a Chrome extension that eliminates copy-pasting into ChatGPT

HelixLabs-dev — Thu, 12 Mar 2026 21:22:18 +0000

You know this loop:

Find something online you want to ask AI about
Select all → Copy
Open new tab → ChatGPT
Paste → Ask question
Switch back

I did this hundreds of times before I finally built the fix.

Prompt Helix is a Chrome extension that puts an AI assistant
directly on whatever page you're reading. Click the extension,
ask your question or pick a built-in intent (Summary, ELI5,
Fun Fact), and it sends the page content to your AI of choice
and answers right there.

What makes it different

Works with OpenAI, Claude, Gemini and Mistral
You bring your own API key — stays local in your browser
Free tier with no daily caps
Hallucination prevention and confidence scoring built in

The build

Built this solo — Chrome extension plus full SaaS backend,
auth system, subscription management, and website
(helixlabs.studio). Few months of evenings.

Already getting organic installs from Chrome Store search
before any promotion which was a nice signal.

Would love feedback from other devs — what would make
you actually install this?

Umbrella company -> helixlabs.studio

Chrome Web Store link