RONTGEN

Update for those following the RONTGEN build.

Quick background: I'm a radiologist from Brazil, and I started RONTGEN because of a daily frustration nobody warns you about in this job — the report takes longer to write than the study takes to read. Reading the images was never the bottleneck; turning what I see into a clean, structured, signable paragraph is. Multiply that across a worklist and the documentation is the job.

The software that's supposed to help — PowerScribe, Dragon — is genuinely good. But it's hospital software: priced per radiologist per year (a number that only makes sense for a whole department), wired into the PACS, gated behind IT, and tied to one workstation. The moment you're on a locum shift, moonlighting, or doing teleradiology from home, you're back to copying templates off Google Drive or a pen drive.

So I wrote an honest guide to what "dictating reports with AI" actually means in 2026 — and where a tool like RONTGEN fits. The thesis: for the authoring part of reporting, a modern AI editor can replace that hospital software instead of sitting beside it. In practice:

→ Voice-to-text with a personal dictionary — add an eponym or drug name once and it stops getting it wrong, on every machine. → Agent pipelines that apply your template and house style in one pass — define it once, run it on every report. → A copilot for the impression — draft from your findings, or get a second opinion / alternative wording from a different model. → Every major model in one place — and if one's ever down, priced out, or restricted, you switch without rebuilding anything. → Optional local, private models (Ollama) for sensitive text — nothing leaves your machine. → A fraction of enterprise pricing — a small monthly plan plus credit packs that scale with how much you use, or your own API keys at cost.

The honest boundary (candor is the whole point with this audience): RONTGEN is the authoring layer, not the hospital's records system. It doesn't reach into PACS to pull images or push the signed report into the hospital DB — you deliver the finished report into whatever system the site uses. You stay the radiologist; the AI handles the slow part, the writing.

Now the part IH might care about more — the meta. This post is piece #1 of a content experiment. My funnel diagnosis is brutal: plenty of signups, but my organic traffic is ~100% brand search (people who already know the name). Basically zero discovery. So instead of more generic "AI writing tool" posts, I'm testing use-case / persona SEO: enter through one concrete persona (radiologists), speak their exact pain, and try to get found by people searching the problem — not my brand. Radiology is the wedge because it's the one niche I've actually validated, and it's my own domain so I can write it credibly.

Read the post: https://rontgen.app/blog/dictate-radiology-reports-with-ai.html

Two things I'd genuinely love input on:

1. If you've used use-case/persona SEO to drive real activation (not vanity traffic), what actually worked — and how long before it showed up?

2. For anyone who's sold into healthcare or other regulated niches: how did you handle the "this isn't a certified medical device" line without killing momentum?

I just published a blog post comparing RONTGEN (my product) with ChatGPT for writing workflows. Not as a takedown — ChatGPT is genuinely great for brainstorming and quick tasks. But for professional writing, the chatbot model has real limitations.

The TL;DR:

ChatGPT = conversational interface. You talk to it, it responds. Great for back-and-forth, bad for sustained document work.

RONTGEN = text editor with AI built in. You write in a rich-text editor, create custom AI agents, and chain them into workflows that process your text directly.

The comparison page breaks down the differences in detail — formatting, model selection, voice input, workflows, cost.

One feature I'm particularly proud of: you can select specific parts of your document and process just that selection with any agent. Need to translate one paragraph while keeping the rest? Select it, pick your agent, run. The rest stays untouched.

Read the full comparison: https://rontgen.app/blog/rontgen-vs-chatgpt.html

Would love feedback from the community — especially if you've built comparison/vs pages for your own products. Did they help with SEO?

Quick update on RONTGEN for those following along:

I just shipped the Library — a community space where users can share and import agents, templates, and shortcuts openly.

The idea came from my own experience. Every time I spent hours fine-tuning a prompt for radiology reports, I wished I could just share the whole configuration with a colleague instead of explaining step by step how to recreate it. And when I saw someone else's setup that worked well, I wanted to import it and adapt it — not start from scratch.

Most AI tools treat prompts like a black box. You use what's built in, but you never see how it works. I wanted the opposite: full transparency. When someone shares an agent in the Library, you can see everything — the model, the prompt, the parameters, the temperature. You learn from it, improve it, and share it back.

How it works:

→ Browse shared items from other users — search by keyword or filter by type (agent, template, shortcut) → Preview full details before importing — no hidden configs → Import with one click — it's yours to customize → Publish your own creations back to the community

I think the best AI workflows come from collaboration, not isolation. The Library is my attempt at building that into the product.

Would love to hear what you think — especially if you've tried building something similar in your own tools.

Try it free → https://rontgen.app

RONTGEN is now open for signups — AI writing tool with voice-to-text and custom agents Hey IH! Quick update: RONTGEN is now open for everyone — no invite code needed. For context: I'm a radiologist and solo founder from Brazil. I built RONTGEN to solve my own problem — dictating medical reports and having AI format them automatically. Stack: Next.js + Django + LangChain, built almost entirely with Claude Code as my AI coding partner. What's working: → Free tier with full editor access → Voice-to-text streaming transcription → Custom AI agent pipelines → Copilot with GPT, Claude, Gemini, DeepSeek → BYOK (bring your own API keys) Would love feedback from the community. What would you want from an AI writing tool? https://rontgen.app

Hey everyone! I'm Thiago, and I've been building RONTGEN — a rich text editor that integrates AI agents directly into your writing workflow.

What makes it different:

• Agent Pipelines — chain multiple AI steps (translate → review → format) in one click

• Voice Transcription — dictate and edit hands-free with multiple transcription providers

• BYOK (Bring Your Own Key) — use your own API keys from 10+ providers (OpenAI, Anthropic, Google, DeepSeek, etc.)

• Copilot Chat — AI assistant with full context of your document

It's currently in closed beta. Would love feedback from the community!

Check it out: https://rontgen.app