I m working on TabyDial, a browser-based SIP softphone for making and receiving calls with an existing SIP account.

The idea is simple: make business calling easier without requiring a traditional desktop softphone.

With TabyDial, users can:

• Connect an existing SIP account

• Make and receive calls directly in Chrome

• Keep calls active while switching tabs

• Continue calls while Chrome is minimized

• Work in other applications without interrupting the call

• Use WebRTC calling without changing their current VoIP provider or PBX

Hey

15 years of watching teams ship the wrong thing because the spec wasn't clear. Then Cursor and Claude Code arrived and made it worse coding agents can't fill gaps the way a senior engineer can.

So I built Outlain. Drop in customer research (transcripts, recordings, support tickets). The AI extracts themes, ranks them by severity, and generates a complete spec Jira tickets, acceptance criteria in Given/When/Then, and an agent-ready prompt block for Cursor or Claude Code. Every line traces back to a real customer quote.

Two modes:

I kept opening an AI chat just to fix one awkward sentence, then copying the result back. So I built Polish, a Chrome extension that fixes selected text inside the editor you are already using.

Select a sentence, use the shortcut, and the corrected text replaces it in place. It is designed for everyday web writing and keeps the original meaning and tone.

I am looking for desktop Chrome users who write in English at work. If that is you, please try one real sentence and tell me where the experience breaks.

Demo and install:

I'm building NeuroFlow, a local-first AI research workspace designed for researchers, PhD students, research assistants, and AI labs who want more control over their research infrastructure.

Today, researchers rely on a fragmented stack of cloud tools, AI assistants, PDFs, notebooks, and disconnected workflows. NeuroFlow is built around the idea that the future of AI research should not require sending sensitive data, unpublished findings, or proprietary research workflows to external platforms. Instead, researchers should be able to own their infrastructure, run models locally, and have complete control over their data, tools, and knowledge.

The goal is to bring the entire research workflow into one environment: searching millions of papers, building interactive knowledge graphs, analyzing research code, discovering connections across literature, identifying research gaps, and generating evidence-backed hypotheses.

The biggest challenge I'm solving is making AI systems that can reason over evidence rather than just generate convincing answers. In scientific research, a claim is only valuable if it can be traced back to the underlying evidence: a paper, dataset, experiment, or piece of code. NeuroFlow is focused on building transparent AI workflows where researchers can understand not only what the AI suggests, but the reasoning and evidence behind every conclusion.

Hey PH

Today is launch day for Sujova, and since this is the forum for showing what you're working on, here's mine and the story behind it.

Hi PH community! I m Utku, a 15-year-old student-founder. I ve realized that traditional study systems especially static PDFs are where focus and time go to die.

I ve spent my week vibe-coding to build izeo.app (@izeoapp), an ecosystem designed to kill the 'PDF Graveyard.' Based on my tests, here is how a rhythmic ecosystem outpaces the old way:

AI Flashcards (20x Faster): Manually creating cards takes hours. Our AI deconstructs documents into active-recall cards in seconds. Saving: ~50 mins per study session. Smart Flow vs. Scrolling (2x Faster): Static scrolling leads to passive reading. Smart Flow forces a rhythmic, interactive pace, doubling information absorption speed. Integrated Deep Work (3x Focus): Jumping between Pomodoro apps, Spotify, and task boards causes 'context switching' fatigue. Having them in one flow eliminates the 15-minute 'refocus' period. Streak & Gamification: Increases consistency by 40% by gamifying the boring parts of mastery.

Combined, this makes your study sessions 5x to 10x more efficient than the old-school PDF-and-highlighter method.

Stop scrolling on autopilot.

Ever opened Instagram "for just 2 minutes" and somehow lost an hour?

We've all done it.

INTENT isn't here to shame you or block your phone. It's here to help you pause, choose, and stay intentional.

a tool that turns complex medical research into simple, honest summaries.

The goal: help people actually understand what studies say (and don t say).

Still early would love feedback from anyone interested:

https://curecompass.app