DEV Community: A-K

Day 2: We're Not Giving Up. 🏃‍♂️

A-K — Tue, 03 Nov 2026 01:06:33 +0000

As developers, we spend a lot of time behind screens — writing code, debugging, learning new technologies and building projects.

But I wanted to challenge myself outside the screen too.

So, I started running.

Day 1: 3.16 km | 6:37/km

Day 2: 2.26 km | 6:33/km

Two days might not sound like much, but everyone starts somewhere.

Today's run was shorter, but I managed to improve my pace slightly. And honestly, that's enough motivation to keep going.

I'm not trying to become a professional athlete overnight. I just want to build discipline, stay consistent and become better physically and mentally.

Coding teaches us to be patient with progress. Running is teaching me the same thing.

There will be difficult days, slower runs and days when motivation is missing.

But we're showing up anyway.

This is just Day 2. The journey is far from over.

One step at a time. One day at a time. 🚀

We're not giving up.

How Building an AI Pitch Deck App Made Me Realize How Much I Need Voice Dictation

A-K — Sun, 25 Oct 2026 17:45:30 +0000

Starting my build session late today brought a sudden wave of panic when I realized my Wispr Flow free subscription had officially ended. Building VoxDeck over the last few days had become so seamlessly tied to speaking at 125 WPM across 21 different apps—racking up over 20,000 dictated words[cite: 15]—that going back to a standard keyboard felt like typing through wet cement. Without that lightning-fast voice dictation, my inner friction returned instantly, showing me just how deeply a great tool transforms the developer workflow. It really made me appreciate how much faster raw thought translates into code when your hands aren't locked to a mechanical keyboard. If you've been relying on voice-first tools to crush your building goals, hitting that subscription wall is a harsh reminder of how indispensable they become to your daily routine.

🚀 What is VoxDeck?

VoxDeck is an AI-powered voice-to-deck engine built on Next.js 15 and Google Gemini. Instead of forcing founders to type out rigid bullet points or struggle with a blank screen, VoxDeck takes a raw voice brain-dump and instantly structures it into:

A 10-Slide YC Narrative Deck
An Executive Overview
A 60-Second Spoken Pitch Script
A TAM / Business Model Breakdown
Dedicated About Us & FAQ Sections

📊 The Stats That Powered the Build

Before my free tier wrapped up, my Wispr Flow highlights captured a wild ride:

20,048 Words Dictated.
125 Words Per Minute Average Speed.
21 Different Apps Used.

Hitting 125 WPM meant my voice was operating nearly three times faster than my average typing speed. Being able to "brain-dump" architectural layouts, prompt logic, and documentation vocally while my hands focused entirely on writing clean code completely changed my shipping velocity.

🛠️ The Tech Stack

Framework: Next.js 15 (App Router)
AI Integration: Google Gemini API (GEMINI_API_KEY) for rapid unstructured text parsing
Voice Dictation: Wispr Flow (supporting multi-language brain-dumps in English, Punjabi, Marathi, Tamil, and Japanese)
Deployment: Vercel (Production serverless deployment)

🎯 Final Thoughts

Building VoxDeck taught me that the true bottleneck of software development isn't thinking or coding—it's translation speed. Going back to manual typing today made me realize how spoiled I got dictating over 20k words[cite: 15].

If you haven't tried pairing your development workflow with high-speed voice dictation, check out your own stats and see how much faster you can ship. Let me know your thoughts in the comments below! 👇

GraphHacks Hackathon Wrap Up

A-K — Mon, 19 Oct 2026 16:35:13 +0000

Just wrapped up my GraphHacks experience! 🚀

I participated in the hackathon, worked on my project, and submitted it.

One thing I'm realizing as I explore AI and build projects is that having an idea is only the beginning. Turning it into something functional, making decisions under time pressure, and figuring things out when they don't go as planned are challenges of their own.

This experience gave me another opportunity to learn by doing rather than just learning concepts in theory.

As a CSE student, I'm still figuring things out, experimenting with new tools, and trying to become better at building things from scratch.

There's definitely more to learn, but that's part of the journey.

One more experience added. On to the next! 👨‍💻

GraphHacks #Hackathon #AI #BuildInPublic #StudentDeveloper

How I Built ALIBI GRAPH: My Solo Journey Building a Multi-Agent Cyber-Forensics Lie Detector

A-K — Sun, 18 Oct 2026 13:16:40 +0000

Project Concept & Core Goal: Built ALIBI GRAPH, a solo-developed multi-agent cyber-forensics tool designed to catch liars by automatically cross-examining suspect alibis against surveillance evidence and interrogation logs.

Building a hackathon project completely solo is always a chaotic rush,

Why I Made It

I wanted to solve the absolute nightmare of manual forensic analysis. When detectives have to sift through multi-page interrogation notes, vehicle tracking logs, and security footage, it takes hours to spot a lie. I wanted an AI app that could ingest these raw case files, map out the relationships, and instantly flag when a suspect's alibi falls apart.

How I Put It Together (The Real Tech Stack)

The Frontend: I used Streamlit to build out the interface because it let me spin up custom pages, file upload bays, and live terminal views super fast.
The Multi-Agent Pipeline: I split the logic into two main agents:
Agent 1 handles the dirty work of ingesting raw text evidence files, pulling out suspect names, and parsing out semantic topics.
Agent 2 acts as the cross-examiner, looking at the suspect's claims and matching them against physical evidence and surveillance timestamps.
The Database & API Setup: I used FalkorDB Cloud as the graph memory layer. Instead of dumping everything into a flat database where context gets lost, I needed a way to store suspects, evidence exhibits, and claims as nodes so I could run Cypher queries and map everything out in real-time.

The Real Struggles (Developer API Problems & Late-Night Coding)

Let's be honest—dealing with developer API problems, handling rate limits, and getting multi-agent loops to talk smoothly to a cloud database completely by myself under hackathon pressure was brutal. I ran into plenty of annoying connection drops, local server hiccups, and sudden Streamlit crashes right when I was trying to record. Trying to format Cypher queries dynamically while an agent is streaming data and wrestling with cloud configuration can drive you crazy at 3 AM.

But seeing it all finally click—dropping in a file for a suspect like Jordan or Morgan(Imaginary Entities considered only for projects), watching the live graph nodes stream in, and seeing those red contradiction edges light up on the visual canvas—made all the debugging completely worth it.

If you're building agentic apps with complex relational data as a solo dev, graph databases are awesome once you tame them. Check out my GitHub and demo video to see how it turned out!

Introduction

A-K — Sun, 18 Oct 2026 11:25:46 +0000

Hello, Dev.to community! 👋

After spending a long time reading incredible articles on this platform, I have finally decided to step out of my comfort zone and start sharing my own tech journey.

Who Am I?

I am a software student passionate about [ Python, Frontend Web Development, Open Source].

Why Am I Blogging?

I believe that the best way to solidify your own understanding of a concept is to explain it to someone else. Through this blog, I want to:
Document my learning process as I tackle new technologies.
Share quick fixes for bugs or errors that took me hours to figure out.
Connect with other developers in the community.

Let's Connect!

I would love to meet fellow developers!