DEV Community: Mohammed E. MEZERREG

Eisen Flow: Yet Another To-Do App But Better

Mohammed E. MEZERREG — Sun, 15 Feb 2026 11:41:23 +0000

This is a submission for the GitHub Copilot CLI Challenge

What I Built

This is an idea I got since I was working with my previous employer. We were using Jira for managing projects. In parallel of Jira I used Toggl, Trello, Clockify and even the Pomofocus timer.

I used these tools both through web and mobile. None of them satisfied me. I am not saying they're bad, but they didn't have what I was looking for.

I took this challenge to test a concept of my idea and see if people like it and why not win the challenge :) .

The idea revolve around implementing the Eisenhower matrix in a task or to-do list app. I didn't have the time to implement everything. But the MVP of the app is here.

Demo

You can check the app here.

My Experience with GitHub Copilot CLI

I used Copilot CLI for everything. I only used NeoVim to change some lines every now and then. You can say I developed this project through prompting Copilot CLI (Haiku, Sonnet, and Opus) 98% of the time.
I started with a free plan with Haiku. After three sessions I think I hit the limit and I was asked to wait until March. Since I have to finish the MVP and share it here. I was obliged to go buy a month of the pro plan.

Since then, I selected Opus and went through the rest of the plan finished it in one set. Then I added more features to implement to the plan and gave Copilot all permissions in the project's folder.

I changed the direction for this app two times and the agent never failed me. It even remembered removed changes even though I wasn't in a git repository! I don't know how is that possible to be honest.

i discover that I Copilot is more mature than ever. It has everything other tools have. It has skills, plan, MCPs, and so on. The funny thing is me starting a new session every time I start my machine. To my surprise they have a continue/resume command as well. So for the last three days I used

/session rename eisenflow

to rename the last session for this app. Then every time I want to work on this project I just use:

copilot --continue

This when I am sure that I didn't use Copilot for something else. It resumes the last opened session.
To select a session or provide the ID of a session I use:

copilot --resume # A list will show and I select my session.
copilot --resume session-id # I never used it

This really helped and gave me a GUI vibe. It's similar to selecting an existing thread from Antigravity, Cursor, etc. Or select a chat from ChatGPT, Claude, etc.

Some Usage Stats

Sessions by log size

Feb 12 — 132 KB / 1,550 lines (Pomodoro + Task UX)
Feb 3 — 104 KB / 1,228 lines (Core app build)
Feb 10 — 84 KB / 969 lines (Feature sprint)
Feb 2 — 80 KB / 898 lines (Scaffolding)

🤖 AI Model Requests

Date	Model Requests
Feb 1	0 (setup only)
Feb 2	244
Feb 3	346
Feb 8 (AM)	33
Feb 8 (PM)	29
Feb 10	288
Feb 12	464 ← heaviest
Feb 13	10
Total	1,414 model requests

📐 Context Window

Metric	Value
Context windows used	128K tokens (primary), 90K tokens (sub-agents)
Peak utilization	80% (~102K/128K tokens) on Feb 10 & 12
Compactions triggered	0 (never hit threshold)

🕵️ Sub-Agent Usage

Type	Count
Explore agents	3 (all on Feb 12)
Task agents	0
General-purpose agents	0

⏱️ Session Durations

Date	Duration
Feb 1	22 min
Feb 2	4h 15m
Feb 3–5	~50h (long-running session)
Feb 8 (AM)	12h 9m
Feb 8 (PM)	12 min
Feb 10	11h 9m
Feb 12	19h 15m
Feb 13 - 15	38h 36m 38.398s
Total	~136 hours of session time

💬 Prompt & Turn Counts

Metric	Count
User prompts	91
Assistant turns	1,406 (~15.5 turns per prompt)
Tool executions	1,563
Context compactions	8

🧠 Model Usage

Model	Role	Calls Logged
Claude Opus 4.6	Primary model (premium ⭐)	~1,414 requests (main agent)
Claude Haiku 4.5	Sub-agent (explore/task)	55 calls
Claude Sonnet 4.5	Sub-agent (general-purpose)	2 calls

⚠️ Quota Issues

Date	Event
Feb 8	10 quota exceeded errors ("You have no quota")

📊 Estimated Premium Requests

Source	Est. Count
Main agent (Opus)	~1,414
Sub-agents (Haiku/Sonnet)	~57 (non-premium)
Total premium requests	~1,414

Well toward the end GitHub Copilot CLI advised me to use general purpose models as he refers to Haiku and Sonnet to save on premium models requests like Opus. I took his advise and worked with Sonnet for quite a bit after that.

Tech Stack

The stack used in this project is:

React/Vite with TypeScript of course.
Convex for DB, Auth and so on.
Cloudflare Workers for hosting.

A Portfolio For Fun!

Mohammed E. MEZERREG — Sun, 01 Feb 2026 18:12:01 +0000

This is a submission for the New Year, New You Portfolio Challenge Presented by Google AI

About Me

I am the founder of تقن - Ta9in. This is the title I go with these days. I worked as a developer for ten years before deciding to start my own company, Ta9in, where we focus on bring the next generation of bright problem solver through apprenticeship and real life work that help us and our clients.

Portfolio

You can visit the app from here to get a better experience.

How I Built It

I started with Antigravity which is the editor of choice these days for me. However, even though I have pro subscription I hit the limits so quickly. I tried to build an RPG game-ish experience. It didn't work so well because of the arts and stuff. So I abandoned this idea.

To use an AI assistant without limits, I typically work in AI Studio. This project was made with it. I searched for game UI in Pinterest and chose one I liked. I passed it to AI Studio and gave him a prompt basically saying: "Create a game-like pixel art card interface for portfolio showcase. It's about a developer/artist going in a journey from studying in college to..."

Gemini is bright when it comes to playing words based on my experience. So the prompt was altered but it did a great job from the get go. The game theme was already there. The only thing I needed is to polish some styling and provide data about myself.

It took me 22 prompts varying from data updates, fixing bugs, fixing styling issues, to prompts suggested by AI Studio to get this result.

The best part is how Gemini twisted the description I gave and blend it into the game theme.

What I'm Most Proud Of

The main challenge in creating this website is the game-ish styling. It's absurd to make it myself without leaving my actual work and focus for at least a weak to craft the style. However, with AI I tested different styles in day and chose what hit closer to my goal. So the biggest decision is to bootstrap things and brainstorm with the help of AI. That's what I teach our new employees. Embrace the power of AI and integrate it in your thinking workflow.

The website is plain simple when it comes to architecture. It doesn't really need something complex. Just a one page static page like the old WWW. Yes it uses React underneath to handle interactions. But in reality it's just a simple page with static content. I tried to add some Nano Banana Generation power. But it's not that obvious and you have to spot it. I did it on purpose to keep my balance protected :). In general that's what I think how a personal website should be. Hence my plain personal website.

Since I used AI Studio it goes directly to React/TypeScript (selected by default).

Ideas for Future Versions

The idea is to have an old gaming console in a room with some games' cards on a table. The user would drag one and put it in the card slot. Then power on the gaming console.

The view zoom in the screen (transition view) and load the game view (another page). Each card will use a different version of my own portfolio and go with the user through the history of my website. That's the main idea and I might work on it if I have time.

Image Flow Editor

Mohammed E. MEZERREG — Sun, 28 Sep 2025 22:51:32 +0000

This is a submission for the KendoReact Free Components Challenge.

What I Built

I am not a designer nor an image editor. However, I find myself going to Google every now and then, searching on background remover, light enhancing, etc. I go to Figma as well to add some effects, or apply masks or whatever.

As a casual image editor, I need what works right a way with the fewest clicks possible. I am not willing to invest my time on learning something I need few times a month.

Figma is great. However, when any tool start to get traction. The team behind it start to seek growth and domination. Figma and Canvas started as simple tools that do one or two things. Now, they require a learning curve to achieve things.

These days, I find myself going to Excalidraw to be honest to draw my creatives for posts or what not. Why? I believe on the saying: "With greater power comes greater responsibilities." Apply to this field and it becomes: "With more options, comes more distractions." For a simple remove background task and add stroke to make stump like. You start exploring the never ending plugins ecosystem searching for one who does both tasks. A task of three minutes max turns to a full day of trying different options, signing to countless services for an API key. Of course, days after that, you still didn't edit your image and forget about the project all over.

The Concept

I imagine myself as the main end user:

I can upload multiple images.
Add some tasks or editing flow as drag and drop.
Hit compile or run.
Get the result files (preview, download, download all).

It should be as simple as it was described.

Demo

Demo Video:

You can test the app from these two domains:

You can also find the repository for this project here.

KendoReact Components Used

The components used in this project are:

kendo-react-common
kendo-react-intl
kendo-react-buttons
kendo-react-inputs
kendo-react-dropdowns
kendo-react-dialogs
kendo-react-notification
kendo-react-indicators
kendo-react-animation
kendo-popup-common
kendo-react-popup
kendo-react-layout
kendo-react-labels
kendo-react-data-tools
kendo-react-charts
kendo-react-grid

Assistant Usage

I don't have much time for the challenge. Even though I have ten years of experience with the Kendo UI and Telerik. I mainly used jQuery version for dashboard related work. Still, five days is not enough time for me to come with an idea, code it and write about it while doing my work.

Since the trend this year is all around Vibe Coding, Coding Assistants, Agents, AI Editors. Why not go this road and Vibe Code my idea for this challenge?

I tried a couple of these Vibe Coding platforms before. However, the main problem I usually face is their limitations. Meaning, if you let the agent code the way it knows how. It will give you working prototypes fast and almost perfect. However, when you ask them to use a certain library or framework, they struggle with that and only bring you blood pressure up.

So, I started with Google AI Studio Build. It proved itself as reliable when it comes to using libraries with React and Angular. However, this time it wasn't efficient. It kept showing errors that it couldn't fix. I even deleted the project and started from scratch. The Kendo MCP configuration doesn't seem to work at first in this environment neither.

So, I downloaded the code base and opened my ZED editor. I configured the Kendo MCP and started prompting.

The first iteration was easy. I prompted Zed to fix the issues. It did very quickly. The problem was in importing react in multiple places from different CDNs. I updated the AI Studio code base and it worked.

Later on, things started to get very nasty. Both Zed & Ai Studio were needed for different tasks. I tried to stop using AI Studio, but the API key calls from my local version kept preventing me from doing anything claiming that I exceeded the limits or whatever.

At the end, I continued on AI Studio. I added the Kendo MCP configuration in its settings. Luckily for me, it started using it to access the latest documentation and recognizes my prompts with ease. It even fixed an issue related to license while using a premium feature of the dropdown component. Same happened with the button at certain point. I wonder if the MCP can pinpoint the paid features in free components without making a mistake and I had to point to it. Of course, I didn't point to the component causing the issue. I only gave my feedback about the licensing strips showing in the dialog form.

Adding more features

I have to say. I never felt cold adding a feature like in this project. The AI Studio ruined my app two times while adding a simple button. It's unfortunate that the GitHub integration isn't working correctly. So I had to download a version every now and then.

Dashboard

Let's be honest. Kendo UI shines in dashboards. In my previous job, we decided to buy it because of how straightforward building dashboards was with the Data Grid, Charts, Editors and so on.

After the first prompt about the dashboard. I confirmed all my fears. It crashed and I had to track errors and fix them. The same error keeps happening whenever I add a new component. Ai Studio uses ESM CDN for its packages management. The problem in versioning. So I had to check the right version for each component or package.

Licensing

I was hoping to use the tiling layout and the data grid components. Unfortunately,the little I am doing with them shows the licensing strips. So I removed them all together.

Deployment

Even though I prefer Cloudflare these days. I chose Vercel to host this project. However, to deploy it outside of AI Studio I have to do some changes.

The first thing I did was removing adding a new option for the user to add his own Gemini API KEY. This way, anyone can use the app without me worrying about credits and so on. Of course, this will change if the app gets to a certain point.

Once again, I used only free components. However, the dialog for the API configuration shows the license strips!!! I was confused, so I prompted Claude in Zed to use the MCP and investigate the issue. Unfortunately, the investigation didn't lead to a good result. Since Claude went and deleted the Kendo theme and did other unnecessary stuff. Then he went out of service because I exceeded the limit of using it.

I switched the model to ChatGPT 5 mini through GitHub Copilot and prompted:

in the @ApiKeyConfig.tsx file there something that make Kendo add the license strips. Please use the kendo react mcp to investiage this. Don't do anything until you ask

This model did a better job with the Kendo MCP. It asked for a list of all premium components. Then it asked for free components with premium features. Compiled a plan for me on how to fix the issue. After executing the plan the license strips gone.

Plans

I started this project for fun. After spending almost five days working on it. I am planning to continue enhancing it to see how it turns out. I added a todo list to the README file of this project. But that's just the starting point. But first, let's see how it perform in this challenge.

How to Host Hugo in Vercel

Mohammed E. MEZERREG — Thu, 28 Nov 2024 10:30:55 +0000

I decided to go with Hugo to build my personal website. The only thing I based my choice on was the build time. I thought Hugo was in the same league as Astro when it comes to content management perks, but it isn't quite there yet. Or, I can say it has its own path since it's older than most of the other static site generators I've encountered. Moreover, it's a Go application, which is another important factor to consider when evaluating technology choices.

What Can Be Added!

Yes, it's possible to extend Hugo's functionality. You can add missing features through modules that modify the build process. For example, I was missing MDX support in Hugo. I can address this through a module that renders MDX at build time. I haven't tried it myself, but it seems possible.
I can also potentially add a parallel building pipeline—if we can call it that. This might involve using tools like Vite, Turbo, or Webpack. However, this approach would likely complicate the build process and potentially slow down Hugo's main building mechanism. These integrations have been used to incorporate Tailwind and other frontend libraries. Interestingly, if you look at Hugo's upcoming features, you'll see plans for integrating Tailwind and other technologies.

Building on Vercel

I used some third-party Hugo tools, specifically HugoMods. The icons module caught my attention because I wanted to add icons to my website without importing an entire font. While searching, the Icons module was the first thing that appeared. It offers a variety of icon vendors, including Bootstrap, Font Awesome, Feather icons, and more.
Locally, everything worked perfectly. However, after pushing my changes, nothing seemed to change. Upon checking the build page in Vercel, I noticed...

[12:10:48.021] Running build in Washington, D.C., USA (East) – iad1
[12:10:48.210] Cloning github.com/mohessaid/mohessaid (Branch: main, Commit: eaeecd1)
[12:10:48.449] Cloning completed: 238.727ms
[12:10:49.038] Restored build cache from previous deployment (5i5sCdjnY3KZXgGBqbqfgJUjrwYB)
[12:10:49.132] Running "vercel build"
[12:10:49.714] Vercel CLI 39.0.2
[12:10:50.440] Total in 3 ms
[12:10:50.441] Error: failed to load modules: failed to download modules: binary with name "go" not found in PATH
[12:10:50.446] Error: Command "hugo --gc" exited with 1
[12:10:50.625]

When Hugo attempted to install the modules needed for the build, it couldn't find the Go binaries. I sought help from Claude and GPT, hoping for a quick solution, but they were unable to provide direct assistance. I had to guide them through each step, and eventually, I lost hope in their ability to help me.
I had even used Claude for a solution that was nearly successful, if not for the limitations in the Vercel input fields.

What Worked?

I navigated to the settings page of my website in the Vercel dashboard. In the "Environment Variables" tab, I added a variable named "HUGO_VERSION" and set its value to the latest available version of Hugo.

In the "General" tab, select Hugo as the framework preset. Then override the build command with the following:

curl -L https://go.dev/dl/go1.22.2.linux-amd64.tar.gz -o go1.22.2.linux-amd64.tar.gz && tar -C /usr/local -xzf go1.22.2.linux-amd64.tar.gz && export PATH=$PATH:/usr/local/go/bin && go env GOTPATH  &&  hugo --gc --minify

Note: I'm using Go version 1.22.2, which is the latest at the time of writing. You can modify the version to match your specific requirements.

Why Build Command?

I understand your skepticism. Like you, I thought I had a clever solution. Initially, I attempted to install Go in the Install Command field, but it failed miserably. Vercel's build process couldn't locate the binaries, despite my exhaustive troubleshooting.
After exploring countless potential solutions without success, I stumbled upon a GitHub issue where someone had placed their entire installation process directly in the build field. Replicating their approach, I finally achieved success. At this point, the solution speaks for itself.
Attempting to place these steps in the install command field will likely result in errors.

Or this one

Installing Amazon Linux Extras won't solve the Go installation challenge. The version of Go available through this method is significantly outdated. I tested this approach thoroughly and encountered consistent failures. I attempted to use both yum and dnf package managers in the install command, but neither method successfully resolved the Go binary issue.

Finally, I shared this post across different platforms to test which one of them get first in search results. I was willing to do this months ago. However, I couldn't the right post for it. You can follow the experiment from here.