Freelancers using C++ in London

Freelancers using C++ in LondonFreelancers using C++ in London

Projects People

CGI & AI Pipeline Architect for VFX and Product Teams

New to Contra

CGI & AI Pipeline Architect for VFX and Product Teams

Cover image for Supernova, a modern compositing Open Source

Supernova, a modern compositing Open Source

0

16

Cover image for Creating Realism: A normal weekend in London

Creating Realism: A normal weekend in London

0

13

Cover image for Project: RealFoodRitual - Visual Development

Project: RealFoodRitual - Visual Development

0

235

Cover image for AFTER CHRISTMAS is a 30-second

AFTER CHRISTMAS is a 30-second one-take AI short film created for the CapCut Seedance 2.5 Video Challenge. The film explores how a seemingly ordinary Christmas night can gradually become unsettling, told entirely through a single continuous camera movement. The challenge was to maintain spatial, character and prop continuity throughout the entire shot while allowing the camera to naturally discover the story. No cuts. No dissolves. No camera resets. Written & "Directed" by Leonardo Bruni Created with CapCut Video Studio + Seedance 2.5.

9

24

1.1K

AI Product Engineer | Building Production Ready AI Apps

23: Followers

AI Product Engineer | Building Production Ready AI Apps

Cover image for 62% today. 100% is the

62% today. 100% is the goal. 🚀 I challenged myself to reach a 100% Discovery Score before the end of the month. That means showing up consistently, building in public, sharing what I learn, and creating value every day not chasing numbers. Every post is one step closer. What's one professional goal you're determined to achieve before this month ends?

13

12

479

Cover image for I’m not just building a

I’m not just building a poker UI. I’m building a system that can understand the table. This project started with a simple idea: Can software look at a poker table and turn what it sees into structured game logic? The deeper I get into it, the more interesting the engineering becomes. The system has to deal with things like: → Card recognition — identifying cards from the screen → Board detection — understanding the current board state → Player positioning — determining where players are located → Action recognition — interpreting Fold, Call, and Raise → OCR — extracting information from visual elements → Coordinate mapping — knowing where important elements exist on different layouts → Game-state logic — turning all that visual information into something the application can actually understand And this is where AI-assisted development becomes powerful. I can use an AI coding agent to help investigate the codebase, implement changes, run tests, and work through bugs. But the outcome still depends on how I design the logic, test the edge cases, and verify what the system is actually seeing. The goal isn't: “Make AI write a poker application.” The goal is: “Build a system that can reliably understand what is happening on the table.” That's a completely different engineering problem. Right now I'm focused on making the recognition and game-state pipeline more reliable because one incorrect card, coordinate, or player action can affect everything that comes after it. Computer vision + AI + software engineering = some seriously interesting problems. 🧠🔥 What would you build with this kind of technology if you had reliable real-time visual recognition?

1

14

Cover image for AI can write the code.

AI can write the code. Engineering is knowing what to test. I’m currently working on a poker-vision system where the application needs to understand what is happening on the table — recognize cards, identify ranks, process board states, and translate visual information into usable application logic. And this project is teaching me something important about AI-assisted development. The difficult part isn't getting AI to change the code. The difficult part is proving that the change actually works. My current workflow looks more like: Read the codebase → Understand the existing logic → Make the change → Run the test suite → Inspect the real output → Find inconsistencies → Fix → Test again. For example, I’m currently testing multiple buyer frames against the recognition logic instead of assuming that one successful test means the system is correct. That's a big difference. A function can compile. A test can pass. The UI can render. And the system can still be wrong. That's why I don't want my AI workflow to be: “Generate the code and move on.” I want it to be: “Make the change, challenge the result, and verify the behavior.” This is becoming increasingly important as coding agents take on more implementation work. Modern agent workflows are already moving toward repository-wide investigation, automated tests, linting, code review, and validation rather than simply generating files. The GitHub Blog (https://github.blog/changelog/2026-03-18-configure-copilot-coding-agents-validation-tools/?utm_source=chatgpt.com) For me, AI isn't replacing the development process. It's changing where I spend my attention. Less time typing every line. More time understanding: What should happen? What actually happened? Why are they different? And how do I prove the fix is correct? That's where the interesting engineering work begins. 🔥 For developers building with AI agents: what do you trust more a passing test, the actual application behavior, or both?

1

34

Cover image for The hardest part of AI-assisted

The hardest part of AI-assisted development isn't generating code. It’s knowing when the code is wrong. I’m currently working on a poker-vision project where the system has to interpret what’s happening on the table — including card recognition, board ranks, hero cards, and positional coordinates. And this is exactly where AI-assisted development gets interesting. The agent can make a change. It can tell you the change looks correct. It can even run the code. But then you look at the actual result and realize: “Something is still wrong.” In this case, I was working through an OCR/ranking issue where the system was reading card information and producing an incorrect interpretation. So the workflow became: Inspect → Understand → Change → Run → Compare → Debug → Verify. Not: Prompt → Generate → Ship. That difference matters. AI coding agents are increasingly capable of working across repositories, editing multiple files, running tools and debugging issues. But current engineering discussions increasingly focus on the verification layer making sure generated changes actually produce the intended behavior. CodeRabbit (https://www.coderabbit.ai/guides/coding-agent-workflow?utm_source=chatgpt.com) For me, this is changing how I think about development. The value isn't just how quickly I can generate code. It’s how well I can understand the system, identify the real problem, direct the agent, and verify the final result. That's where engineering judgment still matters. And honestly, some of the best lessons come from the bugs that refuse to disappear after the first fix. 🔥 Developers using AI: what's one bug that looked “fixed” until you tested the actual behavior?

0

25

Your value driven Software Engineer

Your value driven Software Engineer

Cover image for Midicircuit

0

15

Cover image for Babylon Health

0

18

Cover image for Christies

0

9

Cover image for Etermar

0

20

Fullstack React/C# Industry Expert

Fullstack React/C# Industry Expert

Cover image for Options Pricer C++

Options Pricer C++

0

22

Cover image for Advanced Trading Analytics Platform

Advanced Trading Analytics Platform

0

19

Cover image for SOLID Principles

SOLID Principles

0

21

Placeholder project card media

View more →

All-in-One Expert Software & Hardware Developer

All-in-One Expert Software & Hardware Developer

Cover image for Industrial Omnidirectional Autonomous Robot

Industrial Omnidirectional Autonomous Robot

0

17

Cover image for GUI for Industrial Machine

GUI for Industrial Machine

0

21

Cover image for Medical Device Concept Render

Medical Device Concept Render

0

16

Placeholder project card media

View more →