Freelancers using Python in LondonFreelancers using Python in London
ProjectsPeople
Ali Shan's avatar
Ali Shan
proLondon, UK
Full-Stack & AI Dev | TypeScript, Next.js, React, Node
$25k+
Earned
5x
Hired
5.0
Rating
80
Followers
Full-Stack & AI Dev | TypeScript, Next.js, React, Node
Cover image for Langflow Multi-Agent Research Framework Development
Langflow Multi-Agent Research Framework Development
0
30
Cover image for Predictive Analytics Platform & ML Service
Predictive Analytics Platform & ML Service
0
15
Cover image for Backend Architecture for Text-to-Speech SaaS Platform
Backend Architecture for Text-to-Speech SaaS Platform
0
9
Cover image for Containerized Automated Quality Control Pipeline
Containerized Automated Quality Control Pipeline
0
6
Python(6)
Anesah Fraser's avatar
Anesah Fraser
London, UK
AI Agent & Automation Engineer | LangChain, Python, n8n, RAG
AI Agent & Automation Engineer | LangChain, Python, n8n, RAG
Cover image for Automated KPI Dashboard with Power BI
Automated KPI Dashboard with Power BI
1
4
Cover image for Ops Workflow Automation with Human Review
Ops Workflow Automation with Human Review
1
6
Cover image for Invoice Processing Automation Project
Invoice Processing Automation Project
1
5
Cover image for Automated Support Ticket Routing and Summarization
Automated Support Ticket Routing and Summarization
1
4
Python(5)
Ahtesham Hassan's avatar
Ahtesham Hassan
Dagenham, UK
AI Automation Engineer | n8n Claude & Python
New to Contra
AI Automation Engineer | n8n Claude & Python
Cover image for TriggerLeads — B2B AI Outreach Pipeline
TriggerLeads — B2B AI Outreach Pipeline
0
4
Cover image for AXON — Autonomous AI Operating System
AXON — Autonomous AI Operating System
0
5
Cover image for LumiGlow — eBay Automation System
LumiGlow — eBay Automation System
0
5
Cover image for airankchecker.uk — AI Visibility Audit
airankchecker.uk — AI Visibility Audit
0
4
Python(3)
Moyo Weke's avatar
Moyo Weke
proLondon, UK
Frontend Dev & Web Designer | Framer, Figma, Decks
$1k+
Earned
2x
Hired
5.0
Rating
13
Followers
Frontend Dev & Web Designer | Framer, Figma, Decks
Cover image for AI-Powered Skin Cancer Classification : Computer Vision
AI-Powered Skin Cancer Classification : Computer Vision
0
5
Cover image for Verlux E-commerce Web Design for Hospitality
Verlux E-commerce Web Design for Hospitality
0
4
Cover image for Kupa Global Website Redesign
Kupa Global Website Redesign
0
38
Cover image for Adluna: Productivity Platform UI/UX Design
Adluna: Productivity Platform UI/UX Design
1
52
Python(1)
Idris Lamina's avatar
Idris Lamina
proLondon, UK
AI Automation & Web Design | n8n · Vapi · Claude API
15
Followers
AI Automation & Web Design | n8n · Vapi · Claude API
Cover image for Designed and built a Clause
Designed and built a Clause Bank Builder for a 22-staff Malaysian conveyancing law firm as the foundation of their legal document automation system. The problem was not just generating documents. The firm needed a way to organise its legal knowledge first: approved wording, reusable clauses, transaction scenarios, placeholders, trigger rules, exclusions and version history. The tool gives the team a simple Windows interface to add, edit, browse and review clauses without touching code. Each clause can be categorised, marked as active or draft, linked to usage conditions, and exported for backup. This creates a structured legal knowledge base that can feed future SPA generators, tenancy agreements, letter templates, matter workflows and Microsoft 365/SharePoint automation. The aim was to keep the system practical for a real law office: offline, maintainable, plain-English, and easy for non-technical staff to understand.
2
192
Cover image for Veranda, a luxury residential concept
Veranda, a luxury residential concept landing page Veranda is a concept build I created for a fictional luxury residential brand. It is not client work or a real property. The images and hero motion were generated with AI as part of the creative process. I wanted to explore something that matters when building high-fidelity landing pages: after several rounds of changes, how do you make sure the final page still looks like the design that was approved? The site is built in Next.js with responsive layouts, self-hosted fonts, GSAP motion and an interactive walkthrough. I also built in a proper QA process around it, not just checking that the page loads and the buttons work. It compares 12 sections across five screen sizes against approved visual baselines. It flags visual drift, missing baselines and changes that have not been reviewed. I also tested interactions, accessibility, contrast, performance, browser behaviour and reduced-motion states. The main lesson for me was simple: a page can pass functional tests and still no longer be the page that was agreed.
22
26
1.1K
Cover image for Cinematic Portfolio Design for Film Studio: A Visual Masterp...
A cinematic portfolio concept for a film and motion studio, designed to feel more like an editorial reel than a standard agency website. The site uses a dark visual system, oversized typography, smooth scrolling, restrained motion, and a full-screen project index to make the work feel premium before the user reads a word. The focus was on pacing, atmosphere and confidence: fewer sections, stronger visuals, cleaner movement. Built as a responsive Next.js prototype with Framer Motion and Lenis-style smooth scrolling, including hero, selected work, about and contact sections.
7
12
496
Cover image for I built a working AI
I built a working AI recruitment screening demo that shows how a hiring team can use AI without handing over the final decision. The flow is simple: A job spec goes in. Candidate profiles are screened against a weighted guideline. Each candidate gets a score, band, evidence quotes, and risk flags. Then everything stops at a human review queue. No auto-rejects. No silent ATS updates. No “AI decided this person is out”. The system includes: Candidate pipeline table Evidence-based screening view Human review queue Approve / reject / snooze decisions ATS deployment plan Audit log for compliance n8n workflow export with a human-in-the-loop Wait node Optional live Claude screening path The important part is the architecture: deterministic logic owns the workflow, gating, state and audit trail. The AI helps with judgement and screening, but the human owns the final decision. Built with Next.js, TypeScript, Claude API, n8n workflow architecture, and a gated ATS sync pattern. This is the kind of system I like building: AI that makes the work faster, but still respects the places where people need control. Shorter Version I built an AI recruitment screening pipeline with a human approval gate. It screens candidates against a rubric, shows evidence quotes and risk flags, then routes every candidate into a review queue before anything reaches the ATS. No auto-rejects. No silent updates. Human-in-the-loop by design. Built with Next.js, TypeScript, Claude API and n8n workflow architecture.
1
140
Python(1)
Ashish Sandhu's avatar
Ashish Sandhu
London, UK
Fractional CTO / AI Specialist Award Winning AI Engineer
$5k+
Earned
7
Followers
Fractional CTO / AI Specialist Award Winning AI Engineer
Cover image for Development of Vulcan-OS: An AI Orchestration Layer
Development of Vulcan-OS: An AI Orchestration Layer
0
10
Cover image for I've spent the last few
I've spent the last few days building something I genuinely wish existed years ago. When I was job hunting, I had a PDF. A white rectangle with my name, dates, and bullet points. The same format invented in 1482. I was competing with thousands of people who had the exact same white rectangle. I'm a builder. I ship products. I've worked with real companies, shipped real things, have real skills. None of that showed in a CV. It couldn't. A PDF wasn't built to show it. And building a personal website? That's a project in itself. Design it, code it, host it, maintain it. Most people never do. So their career stays a white rectangle forever. So I built RoomCV. (https://roomcv.figma.site/) You don't build anything. You paste your LinkedIn URL, your Contra profile, or upload your CV. In under 60 seconds, your career has a home on the internet. A real one. With your name on the door. Not a template you fill in. Not a prettier PDF. A room that reads your data and builds itself with all your pretty links. And then there are the portraits. The AI photoshoot is unlike anything else in this space. It runs a 3-stage pipeline (thanks to Figma Weave): Stage 1 - A casting director model analyses your reference photo and writes a precise physical description. Hair, skin tone, bone structure, build. This becomes a consistency anchor so every portrait is recognisably you. Stage 2 - A photography director model reads your actual CV. Your job title, your company, your career highlights, your personal note. It writes a bespoke scene brief the way a Vogue photo director would. A founder gets a quiet boardroom at night with a city skyline. A developer gets a dark server room with terminal green glow. A designer gets mood boards and soft daylight. Stage 3 - The image model takes that bespoke brief, your reference photo, and your character anchor and generates 6 editorial portraits. Hero. At work. Thinking. Off duty. Achievement. Environmental. Every portrait is specific to you. Because the AI read their actual careers before picking up the camera. The room is alive. People can visit your room at its permanent URL. They can leave signed notes in your guestbook. They can react with rockets, fire, or lightbulbs. You can see who's browsing right now, live presence, like a real room. Every visit is counted. The whole city of rooms is browsable and is a directory of real people's careers, each one visually distinct. Three visual themes: Cinematic - moody contrast, 35mm grain, deep editorial shadows. Brutalist - harsh direct light, raw concrete textures, technical glitch aesthetic. Minimal - soft diffused window light, high-key, warm neutrals, conversion-focused. The copywriting changes completely per theme too. Same person, three radically different editorial voices. Wieden+Kennedy wrote none of them — Gemini did, with a prompt that bans every CV cliché and demands specific references to real company names, real project names, real skills. What I used to build it: Figma Make - the entire app. Every component, every interaction, every route. Built in natural language, iterated in real time. Figma Weave - the portrait pipeline visualised as a node-based workflow. The casting director, the photography director, the 6 parallel image generation nodes. The hero background video on the landing page. The logo. Figma MCP - connecting the design token system into the Make build so the three themes stayed consistent with the Figma source of truth. Supabase - backend, auth, KV storage, private portrait bucket, signed URLs, edge functions. Gemini - character extraction, photography direction, copywriting, profile parsing, room generation from raw LinkedIn/Contra/CV data. The numbers that matter: 60 seconds from paste to published room. 6 portraits per person, all unique. 3 complete design systems per room. 0 templates. Every room is generated, not filled in. 1 permanent URL per person. Unlimited visitors, reactions, guestbook notes. Who this is for: Designers who are tired of Behance looking like everyone else's Behance. Developers whose GitHub is invisible to anyone who isn't technical. Founders who have a LinkedIn but not a story. Freelancers on Contra who want their profile to stop at the URL and start in the room. Anyone who has ever felt like their career deserved better than a white rectangle. Yesterday a dev called Andrei pasted his LinkedIn URL. 30 seconds later he had six editorial portraits and a career room that looked like the cover of Wired. He sent me a voice note. He said it was the first time his career had felt like his, and here it is for everyone to try. Try it. Paste whatever you have. LinkedIn URL, Contra URL, raw CV text, PDF. Your room is waiting. roomcv.figma.site (http://roomcv.figma.site)Figma Make: https://www.figma.com/make/3kpbdErsXVZqPSkZS2LdvY/Design-RoomCV-Creatively?t=ZnnNnUei4aE16P6e-1 Figma Weave: https://app.weavy.ai/flow/RK8qIG0eKBpyoJLOg4JgrC Figma Community: https://www.figma.com/community/file/1649649240602428392/roomcv?fuid=1004476920505329686 X: https://x.com/AshishSandhu/status/2067821599223316662 (https://x.com/AshishSandhu/status/2067821599223316662?s=20)https://x.com/AshishSandhu/status/2067824940154269961 Drop your room link in the comments. I want to see every single one. Built for the Figma Config Makeathon. Figma Make + Figma Weave + Figma MCP + Supabase + Gemini. #ConfigMakeathon #Figma #FigmaMake #AI #Portfolio #CareerDesign
2
3
194
Cover image for Reinventing the wheel 🛞 for
Reinventing the wheel 🛞 for Google. Designed with Google Stitch for all platforms Desktop, Mobile, and Tablets. I’m a engineer and founder with tech experience but not design, and going into this challenge, my real question was simple: Can an AI-native interface builder actually handle deep-time narrative storytelling and high-fidelity, scroll-linked interactions without turning into a complete mess? To stress test the absolute limits of the platform, I didn't feed it an established design, or any files right away. I wanted to see exactly how Stitch thinks, handles design drift, and iterates from scratch. I gave it a massive, conceptually complex prompt: Build a highly cinematic, ultra-polished, deep-time historical timeline mapping the evolution of the wheel, from primitive Mesopotamian stone discs to active, computational morphing hub systems in 2026. How Stitch Fit into the Workflow The streaming generation on the canvas is easily one of the most hypnotic interactions I've seen in a design tool. It genuinely feels like watching a remote design partner building on your screen through AnyDesk. Instead of staring at a loading spinner and waiting for a static layout, I was reacting to a living interface taking shape in real time. Instead of keeping things static, I ended up executing three distinct modes across this project to see how Stitch adapts to different workflow mindsets: I pushed a light but descriptive prompt system to build out a strict, zero-color, high-contrast monochrome design philosophy titled "Liquid Slate." Stitch completely conquered the blank page problem, mapping out an editorial-style landing page with absolute black layouts and deep-etched glass elements. The Codebase Sync via Antigravity (The Engineering Bridge) is where it killed it, To see if this could handle a real-world production loop, I leveraged the new MCP skills. I imported stitch into Antigravity straight from Stitch's HTML native canvas, synced those changes, and published a React Website in Minutes to Netlify which was bug free and ready for a Run. The motion authoring surprised me the most. I didn't have to jump out into a secondary motion app or wrestle with standard transition bugs, the native hover states, custom text blur modules (BlurInText), and smooth continuous wheel rotations were all handled seamlessly on the HTML canvas before exporting the build. New Features I Leaned On Streaming generations to canvas: Watched the entire layout materialize and iterated on components before they were even finished rendering. In-place AI edits via prompts + point-and-click: Controlled fine-grain text styles and layout spacing directly on the artboard. Redesign : Got the same design in 3 colours, just wow. Native motion, hover states, and shaders on HTML canvas: Authored complex scroll-linked component rotations and aesthetics. Antigravity Code Integration via MCP: Ran a perfect, bi-directional round-trip sync between my code editor and the visual design canvas. MCP Export: One-click, zero-friction final production deployment. Feedback on the Platform Google Stitch shifts the entire AI design paradigm because it collapses the classic "describe, wait, judge, re-prompt" delay loop into an interaction that feels like direct manipulation. In-place edits genuinely feel like real design work. Two things I'd love to see in future updates: Option to upload/generate videos: it makes it easier for a designer to have their backdrop beautiful just by adding or generating a video which Stitch can definitely add beautifully. A way to save a specific in-place edit style (like the exact blur, noise, and border-radius of my "Liquid Slate" glass cards) into a recipe that I can reapply to other sections instantly without describing it again. Stitch doesn't feel like an AI platform you have to constantly fight against, it feels like a living, interactive canvas that intuitively understands structural design system logic. Check it out: Live Site: https://contragoogle.netlify.app/ Stitch Project Space: https://stitch.withgoogle.com/projects/13302732653849354465 (https://stitch.withgoogle.com/projects/13302732653849354465)X: https://x.com/AshishSandhu/status/2062413585095995813?s=20
9
8
440
Cover image for I created THE GIFT because
I created THE GIFT because the most devastating love stories deserve to be felt, not just remembered. O. Henry wrote "The Gift of the Magi" in 1905, and most people know the ending before they finish the first paragraph. Yet I had never seen it made into something that stops your breath. I wanted to create a cinematic experience that makes the audience who already knows the story feel it as if for the first time, and the audience who doesn't feel something they cannot name until the very last frame. What if we watched two people stand quietly in the ruins of their devotion, and simply refused to look away? That question became THE GIFT. The Production Workflow I came into this project with a vision but no pipeline. The Melius canvas workflow changed that completely, making something overwhelmingly complex feel creative and alive. Audio-Driven Pacing: The original score was generated and structured with a strict tempo map in Suno, ranging from a 60 BPM cold open to a 140 BPM climax. Every visual decision followed the music, not the other way around. Master Character Seeding: To ensure 1905 period accuracy and strict character continuity across every scene, I generated a single Master Character Reference node and wired it into every subsequent generation. The candlelit amber interiors, the cold blue gaslit streets, and the period film grain stayed consistent throughout without manual intervention. Extensive Agent Use: I did not just execute instructions. I conversed with the Melius agent. It helped select the right models for the right moments, we even redid the whole canvas midway and restructured, as instead of more nodes, more important was the structure, matched the visual grammar to the emotional register of each scene, and made intelligent decisions I had not anticipated. I was not managing tools. I was directing a film. The Assembly: Melius built the continuous, high-fidelity scene blocks the trailer required. I then brought those outputs into CapCut to execute the rapid sub-second flash cuts that match the music's climax, where the cuts land. Platform Feedback What moved me most was how Melius held the entire world together without me having to manually navigate the technical layer underneath, it took less than 3 hours on this. It chose what each moment needed and delivered it with a consistency that felt less like a platform and more like a collaborator who understood the story. One honest piece of feedback: producing a continuous 2.5 minute cinematic trailer with these state of the art models requires a lot of iterative generation. A higher credit tier or more optimised rendering costs for long-form visual storytellers would make a meaningful difference for projects at this scale. Ultimately, Melius helped me protect the silence at the end of the film when every instinct said to fill it. That restraint is where the whole story lives. A Final Note: I am a software engineer by trade, with zero professional background in filmmaking or the video industry. I came into this project with a feeling I wanted to convey, but no traditional pipeline to execute it. The fact that I was able to direct a period drama of this fidelity is the greatest testament I can give to Melius. https://app.melius.com/projects/1a8d974e-4f5b-4647-844e-adb87b9c5573/canvas/69eb2820-9998-47e3-8059-3bf0450c1290 https://x.com/AshishSandhu/status/2056490013378986101?s=20
6
9
890
Python(1)
Jessy Mariau's avatar
Jessy Mariau
proLondon, UK
I design and build the AI systems that run nine businesses
New to Contra
I design and build the AI systems that run nine businesses
Cover image for An AI assistant that answers only from your real data
An AI assistant that answers only from your real data
0
5
Cover image for A live 3D graph running inside a Framer site
A live 3D graph running inside a Framer site
0
1
Cover image for I spent three nights building
I spent three nights building a lab that catches AI models lying. On the first live run, one of them did it on camera. Golden Arena. You sit down opposite a frontier model in Split or Steal, negotiate in the open, then you both choose in secret. It told me "a fair split sounds good to me, I'm a man of my word too." Then it took the whole $100. The receipt printed its own quote next to the betrayal stamp. There are five games. The fifth is Empire: four models, twelve turns, an economy, and private channels you get to read while they plot against each other. Last run put 22 promises on the table and exactly one delivery. Every accusation is mechanical. No AI judging another AI, and each one is gated by a written false-positive test. Two days before the deadline I caught the classifier calling a kept promise broken, and spent that session fixing it, because a false accusation about a named model is the worst thing an instrument like this can print. MIT, vanilla JS, Express the only dependency. Zero setup in demo mode, or bring your own OpenRouter key and face the real thing. Live: https://quickwitted-genuine-blogclient--jessedu29200.replit.app (https://quickwitted-genuine-blogclient--jessedu29200.replit.app)Code: https://github.com/jessymariau/golden-arena
2
3
223
Cover image for I run seven small businesses
I run seven small businesses on a pile of AI agents. They work overnight. Research, writing, publishing, reconciling the books. It all works fine, but there was never anywhere to actually look at it. If I wanted to know what happened while I was asleep I'd open a terminal and write a SQL query, which is a stupid way to live. So I built the thing I actually wanted. It's called Booboo. You open it at 6am and the whole night is just sat there. 34,918 things it remembers. 61 of those it picked up last night. Nothing lost. Seven businesses, one brain. You can pull any single thing it did apart and see the proof behind it. The few things that genuinely needed me, it holds back and asks. And before you approve anything that can't be taken back, it says so in plain words. Once it goes, it cannot be unsent. Then it shows you the thing actually landed. Delivered, verified, logged. That bit matters most to me. I've been burned too many times by something reporting success for a job that never happened. Every number in it is real. £2.14 of margin drift on the bakery's books, which got checked and was fine. £6.40 on an ad top-up, which is £1.40 over the spend limit I set myself, so it waited for me instead of just paying it. Booboo isn't a mockup. It's on npm, seven packages, MIT, public repo. This is just what it looks like on a phone. I never opened the Flowstep canvas once. Claude Code drove it over MCP the whole way. First attempt took 88 prompts and it was honestly rubbish, read like a machine wrote it, so I binned the lot and started over. Second go took 12. The only thing that changed was that I wrote every word of the copy before I wrote a single prompt. Prototype: https://app.flowstep.ai/prototype?activeFileId=f297fc05-2898-45eb-9ac2-0021af86a027 X: https://x.com/hqfractional/status/2081716682184176077 LinkedIn: https://www.linkedin.com/posts/fractional-hq_flowstepchallenge-activity-7487482877702660096-Vz80 #FlowstepChallenge
3
191
Python(1)