Freelancers using Claude in LondonFreelancers using Claude in London
ProjectsPeople
Christopher Brisley's avatar
Christopher Brisley
proLondon, UK
Platform development, AI Agents & Product Strategy
$10k+
Earned
1x
Hired
5.0
Rating
77
Followers
KAJABI_EXPERT

Expert

Platform development, AI Agents & Product Strategy
Cover image for Virtual Studio Platform
Virtual Studio Platform
1
0
10
Cover image for Personalised Fitness Platform
Personalised Fitness Platform
1
0
8
Cover image for Privacy Compliance Platform
Privacy Compliance Platform
1
0
5
Placeholder project card media
View more →
Claude(3)
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 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
144
Cover image for GHL AI Lead Desk —
GHL AI Lead Desk — AI Lead Qualification & Speed-to-Lead Automation
0
91
Cover image for I built a productized AI
I built a productized AI workflow for ecommerce and marketing teams that need faster creative production without removing human review. The agent takes a simple campaign brief and product image, generates multiple creative directions, creates platform-ready captions, stores all assets, and sends the finished pack to Slack for approval. What It Does Takes product image, product name, campaign type, platform, and brand voice Generates 4 creative image concepts Writes 3 captions per concept Stores source and generated assets in Supabase Logs the campaign run in Postgres Sends a Slack approval card for review Keeps a human approval step before publishing Tools Used n8n, Claude, fal.ai (http://fal.ai), Supabase, Slack Best For Ecommerce brands, DTC teams, agencies, social media managers, and founder-led teams that need more ad creative without adding more manual production work. Outcome One brief becomes a structured creative pack: 4 visual concepts, 12 captions, stored assets, and an approval workflow ready for review.
0
90
Cover image for PitchOS — AI Pre-Sales Intelligence Platform
PitchOS — AI Pre-Sales Intelligence Platform
0
9
Claude(6)
Dathan Eldridge's avatar
Dathan Eldridge
proLondon, UK
I build secure AI and business apps for complex workflows.
New to Contra
I build secure AI and business apps for complex workflows.
Cover image for SYNAPZ — Governed AI Execution and Decision-Support
SYNAPZ — Governed AI Execution and Decision-Support
1
4
Cover image for I designed and built an
I designed and built an AI system guardian focused on operational health, memory, security, resource monitoring and controlled deployment decisions. The system evaluates runtime conditions, identifies risks, records supporting evidence and provides clear hold, approval or rejection decisions before sensitive changes proceed. I led the product architecture, monitoring workflows, decision controls, frontend, backend and testing.
1
43
Cover image for I designed and developed an
I designed and developed an AI-assisted application-building system that supports product definition, architecture, code generation, testing, review, deployment and controlled iteration. Unlike unrestricted code generation, the platform uses structured workflows, specialist agents, human approvals, validation gates and deployment controls to create more accountable and reproducible software builds.
4
151
Cover image for SYNAPZ — Governed AI Technology
SYNAPZ — Governed AI Technology Company Website I founded and built SYNAPZ as a governed AI technology ecosystem designed to coordinate specialist AI agents, operational data, human approvals and controlled software workflows. The wider platform includes governed AI infrastructure, application-building systems, operational integrity and memory controls, security and deployment guardians, real-time intelligence platforms, document and evidence systems, creative-production engines and specialist business applications. Rather than allowing unrestricted autonomous execution, the architecture uses policy gates, human approvals, audit records, sandboxing, testing, deployment controls and rollback protection. I led the overall vision, product strategy, system architecture, workflow design, development direction, integration, testing and deployment across the ecosystem.
3
108
Claude(6)
Ayodimeji Adedotun's avatar
Ayodimeji Adedotun
London, UK
AI Native Product designer
New to Contra
AI Native Product designer
Cover image for Tinder but for service discovery. While
Tinder but for service discovery. While designing for Littleseconds, we explored alternatives to the usual vertical scroll or grid layout for finding services near you. We tested a swipe-based discovery pattern, like, skip, next. It didn't move forward, other directions just tested better at the time. I revisited the file recently and built it out as a working iOS prototype using Xcode and Claude Code. Took an afternoon. And that's kind of the point. Back then, showing interaction intent meant annotated Figma flows that stakeholders half-read. Today you hand them something they can actually tap through. The idea gets a fairer hearing. Better tools don't just make us faster. They make us better at being understood.
2
1
69
Cover image for I designed and built a
I designed and built a concept prototype for a problem I keep hitting inside AI chat. AI chat is modelled on SMS. Linear. One thread. Newest at the bottom. But thinking isn't linear. Two friction points that shouldn't exist: You're mid-conversation and need to explore a different angle. Your only options are start over and lose context, or pollute the thread you're already in. You organise chats by topic inside a project. But when you're on chat 15 and need to follow up on something from chat 5, there's no cross-reference. You end up asking the model if it remembers, which is not a UX. Threaded conversations inside AI chat. A thread branches from any message. It carries the context of that moment as its anchor. The main conversation stays intact. The model gets a focused, bounded context window, less noise, sharper answers.
0
61
Cover image for Spent a weekend prototyping a
Spent a weekend prototyping a custom card design flow for a fintech app. Not Figma frames, actual SwiftUI screens running on device. The designer picks their card theme, uploads a photo, chooses where the details sit (front or back face), and confirms. The card responds to gyroscope tilt in real time. Scrub the spending chart and the number morphs with a haptic tick on each data point. Confetti on order confirm. This is the workflow I'm bringing to teams, concept to tappable prototype in days, not sprints. Not something to hand off to developers to interpret. Something you can feel. AI native designer available for fintech, product and interaction work. DMs open.
0
64
Cover image for Unpopular take: most MVPs are
Unpopular take: most MVPs are overbuilt. I shipped an iOS app — SayItLater. No signup. No backend. No internet. Just write and go. I wasn’t trying to build a big product. I wanted to see how fast I could go from idea → App Store. Answer: faster than you think when you remove 90% of the fluff. Biggest lesson: The hard part isn’t building. It’s deciding what not to build. If you’re sitting on an idea, cut it down and ship it. If you need help getting something live quickly, I’m open.
3
80
Claude(3)
Chester Smith's avatar
Chester Smith
London, UK
Business automation specialist. Get the most out of AI.
New to Contra
Business automation specialist. Get the most out of AI.
Cover image for AI Integration for UK Property Agencies
AI Integration for UK Property Agencies
0
5
Cover image for End-to-end automation factory
End-to-end automation factory
0
3
Cover image for Sleek website I built for
Sleek website I built for my SaaS business
0
40
Cover image for Sales Progression Automation for an Estate Agency
Sales Progression Automation for an Estate Agency
0
3
Claude(4)
Evgeniya Strygina's avatar
Evgeniya Strygina
proLondon, UK
AI Video Producer for Campaigns, UGC & Brand Films
5.0
Rating
25
Followers
LUMMI_EXPERT

expert

AI Video Producer for Campaigns, UGC & Brand Films
Cover image for DracoSlides — Scalable AI Content System
DracoSlides — Scalable AI Content System
0
10
Cover image for One-take cinematic AI film production This
One-take cinematic AI film production This is an FPV drone flight through a city during a solar eclipse. The camera moves from a crowded square to a football stadium without any cuts or transitions. I wanted to show how people react when something unusual happens, and routine becomes ritual As the eclipse shadow advances, people who don't know each other start moving in sync — looking up at the same time, adjusting their position together, reacting as one group. The drone follows this rhythm from quiet individual moments in the city to a massive collective gasp in the stadium Built in CapCut Video Studio with Seedance 2.5. #contraseedancechallenge #CapCutCPP
18
75
7.9K
Cover image for AI music video / Creative
AI music video / Creative direction I guess everyone’s had a chance to play with Seedance 2.5 by now, right? Here’s what actually stood out to me. The biggest difference isn’t resolution or motion quality — it’s how well the model holds a visual reference. When I fed it a specific aesthetic — early 2000s digital, raw grain, handheld imperfection — 2.5 preserved the character of it. Camera movement felt stylistically consistent, not just technically correct. The previous version tended to simplify, smoothing things out toward something more generic. For this experiment, I used a Charli xcx track as the starting point and built the visual around its energy and aesthetic. For anyone doing editorial or narrative AI work, that distinction matters a lot. A tool that interprets your reference rather than flattening it changes what’s possible in the creative direction process.
1
5
710
Cover image for SaladPower Creative Challenge — concept
SaladPower Creative Challenge — concept campaign for a premium vegetable pouch brand. Most healthy food ads over-explain the product. They try to sell clarity, benefits, and lifestyle. I approached it differently. A short-form motion piece built around restraint — texture, pacing, and visual tension instead of messaging or persuasion. No wellness framing. No lifestyle narrative. Just the product in focus.
1
4
978
Claude(1)