Freelancers using LangChain in SpainFreelancers using LangChain in Spain
ProjectsPeople
Facundo Cappella's avatar
Facundo Cappella
maxMadrid, Spain
Tech Lead | Solution Architect | AI Engineer
133
Followers
Tech Lead | Solution Architect | AI Engineer
Cover image for Whitepaper Finder
Whitepaper Finder
1
3
Cover image for Post your ideas, or random
Post your ideas, or random thoughts anonymously. Get ratings and opinions from people everywhere, no sign-up. https://rateidea.us/
0
26
Cover image for https://dealy.figma.site/ Latest Updates 🚀 📍 Improved
https://dealy.figma.site/ Latest Updates 🚀 📍 Improved User Location Accuracy The map now centers precisely on the user's current location. Increased zoom levels make it much easier to identify the exact position and nearby points of interest. 🌐 Domain Update Renamed the domain to better reflect the application's purpose and branding. Tech Stack Supabase Next.js Skills & Focus Areas UI/UX Design Next.js Best Practices Geolocation & Mapping Frontend Performance Optimization Small improvements like these can make a significant difference in usability and overall user experience.
1
2
109
Cover image for Create Stunning Custom Banners with This Easy Canva Alternative
Hello, I just built a simple tool similar to Canva that lets you create custom banners. I originally made it for personal use, but I decided to make it public in case it could be useful for others. Feel free to use it, and if you have any suggestions or feedback, I’d really appreciate it. https://ln-banner-generator.vercel.app/
0
197
LangChain(1)
Alex Mamaev's avatar
Alex Mamaev
Madrid, Spain
AI & SaaS Developer with Product Expertise
AI & SaaS Developer with Product Expertise
Cover image for Developing a Chatbot and Widget for Property Managers
Developing a Chatbot and Widget for Property Managers
0
13
Cover image for Developing an AI-Powered Tool for Gathering Customer Feedback
Developing an AI-Powered Tool for Gathering Customer Feedback
0
14
Cover image for Chrome Extension for Scheduling Meetings Globally
Chrome Extension for Scheduling Meetings Globally
0
13
Placeholder project card media
View more →
LangChain(1)
Roberto Nauzet Dorta Harteveld's avatar
Roberto Nauzet Dorta Harteveld
Santa Cruz de Tenerife, Spain
Building Smart Web Apps and Automating Your Business Growth
New to Contra
Building Smart Web Apps and Automating Your Business Growth
Cover image for I designed and implemented the
I designed and implemented the architecture of a business Artificial Intelligence Agent focused on automating support and capturing potential customers (Lead Generation). The core of the system uses OpenAI GPT-4o orchestrated with LangChain to inject custom context and dynamic knowledge bases. The data pipeline processes user interactions in milliseconds, syncs information in real-time with MongoDB databases, and sends qualified leads directly to the company's CRM. The project includes an advanced analytics dashboard that monitors the agent's performance, managing to maintain an optimal average response time of 1.8 seconds and operating 24/7.
0
14
Cover image for I developed a large-scale backend
I developed a large-scale backend automation solution for the real estate sector that collects, analyzes, and structures property metrics. The system uses the GPT-4o-mini model to process large volumes of market data by geographic location and autonomously generate executive analytical summaries. Once the AI processes the information, the system compiles the data into high-quality professional PDF documents ready to download. The entire infrastructure was modularized and containerized using Docker (v3.1), ensuring a clean, scalable, cost-efficient, and highly available cloud deployment for production environments.
0
16
Cover image for Creation and layout of a
Creation and layout of a premium e-commerce platform focused on the retail and fashion sector. The frontend was developed from scratch using Next.js and TypeScript, prioritizing load speed, SEO optimization, and a smooth user experience on both desktop screens and touch mobile environments (100% responsive design). As an added value to boost conversion, I integrated a custom smart chat widget connected to language models (LLMs), which assists shoppers in real time by autonomously resolving questions about sizes, shipping, and product stock directly on the product page.
0
15
Cover image for I developed a comprehensive real-time
I developed a comprehensive real-time inventory management system for modern e-commerce stores. The backend is built on a robust architecture using FastAPI and PostgreSQL, ensuring ultra-fast data processing with stable database connections. The admin panel monitors active user sessions, daily sales balances, and automatic syncing of physical/digital stock, reducing discrepancies to zero. Plus, the system features an optimized mobile payment flow, natively integrated with the Stripe Secure Checkout API to maximize sales conversions safely.
0
15
LangChain(1)
Javier Martinez's avatar
Javier Martinez
Spain
24/7 AI Automation | Receptionist + Sales + Workflows
New to Contra
24/7 AI Automation | Receptionist + Sales + Workflows
Cover image for From prospect list to personalized
From prospect list to personalized proposal — fully automated, no manual research required.
0
50
Cover image for Built a full AI consulting
Built a full AI consulting business system — from website to outreach machine. For a boutique AI consulting firm targeting mid-market companies in the US and Europe, I designed and shipped the full technical stack: Production website (React + TypeScript + Express) Not just a landing page. A conversion machine: lazy-loaded routes, per-page SEO metadata, structured data for Google, a sitemap, an OG image for social sharing, and Lighthouse-ready performance fixes (including a Framer Motion LCP bug that was silently tanking search rankings). AI Diagnostic Tool A multi-step lead qualification form that calls Claude under the hood, generates a personalized automation ROI report for each prospect, and delivers it at a unique URL — with prompt injection protection baked in (XML-delimited user inputs, system prompt hardening). Security layer CSP headers, correct trust-proxy config for a Cloudflare + Railway dual-hop topology, hardened email notification logic, and temp file cleanup that survives errors. Production-grade, not tutorial-grade. LinkedIn prospecting engine A Python + Playwright scraper that: Rotates across 10 industry niches Qualifies leads by title, location, and post recency Auto-generates personalized connect requests (≤300 chars) and follow-ups via Anthropic API Exports to Excel, deduplicates across runs Currently targeting Property Management decision-makers in Florida & Texas This is what "full-stack AI consulting infrastructure" actually looks like in practice. What was built A production-ready AI consulting business stack, covering six layers end to end. On the frontend, a React SPA with TypeScript, lazy-loaded routes, per-page SEO metadata via react-helmet-async, and full internationalization in English, Spanish, and Danish. The SEO layer included a sitemap, robots.txt, JSON-LD structured data schemas for Google, a custom OG image at 1200×630px for social sharing, and a performance fix for a Framer Motion bug that was silently blocking the page's Largest Contentful Paint — meaning Google couldn't properly index the main headline. The backend is an Express + TypeScript API deployed on Railway, hardened with Content Security Policy headers, correct trust proxy configuration for a Cloudflare + Railway dual-hop topology, and proper temp file cleanup that survives errors. The AI feature is a multi-step diagnostic form that sends the prospect's business data to Claude, generates a personalized automation ROI report, and delivers it at a unique shareable URL — with prompt injection protection built in so user-submitted text can never hijack the LLM's instructions. On the security side, all user-controlled fields are wrapped in XML delimiters in the prompt, environment variable handling was hardened to eliminate silent fallbacks, and no sensitive data leaks through error paths. Finally, the outreach system is a Python + Playwright scraper that rotates across industry niches, qualifies leads by title, location, and post recency, then uses the Anthropic API to generate personalized LinkedIn connect requests and follow-up messages for each lead — exporting everything to Excel with deduplication across runs. Key technical problems solved LCP blocked by Framer Motion: opacity:0 on H1 prevented Google from indexing the headline. Fixed by rendering plain HTML on first paint. Prompt injection risk: All user-submitted fields wrapped in XML delimiters + system prompt instruction to treat them as data, not commands. Dual-hop proxy misconfiguration: trust proxy: 1 was wrong for a Cloudflare → Railway topology. Corrected to 2 to get real client IPs in logs and rate limiting. Location-aware lead qualification: Scraper's filter system refactored to support per-niche target_locations, enabling pivot from Danish to US markets without touching core logic.
0
36
Cover image for 🚀 We just systematized 100%
🚀 We just systematized 100% of our sales with AI and Automation (and we're looking for top tier talent to run it) At JM Consulting, we don't sell theory; we sell growth systems and AI audits with a strict "ROI-First" approach. To prove it, we just documented our entire internal sales process using artificial intelligence. We've created the Sales Master Playbook v1.0, an operating ecosystem where the sales rep doesn't waste time on manual tasks, but simply "plugs and plays". What have we packaged into this step-by-step system? Everything a Closer or SDR needs to crush their metrics from day one: Aggressive & Clear Commission Structure: Our team earns a 15% commission (1 to 5 closes), 20% (6 to 10 closes), and up to 30% (more than 10 closes per month). The Ultimate Tech Stack: A complete setup integrating Claude, n8n, Apollo, Calendly, and Slack/Telegram. 3 Proprietary AI Agents: The rep gets the exact prompts to install a Lead Qualifier Agent, a Strategist Agent to prepare for calls, and a Closer Agent to generate winning proposals in minutes. n8n Automation Blueprint: The complete workflow, documented node by node. The system automatically prospects, qualifies, sends personalized emails, and pushes alerts directly to Telegram. The 90-Minute Routine: A daily framework where automation does 70% of the heavy lifting, allowing human talent to focus exclusively on calls and closing. Service Catalog & Objection Handling: Precise scripts to sell our AI Opportunity Audits and Quick Wins Sprints, including our signature "Yesterday Morning Method". Who is this for? 👉 If you are a B2B sales professional (Closer/SDR) and want to join a team where technology does the boring prospecting for you, we have a deal for you. 👉 If you want to implement this level of commercial infrastructure in your own company, these are the exact types of systems we build. The key to scaling isn't working more hours—it's having the automation system do the heavy lifting so you can focus on the closing
1
56
Cover image for Yesterday and today we've been
Yesterday and today we've been working intensively on the backend of our B2B prospecting system, and I want to share the results with you. We've gone from a manual and tedious process to an autonomous lead generation machine using n8n, Paperclip, and Apify. What exactly does this ecosystem we built do? 🎯 Surgical Search: Every day, it tracks C-Level profiles (Directors, Leaders, Executives, Consultants) in the Property Management industry (Fast Ejendom). Today, for example, we pivoted the bot's entire memory to focus the strategy 100% on the Danish market 🇩🇰. 🕵️‍♂️ Context Extraction: It doesn't just extract the profile. The system reads the prospect's recent LinkedIn posts to understand what they're currently working on. 🤖 AI-Powered Copywriting: Generate a connection message (under 200 characters, no empty promises) based on their latest post or achievements, and a follow-up message offering our AI-powered Opportunity Audit. 📊 Live Sync: Everything is compiled into a structured spreadsheet with automatic status updates (Connect, Sent, Replied, Not Interested). The "hard work" of researching and copywriting is now done by AI in the background. Our team (and our clients' teams) only needs to focus on what matters: closing meetings and building real relationships. B2B prospecting doesn't have to be a time sink. If your sales team is still copying and pasting generic messages, they're leaving money on the table. What automation tool is saving your life this year? 👇 hashtag#Automation (https://www.linkedin.com/search/results/all/?keywords=%23automation&origin=HASH_TAG_FROM_FEED) hashtag#Artificial (https://www.linkedin.com/search/results/all/?keywords=%23artificial&origin=HASH_TAG_FROM_FEED) Intelligence hashtag#B2B (https://www.linkedin.com/search/results/all/?keywords=%23b2b&origin=HASH_TAG_FROM_FEED) hashtag#LeadGeneration (https://www.linkedin.com/search/results/all/?keywords=%23leadgeneration&origin=HASH_TAG_FROM_FEED) hashtag#n8n (https://www.linkedin.com/search/results/all/?keywords=%23n8n&origin=HASH_TAG_FROM_FEED) hashtag#Apify (https://www.linkedin.com/search/results/all/?keywords=%23apify&origin=HASH_TAG_FROM_FEED) hashtag#B2B (https://www.linkedin.com/search/results/all/?keywords=%23b2b&origin=HASH_TAG_FROM_FEED) Sales hashtag#PropertyManagement (https://www.linkedin.com/search/results/all/?keywords=%23propertymanagement&origin=HASH_TAG_FROM_FEED)
0
28
LangChain(1)
Dimitri Appel's avatar
Dimitri Appel
Barcelona, Spain
AI Workflow Architect & Automation Expert
6
Followers
AI Workflow Architect & Automation Expert
Cover image for AI Invoice Automation via Telegram, OCR & SAP Integration
AI Invoice Automation via Telegram, OCR & SAP Integration
1
57
Cover image for AI Appointment Scheduler (n8n + Twilio + Cal.com + Airtable)
AI Appointment Scheduler (n8n + Twilio + Cal.com + Airtable)
0
23
Cover image for Customer Onboarding Automation with n8n
Customer Onboarding Automation with n8n
0
22
Placeholder project card media
View more →
LangChain(1)
Andrés Lage's avatar
Andrés Lage
proFerrol, Spain
Independent AI Architect&Strategist EU AI ACT&OWASP
New to Contra
Independent AI Architect&Strategist EU AI ACT&OWASP
Cover image for Production-ready multi-agent system demonstrating Agentic
Production-ready multi-agent system demonstrating Agentic AI principles. Built with LangGraph for workflow orchestration, FastAPI for the API, and OpenAI GPT-4. Features autonomous decision-making, tool use, and multi-agent collaboration for intelligent data analysis and strategic recommendations.
0
32
Cover image for This production-ready Hotel Voice Assistant
This production-ready Hotel Voice Assistant integrates Google Gemini 2.0 with a scalable Flask/Waitress backend to power fluid, context-aware conversational booking experiences in Spanish. It leverages a distributed Redis session store for stateful multi-turn memory, backed by native Function Calling to stream live availability and real-time pricing directly from the Amadeus GDS API. Engineered with an "auditability-by-design" framework, the architecture implements pluggable callback hooks and strictly aligns with the OWASP Agentic Top 10 (2026) to mitigate multi-agent risks and secure user data.
1
25
Cover image for Industrial AI replaces opaque, high-cost
Industrial AI replaces opaque, high-cost LLMs with deterministic, hybrid architectures built specifically for high-risk, heavily regulated enterprise environments. It leverages glass-box explainability (like EBMs) and cascading NLP pipelines to resolve up to 80% of operational traffic at zero token cost and sub-millisecond latency on CPU. By embedding continuous statistical drift monitoring (KS-test/PSI), it translates raw telemetry into audit-ready assets, guaranteeing strict compliance with the EU AI Act and ISO 42001.
1
15
Cover image for Most ML projects that win
Most ML projects that win Kaggle would not survive a regulatory audit in 2026. This one is built specifically to do both competitive performance AND audit-ready by design. Insurance claim prediction (Porto Seguro dataset, 3.6% positive class, highly imbalanced) implemented end-to-end with EU AI Act, Solvency II and ISO 42001 compliance as the architectural starting point not as a documentation afterthought. Four pillars: MLOps & Shadow Monitor Architecture. Vendor-agnostic monitoring layer that reads inference logs independently from the production model (Azure ML / SageMaker / Vertex AI). KS-test drift detection in real time. Zero vendor lock-in. The Shadow Monitor is the answer to "how do you audit a black-box cloud ML service?" Explainability vs Performance trade-off, decided with evidence. EBM (Explainable Boosting Machine) chosen over XGBoost/LightGBM. ROC-AUC 0.608 vs 0.64-0.65 for XGBoost a 4% performance cost in exchange for native glass-box explainability that regulators accept without SHAP post-hoc workarounds. The right call for regulated industries, the wrong call for tech. Threshold optimization on imbalanced data. Default scikit-learn 0.5 threshold yields F1 ≈ 0 on this dataset a model that "performs at 96.4% accuracy" is in fact useless. Custom F1-Score curve finds the optimal decision boundary at 0.091. The difference between a Kaggle submission and a production system. Automated Compliance Dashboard. Fairness (demographic parity, equalized odds, protected-attribute analysis), Transparency (feature-level contributions, full documentation), Accountability (model card, ADRs, governance framework, human-in-the-loop). Maps directly to EU AI Act high-risk requirements, Solvency II model validation, and ISO 42001 controls. Why Polars over Pandas? Built in Rust, 5-12x faster, lazy evaluation, native multi-threading. For production ML under EU AI Act, processing speed on inference logs is not a nice-to-have it's an audit requirement. Template replicable for banks, insurers, healthcare, and any organization where ML decisions need to defend themselves in front of a regulator.
0
32
LangChain(1)