Juan ignacio Veltri
Senior Full Stack Engineer · Next.js · React Native · Expo
New to Contra
Juan ignacio is ready for their next project!
BE PAWLY — A COMPLETE LAUNCH KIT, ORCHESTRATED BY AN AGENT IN ONE AFTERNOON
The premise
I'm an indie dev about to launch Be Pawly, an AI-powered app that matches photos of lost and found pets in real time, helping reunite them with their owners. The product is ready. The launch kit wasn't.
Hiring an agency for identity, mockups, ads, and a launch video wasn't on the table for a solo founder. So I gave Melius a single brief and let Mel orchestrate the entire kit.
The result
18 connected nodes. One coherent brand. About 4,000 credits consumed out of 50,000.
→ Hand-drawn bilingual logo with the tagline "Conectamos corazones, reunimos familias"
→ 3 mobile app UI mockups (Upload Lost Pet, AI Match, Reunion Confirmed)
→ 4 emotionally segmented Meta ads (Community, Gratitude, Hope, Urgency)
→ 1 redesigned modern "missing pet" street flyer with QR
→ 1 cinematic 15-second vertical Instagram video, anchored to a keyframe
The process, in three phases
I gated execution by phase to manage credits and review the agent's output at every dependency boundary.
Phase 1 — Foundation (72 credits). Just the logo. The logo anchors every downstream asset, so it was the only node I needed to lock before generating anything else. Mel routed GPT Image 2 (Medium) and delivered a hand-drawn terracotta mark, and proposed a bilingual tagline I never asked for, but that fit the Latin American neighborhood-first tone perfectly.
Phase 2 — Derivatives (around 1,000 credits, 8 parallel nodes). Three UI mockups, four ad variants, one flyer. Mel propagated the Spanish tagline across every asset without prompting, invented credible character names (Max, Toby, María & Simba), and used context-appropriate Latin American Spanish ("publicador" instead of "poster"). The brand feels like a real product, not stock.
Phase 3 — Motion (around 3,000 credits). A cinematic keyframe of the reunion, then a 15-second vertical Instagram spot anchored to it. When I asked Mel which model it would use, it didn't just pick — it offered me Kling 3.0 Omni (2,520 credits) versus Grok Imagine (1,260 credits), explained the tradeoff ("Kling handles the emotional human-first nuance a bit better"), and let me decide.
What separates an agent from a generator
Three behaviors Mel did on its own that no generator I've used does:
Model routing with reasoning. GPT Image 2 across the 8 image nodes for stylistic coherence; Kling 3.0 Omni for the video, chosen for emotional nuance. Transparent about cost tradeoffs.
Style propagation through wired connections. The tagline, color palette, and character voice flowed from one node into every downstream node automatically. No copy-paste, no re-prompting.
Initiative within taste. The bilingual tagline. The character names. The neighborhood-aware Spanish. These were unprompted but always on-brief.
Feedback for the Melius team
What worked beautifully:
→ The canvas-as-conversation model. Being able to point at a specific node and refine it without re-running the whole graph is a step-change versus linear chat-based generation.
→ Mel's proactive credit transparency. Asking "which model and how many credits" before running was huge for budget management.
→ Auto-grouping into Brand Identity, Meta Ad Campaign, and Social Video was an unprompted decision that made the canvas instantly readable.
Suggestions:
→ Surface estimated credit cost on hover for every node before approval, not just when prompted.
→ A "fork node" action to create alternative variants in parallel without losing the original would be useful for A/B-ing ads.
→ An export-as-launch-kit shortcut (a zip with all assets in presentation order) would close the loop from creative to delivery.
Built entirely on Melius. Models routed: GPT Image 2 (Medium) and Kling 3.0 Omni. Total credits consumed: about 4,000 of 50,000. The 15-second reunion video is attached.
Project canvas: https://app.melius.com/projects/04e916b8-35de-4957-8db6-53ac1af180ad/canvas/4d8d194a-d0d5-4e4c-a59b-d7a4561923bb
1
67
Sitio web premium para TMS Construcciones, empresa constructora argentina con más de 30 años de experiencia en el Alto Valle de Río Negro y Neuquén (región impulsada por Vaca Muerta). Showcase de 6 proyectos activos de desarrollo inmobiliario residencial y comercial, con renders 3D, animaciones fluidas, video hero y soporte bilingüe ES/EN. Construido con Next.js + TypeScript, animaciones con Framer Motion + GSAP, renders 3D con Three.js, internacionalización con next-intl. Stack frontend-first con foco en performance, SEO y experiencia visual de alto nivel.
1
2
90
Be Pawly es una plataforma todo-en-uno para mascotas que usa inteligencia artificial para reunir mascotas perdidas con sus familias. El algoritmo analiza fotos, ubicación y características para encontrar coincidencias entre reportes de mascotas perdidas y encontradas, con notificaciones en tiempo real cuando hay un match. También conecta refugios verificados con adoptantes y permite difundir búsquedas en redes sociales. Stack: Next.js, TypeScript, Drizzle ORM, Google Vertex AI, Clerk, Pusher.
1
1
72
Puntify — Anotador de juegos de cartas (IOS)
0
46
Puntify es una app mobile para llevar el puntaje de juegos de cartas argentinos y latinoamericanos sin necesidad de papel y lápiz. Incluye Truco argentino, Truco uruguayo, Chinchón, Generala, Escoba de 15, La Podrida, 10.000 y más. Hasta 8 jugadores por partida, historial completo, dark mode y funcionamiento offline. 100% gratis y sin publicidad. Publicada en App Store y Google Play. Construida con React Native + Expo + TypeScript, deployada con EAS Build.
1
57
Polopage es la plataforma digital del polo mundial. Reúne en un solo lugar el directorio global de jugadores con handicap, país y club; el ecosistema de servicios del deporte (caballos, herreros, veterinarios, talabartería, clubes, transporte); noticias del polo internacional; y una comunidad activa con chat en vivo y surveys con recompensa. Construido con Next.js + TypeScript, optimizado para SEO multi-idioma (ES/EN), con datos de jugadores top como Adolfo Cambiaso, Facundo Pieres y la familia Castagnola.
1
69
Barrial es una plataforma social-commerce para barrios privados que conecta residentes con comercios locales. Incluye feed algorítmico, reviews, stories, anuncios, QR de visitas y un sistema de mascotas perdidas. Construido como monorepo Turborepo con apps nativas iOS/Android (Expo) + web (Next.js), tRPC end-to-end type-safe, Prisma + Postgres (Neon), autenticación con Clerk + Better-Auth, almacenamiento en AWS S3, observability con Sentry y push notifications nativas + web.
1
58
SIU Bot es una plataforma que automatiza el proceso de inscripción a materias en SIU Guaraní, el sistema académico usado por la mayoría de universidades públicas y privadas de Argentina.
El problema: las inscripciones se abren en horarios fijos y los cupos vuelan en minutos. Los estudiantes terminan pegados al navegador a las 7 AM, peleando con CloudFlare, captchas y saturación del sistema. Muchos se quedan afuera de las materias que necesitan.
La solución: el usuario carga sus credenciales (cifradas en reposo con AES-256-GCM) y la lista priorizada de materias. Cuando se abre la ventana de inscripción, el bot se inscribe en su nombre en paralelo, con detección automática de CloudFlare/captcha, backoff exponencial con jitter, y reintentos resilientes.
Alcance: 28 universidades soportadas, 148+ carreras mapeadas, cron jobs sub-minuto, cache compartida multi-usuario y audit logs de cada intento.
1
60