AI Editorial
As Seen at Sanremo Festival

Sanremo AI Lab

Multi-agent AI architecture in partnership with The Jackal. Our AI editorial room observes, analyzes, discusses and judges live performances, producing 5 artist ratings every evening for Sanremo 2026.

Btinkeeng X The Jackal Partnership

Segui Sanremo AI Lab sui social

Architecture

Multi-Agent
System

LangGraph-orchestrated AI agents working in parallel to transform live events into publishable content.

Multiple Personas

Critic, Press, and Tabloid agents analyze the same event through different editorial lenses.

LangGraph

Deterministic workflow with parallel processing. Agents work simultaneously then converge.

Ready to Publish

Ratings, reviews, dialogues, and social carousels generated automatically.

Provato a Sanremo

In partnership con The Jackal per Sanremo 2026. Genera 5 pagelle di artisti ogni sera pubblicate su Facebook, oltre a discussioni approfondite dalla nostra piattaforma multi-agente.

Workflow

How It Works

01

Data Collection

As the artist hits the stage, the system ingests lyrics, video, images, and archive documents into structured evidence packages.

02

Parallel Analysis

Three agents work simultaneously on the same data, each with different voice, age, and perspective.

03

Content Synthesis

The Moderator builds dialogue between desks. Output: reviews, carousels, and social content.

Case Study

Sanremo 2026

Sanremo AI Lab

Sanremo is more than music. It's gossip, pop culture and debate — all compressed into one week.

Each evening of the Festival, every performance generates a wave of content, comments, memes and rankings. At Btinkeeng, we wanted to contribute to this debate in our own way, building an entire editorial team made of artificial agents.

La Sfida

Contribuire al dibattito con la nostra prospettiva — costruendo un'intera redazione fatta di agenti artificiali.

La Piattaforma

Un sistema multi-agente basato su AI generativa — una macchina narrativa che produce output multi-formato.

Il Processo

Per ogni artista in gara, un team di agenti AI specializzati — ciascuno con voce, età e prospettiva diverse — analizza la performance e produce contenuti pronti per la pubblicazione.

02. How It Works

Tutto parte dai dati

The moment an artist steps on stage, the system has already begun processing everything into a structured package of evidence.

Testi Video Performance Immagini Artista Documenti d'Archivio
LangGraph Orchestration Layer - AI Agent Architecture

LangGraph orchestration layer - Parallel agent processing workflow

Orchestrazione LangGraph

The heart of the system is a graph of interactions for each episode. The flow is deterministic but parallel in the central phase:

1

Data is analyzed and constitutes the context

2

Three specialized agents then operate in parallel on the same artist

3

Simultaneous execution reduces times and preserves editorial independence

Modelli LLM

Each agent has an LLM model assigned based on the task. The music critic uses a high reasoning capacity model; the tabloid favors fluidity and lively tone; the press agent works with a model optimized for structured outputs.

All models are called through a unified external LLM gateway

After processing individual episodes, a second level of orchestration aggregates the results together. A Pagellista agent produces evaluation sheets for each artist, while the Moderator agent builds the dialogue between agents and collects insights in the form of carousels for Instagram.

03. The Editorial Flow

The system instantiates multiple autonomous agents working in parallel. Data flows from the three specialized desks through the Moderator and Pagellista, transforming into ready-to-publish editorial content.

Desk 01
Critic

Art and craft lens. Deep analysis of writing, interpretation, aesthetics.

Analisi Giudizio
Desk 02
Press

Segnali radiofonici. Hook, rotazioni, potenziale virale.

Hook Trend
Desk 03
Tabloid

Visual impact and pop culture. Outfits, gestures, memorable frames.

Visual Gossip
Orchestrator
Moderator

Brings voices together, builds dialogue, highlights contrasts.

Aggrega 3 prospettive
Evaluator
Pagellista

Votes by category, rankings, special prizes.

Genera pagelle
Schede di Valutazione

Structured ratings with micro-reviews for each category: voice, lyrics, stage presence, emotion, hype.

Pronto per i social
Dialoghi & Contenuti

TV talk show-style discussions synthesizing all three perspectives into long-form content.

Blog, newsletter, script
Elaborazione parallela • < 2 min

Il modello non è vincolato a Sanremo

L'architettura è progettata per essere ricalibrata su qualsiasi evento che genera un flusso di dati in tempo reale.

Richiedi Demo
As Seen at Sanremo Festival

Sanremo AI Lab

Da Sanremo al tuo prossimo evento. Sport, conferenze, lanci prodotto — architettura scalabile per ogni occasione live.