vector automaton
With great automation comes zero paperwork.
New to Contra
vector is building their profile!
ContentPilot | Agentic AI YouTube-to-Social Content Repurposing Engine
Project Overview
An end-to-end content distribution system built using Relevance AI and Notion. This automated workflow transforms a single long-form video or podcast episode into publication-ready drafts across multiple social media platforms within minutes, significantly reducing manual copywriting overhead.
The Challenge
Content creators, B2B founders, and marketing teams often spend 10 to 15 hours every week manually reviewing long videos, extracting transcripts, and rewriting them into platform-specific formats like X threads, LinkedIn carousels, and short-form video scripts. This operational bottleneck can constrain brand visibility and posting consistency.
The Solution
An intelligent AI agent pipeline designed to streamline the content extraction, generation, and organization process:
Automated Extraction & Ingestion: Ingests a designated YouTube URL as a trigger, utilizing a multi-layered tool stack (Video Data Extractor, Get Metadata & Subtitles, and Transcription Service) to securely pull and process video assets.
AI Processing Agent: Leverages advanced LLMs (such as GPT-4o or Claude via Relevance AI) to analyze the core message, tone, and key takeaways.
Structured Generation: Automatically formats output into platform-ready assets:
X (Twitter) Thread: 5–7 educational, structured posts with clear hooks.
LinkedIn Carousel Copy: Slide-by-slide text structured for professional engagement.
Short-Form Script: A 30–60 second script optimized for short-form video channels.
Centralized Content Hub: Automatically organizes and routes generated assets into designated database properties within the client’s Notion workspace for final human review and scheduling.
Tech Stack & Integrations
AI & Agent Orchestration: Relevance AI, OpenAI / Claude API
Data Ingestion: YouTube Data API & Subtitle Parsers
Content Hub & Database: Notion API
Workflow Logic: No-code agent architecture with strict structured JSON output parsing
Estimated Business Impact & Results
Time Efficiency: Designed to save content teams dozens of hours of manual copywriting and content slicing per month.
Workflow Consistency: Helps scale brand posting frequency across multiple channels without requiring immediate headcount expansion.
Streamlined Operations: Centralizes drafts in an organized Notion dashboard for rapid human review, approval, and scheduling.
1
7
Agentic AI Support Triage: Autonomous Sentiment Analysis & Escalation (n8n)
A High-Class autonomous support operations architecture built on n8n. Designed to bridge front-line customer inquiries, real-time sentiment extraction, cognitive ticket categorization, and instant emergency escalation, this pipeline drastically reduces manual triage delays and enables rapid, automated escalation protocols for critical issues.
Support Intake (Gmail / Webhook): Ingests incoming customer tickets and support emails in real time to initiate the automated triage loop.
Cognitive Reasoning Engine (OpenAI Advanced AI): Evaluates multi-layered customer sentiment, assigns urgency scores, extracts core issue metadata, and formulates contextual response drafts.
Operational Ledger (Airtable / Notion): Provisions structured records containing ticket history, urgency metrics, sentiment analysis, and generated draft responses into the central database.
Dynamic Router (n8n IF Node): Evaluates sentiment thresholds and priority flags to dynamically segment critical issues from routine inquiries.
Emergency Escalation (Slack): Instantly triggers high-priority, rich alerts to internal leadership and dedicated support channels when 'Angry' or 'Frustrated' sentiment is flagged.
Automated Resolution Queue (Helpdesk / Gmail): Applies classification tags to standard tickets and populates auto-response drafts for seamless agent review.
'Prompt and node parameter configurations hidden for client confidentiality
1
46
Agentic AI Order-to-Cash Pipeline for E-Commerce
An end-to-end intelligent automation architecture designed to bridge e-commerce sales, payment processing, cognitive AI data enrichment, automated bookkeeping, and team notifications. This workflow transforms rigid, manual financial operations into a self-managing, responsive pipeline.
Trigger (Shopify): Captures incoming e-commerce orders instantly upon successful customer payment.
Data Enrichment (Stripe): Retrieves detailed payment gateway metadata, customer risk scores, and transaction status for enhanced security validation.
AI Reasoning Engine (OpenAI): Acts as the cognitive core to analyze unstructured order data, dynamically categorize products into appropriate accounting ledger codes, and flag anomalies.
Financial Settlement (Xero): Automatically provisions customer profiles and generates structured sales invoices within the accounting platform.
Operational Loop (Slack): Dispatches real-time, context-rich notifications and alerts directly to internal finance and operations channels.
'Prompt configuration hidden for client confidentiality
2
67
AI Agent Workflow: Lead Qualification & Smart Routing
Automated Lead Management & Smart Routing
Built an automated system to filter and handle new inquiries without the tedious manual work. The moment someone fills out a form, the data flows straight into a database, where AI steps in to score and qualify the lead.
From there, a router automatically sorts them into the right paths:
High-priority leads trigger an instant notification straight to Slack.
Warm leads route directly to WhatsApp for immediate outreach.
The rest drop neatly into a Gmail queue for standard follow-ups.
Bottom line: a purely automated workflow that cuts out manual data entry and keeps your lead pipeline organized.
1
64