ZAR AI
ZZAR AIFree questions

Hey! Whether it's a concert in London or a conference in Singapore, every day brings new possibilities. What would you like to plan next?

07:53 PM
Skip to main content
EventZR
Try EventZR
EventZRIntelligence for LIVE Experiences
  • for Government Events
  • for Festivals & Concerts
  • for Sports & Gaming
  • for Meetings & Conventions
  • for Expos & Trade Shows
  • for Corporate Events
  • for Weddings & Parties
  • for Spiritual Events
  • for Immersive Experiences
  • for Host Families
  • for Performing Artists
  • for Industry Professionals
  • for Agents & Agencies
  • for Trade Associations
  • for Government Ministries
  • for Academic Institutions
  • for Publishers & Broadcasters
  • for Hotels & Venues
  • for Leadership Teams
  • for Content Teams
  • for Creative Studios
  • for Sales Teams
  • for Marketing Teams
  • for Operations Teams
  • for Hospitality Teams
  • for Finance Teams
  • for HR & Admin Teams
  • AI Engine
  • Multi-Lingual
  • Context First
  • WhatsApp-First
  • Security & Compliance
  • Open Platform
  • for Contributors
  • for Partners
  • for Developers
  • for StartUps
  • for Academics
  • for Ambassadors
  • for Sustainability
  • for Referrals
  • for Residency
  • About EventZR
  • Our Founder
  • For Investors
  • EventZR Careers
  • Support Centre
  • Contact Us
Launching SoonCortexCypherBazaarMarketplaceAmplifyWebifySphereBeacon
ยฉ 2026 EventZR Technologies ยท All Rights Reserved
Terms|Privacy|Cookies|GDPR|Compliance|Security|Accessibility|Responsible AI|Sitemap
CORTEX

One Marketplace. Every AI Model. Your Knowledge.

Cortex connects you to 15 AI providers, routes each request to the best model for the job, and lets you build a private knowledge base that makes every answer smarter over time.

Try ZAR AI โ†’
15 AI Providers7 Search Modes50+ Languages

Why teams move from DIY AI to Cortex

Managing multiple AI providers, building RAG pipelines, and evaluating model quality takes months. Cortex gives you all of it on day one.

Without Cortex

Separate API keys and billing for every provider
Manual failover when a model goes down
No visibility into cost-per-query or latency trends
Knowledge lives in disconnected documents
Weeks of engineering to build a basic RAG pipeline

With Cortex

One credit system across all 15 providers
Automatic failover with priority-based routing
Real-time dashboards for tokens, cost, and latency
Structured knowledge namespaces with graph analytics
Production-grade RAG pipeline with built-in evaluation

AI That Understands Your Domain

Cortex combines multi-provider model access with a fully managed knowledge pipeline, so your AI gets smarter with every document you add.

Find venues in Berlin that can host 500+ guests with outdoor space, and check availability for June.
I found 12 matching venues across your knowledge base. Here are the top 3 ranked by capacity, outdoor area, and June availability...Hybrid search across 2 namespaces, 340ms
15AI providers connected
7Search modes available
<400msMedian search latency
6Evaluation metrics tracked
HOW IT WORKS

Ingest. Search. Improve.

Cortex manages the full lifecycle from document ingestion to model evaluation, so your AI keeps getting better.

1

Ingest Your Knowledge

Upload documents, paste text, or point Cortex at URLs and sitemaps. Bulk ingestion handles up to 100 files at once with automatic chunking.

2

Search Intelligently

Choose from hybrid, semantic, keyword, conversational, agentic, or multi-namespace search. Each mode is tuned for different query patterns.

3

Evaluate & Improve

Build golden test sets, run evaluations with NDCG and MRR metrics, and A/B test models to ensure retrieval quality improves over time.

4

Visualise Your Graph

See how your knowledge connects through graph visualisations. Identify gaps, score relationship strength, and fill blind spots.

WHY CORTEX

The Only Marketplace That Trains On Your Data

Most AI marketplaces stop at API access. Cortex goes further with a full RAG pipeline, knowledge graph analytics, and continuous model evaluation built in.

๐Ÿง 

Hierarchical Knowledge Indexing

Documents are indexed at multiple levels of abstraction, so Cortex can answer both high-level strategy questions and granular detail queries.

๐Ÿ”—

Knowledge Graph Integration

Every ingested document is projected into a knowledge graph, enabling relationship-aware retrieval and gap analysis.

โš–๏ธ

Built-In Model Evaluation

Golden test sets and intelligent optimization ensure your retrieval quality keeps improving over time.

15 connected providers with automatic failover

Everything You Need to Operationalise AI

From model routing to knowledge management, Cortex covers the full stack.

Multi-Provider Routing

AWS Bedrock, OpenAI, Anthropic, Google, Cohere, Mistral, Groq, and 8 more. Cortex selects the best model per request based on use case, cost, and latency.

Seven Search Modes

Hybrid, semantic, keyword, conversational, agentic, multi-namespace, and streaming search. Each mode returns citations with source attribution.

Unified Credit System

One credit balance works across every provider. Search costs range from 1 to 15 credits depending on complexity, with full per-query tracking.

Flexible Ingestion

Upload files, paste raw text, scrape URLs, or ingest entire sitemaps. Chunking strategies include auto, fixed, semantic, and recursive options.

Automatic Failover

Provider health is monitored continuously. If one goes down, traffic reroutes to the next best option automatically, with no manual intervention.

Training Pipeline

Fine-tune retrieval models from user feedback, run quality evaluations, and A/B test configurations to continuously improve accuracy.

Knowledge Namespaces

Organise knowledge into separate namespaces by topic, team, or project. Search across one or many namespaces with Reciprocal Rank Fusion.

Namespace Marketplace

Publish your curated knowledge namespaces for other teams to subscribe to, with automatic wallet-based split payments.

Built for Real Event Workflows

Cortex powers AI across every stage of event planning and delivery.

๐ŸŽช

Event Planning & Strategy

Ask questions across your venue database and past event reports, Get culturally-aware recommendations for international events, Compare AI-generated proposals from multiple models

๐Ÿ“š

Knowledge Management

Ingest standard operating procedures, vendor contracts, and playbooks, Build team-specific knowledge namespaces with access control, Visualise knowledge connections and identify coverage gaps

๐Ÿค–

Custom AI Applications

Register AI model assets with benchmarks and cost-per-token pricing, Link marketplace listings to white-label portals for branded AI tools, Track token usage, latency, and cost per model in real time

๐Ÿงช

Continuous Improvement

Create golden test sets to benchmark retrieval accuracy, Run intelligent optimization to find the best parameters, A/B test model configurations with statistical significance

Inside Cortex

A closer look at the capabilities that make Cortex more than a model directory.

๐Ÿ”
Hybrid SearchCombines semantic embedding similarity with keyword matching and cross-encoder reranking for the most relevant results.
๐Ÿค–
Agentic SearchMulti-step, LLM-driven retrieval that plans a search strategy, executes multiple queries, and synthesises results into a coherent answer.
๐Ÿ’ฌ
Conversational SearchRewrites queries using conversation history for natural follow-up questions across multi-turn interactions.
๐ŸŒ
Multi-Namespace SearchQuery across multiple knowledge namespaces simultaneously with configurable fusion strategies: RRF, linear, or max.
๐Ÿ“Š
Graph AnalyticsKnowledge graph visualisations showing how documents relate, where gaps exist, and which connections are strongest.
๐Ÿ“ก
Streaming ResponsesServer-Sent Events deliver search results progressively, so users see answers appearing in real time rather than waiting for a complete response.
TOOLKIT

The Tools Behind Cortex

A purpose-built stack for AI-powered event intelligence.

๐Ÿ—๏ธ

Document Chunking Engine

Four chunking strategies (auto, fixed, semantic, recursive) ensure documents are split at natural boundaries for optimal retrieval.

๐ŸŒณ

Hierarchical Document Indexing

Hierarchical indexing creates multiple levels of abstraction per document, enabling both overview summaries and granular detail retrieval.

๐Ÿ”—

Knowledge Graph Projection

Every ingested document is projected into a knowledge graph, enabling relationship-aware queries and entity resolution.

๐Ÿ“

Evaluation Suite

Measure retrieval quality with NDCG@5, NDCG@10, MRR, MAP, precision, recall, and coverage metrics against golden test sets.

๐ŸŽฏ

Intelligent Parameter Optimization

Adaptive algorithms automatically find the best retrieval parameters for your specific data and query patterns.

๐Ÿ“œ

Citation & Verification

Every search result includes source citations with document references. Blockchain-based verification is available for audit-sensitive environments.

Connected to the EventZR Ecosystem

Cortex is not a standalone tool. It powers AI across the entire platform.

AI Providers

AWS Bedrock, OpenAI, Anthropic, Google AI, Cohere, Foundation Model Partners, Groq, Azure OpenAI, Replicate, Together AI, DeepSeek, Search AI Partners, Fireworks AI, Hugging Face, Anyscale

Platform Services

ZAR AI Chat, Cypher Co-Pilot, Portal Registry, Wallet & Credits, Search Service, Analytics

Knowledge Sources

File Upload (PDF, DOCX, TXT), URL Scraping, Sitemap Ingestion, Raw Text Input, Bulk Upload (100 files)

Infrastructure

Knowledge Graph, Vector Search, Caching, Event Streaming

ENTERPRISE

AI Infrastructure You Control

Cortex runs on the same multi-tenant, row-level-security infrastructure as the rest of EventZR. Your data stays yours.

๐Ÿ”’

Tenant Isolation

Every knowledge namespace, AI asset, and usage record is isolated at the database level with row-level security policies.

๐Ÿ’ฐ

Credit-Based Budgeting

Set credit budgets per team or per project. Every AI operation, from search to ingestion, deducts from the assigned wallet with full audit trails.

๐Ÿ›ก๏ธ

Role-Based Access

Admin, user, and super-admin roles control who can ingest documents, run evaluations, publish namespaces, or manage AI assets.

  • Row-level security on every table
  • Per-operation credit tracking
  • Subscription tier gating
  • Automatic provider failover
  • Full API audit trails
  • GDPR-compatible data handling
EARLY ACCESS

Get Early Access to Cortex

We are rolling out Cortex to teams who want to bring serious AI infrastructure to their event operations. Early access includes onboarding support and priority feature input.

Full multi-provider AI access from day one
Private knowledge namespaces with graph analytics
Built-in evaluation and training pipeline
Dedicated onboarding support
Try ZAR AI โ†’
CREDIT-BASED

Transparent, Usage-Based Pricing

Every AI operation costs a set number of credits. You always know what you are spending and where.

Base
Get started exploring
Free
  • 100 AI credits per month
  • Keyword and semantic search
  • File and text ingestion
  • Basic evaluation metrics
  • Agentic search
  • Multi-namespace search
  • Parameter optimization
  • Namespace marketplace
Pro
For production workloads
From $49/mo
  • 10,000 AI credits per month
  • All 7 search modes
  • URL and sitemap ingestion
  • Full evaluation suite
  • Agentic search
  • Multi-namespace search
  • Parameter optimization
  • Namespace marketplace
Enterprise
Full control at scale
Custom
  • Custom credit allocation
  • All 7 search modes
  • Bulk ingestion (100 files)
  • Full evaluation + A/B testing
  • Intelligent parameter optimization
  • Namespace marketplace access
  • WhatsApp-based human training
  • Dedicated onboarding

Credit costs per operation: keyword/semantic search = 1 credit, hybrid = 2-5, conversational = 3, multi-namespace = 2-5, agentic = up to 15, evaluation = 5, optimization = 10-50.

FAQ

Frequently Asked Questions

Common questions about AI marketplaces and knowledge management.

EventZR Cortex connects to 15 AI providers including AWS Bedrock, OpenAI, Anthropic, Google AI, and 11 others. The routing engine automatically selects the best model for each request based on use case, cost, and latency, with unified billing through a single credit system.

Cortex uses a credit-based system where every operation has a defined cost. You can set credit budgets per team or project, track consumption in real time, and view detailed analytics showing which operations cost the most. All spending is managed through wallet-based budgets with automatic enforcement.

Cortex provides a complete ingestion pipeline. Upload files, scrape URLs, ingest entire sitemaps, or paste raw text. Documents are automatically chunked, indexed at multiple abstraction levels, and projected into a knowledge graph. You can organize knowledge into separate namespaces and search across one or many with seven different search modes.

Yes. Cortex includes an evaluation suite that measures NDCG, MRR, MAP, precision, recall, and coverage against golden test sets. On higher tiers, intelligent optimization automatically finds the best retrieval parameters. You can also A/B test configurations to ensure quality improves continuously.

Cortex monitors provider health continuously. If one provider goes down or exceeds latency thresholds, traffic automatically reroutes to the next best option based on your configured priority list. This happens transparently with no manual intervention required.

No. All knowledge namespaces in Cortex are tenant-isolated with row-level security. Your documents are never shared with AI providers for training purposes. Data stays within your namespace and is only accessible to authorized users in your organization.

GET STARTED

Ready to Build Your AI Knowledge Stack?

Start with 100 free credits and your first knowledge namespace. No credit card required.

Try ZAR AI โ†’