Is LoyJoy a chatbot or an Agentic-AI platform?

Both. We combine AI agents, BPMN orchestration, and MCP to go from answers to actions.

Can we bring our own LLM?

Yes. Use OpenAI/Azure OpenAI on your own subscription and manage prompts, policies, and data access. Also available: Anthropic Claude, Google Gemini, Mistral as well as open-source models like GLM and Kimi.

Is it ensured that AI responses don't reveal unwanted information?

Yes. The AI can only output information provided in the knowledge database. In each agent, you can precisely select which sources it may access.

Can the AI hallucinate?

LoyJoy minimises hallucinations systematically: AI Agents respond exclusively based on your curated knowledge sources, guardrails limit outputs, and integrated AI testing continuously checks response quality. A 100-percent guarantee does not exist with probability-based systems. That is why we make quality measurable instead of promising it.

Are regulations like GDPR, DORA, BFSG, and the EU AI Act met?

Yes, all requirements are met. Detailed information can be found in our Trust Center at /en/trust-center.

How long does an AI Agent implementation take?

We aim to go live with the first agent in 2 to 4 weeks, from kickoff to go-live. Since LoyJoy is a no-code platform with many templates, you can often try a first version in just 15 minutes. It takes longer only due to legacy system integration, fine-tuning AI responses, process exception handling, and role and rights concepts.

What's the difference between a chatbot and an AI agent?

Traditional chatbots follow predefined paths and only respond. AI agents understand natural language, make decisions, and execute actions, from database queries to system integrations. They orchestrate complex business processes via BPMN and can securely access external tools and APIs through MCP.

How does live-chat work with automation?

Asynchronous handover with full context and notifications; humans step in only when needed.

What compliance requirements does the LoyJoy Platform meet?

The LoyJoy Platform meets comprehensive compliance requirements: GDPR compliance through Privacy by Design, EU hosting in Germany, AI-Act-compliant governance with configurable guardrails, DORA-aware operations for financial services, and encryption in transit and at rest. Detailed information on all compliance aspects can be found in our Trust Center at /en/trust-center.

Can I connect my LoyJoy tenant to Claude or ChatGPT?

Yes. Every LoyJoy AI Agent is simultaneously an MCP server from the Professional plan onwards. You can connect your tenant to Claude Desktop, ChatGPT, Gemini, Cursor, or your own MCP client and query analytics, processes, your knowledge base, and other resources in natural language. Implementation support by our project team available on request.

Agentic AI Platform with MCP and no-code BPMN

LoyJoy Platform, AI agent in conversation with a customer

Conversational Agentic AI Platform

The simplest enterprise platform for Agentic Customer Service and Sales

Enterprise strength with self-service simplicity: your business team builds AI Agents itself, a prototype is ready in 15 minutes. AI Agents that resolve customer requests end-to-end via phone and chat, on the phone with a natural voice, low latency, and real-time barge-in. When humans are needed, they hand over seamlessly to your live agents. No-code BPMN for your service and sales processes, IT keeps governance and integrations in hand. MCP for the agentic web, EU hosting, GDPR and AI-Act compliant.

The 3-layer platform for Agentic AI

What is LoyJoy?

AI Agents (Act): Generative AI answers questions, runs tools, and works with your enterprise data. Bring your own LLM (OpenAI/Azure OpenAI) or use pre-integrated options.
Process Orchestration (Orchestrate): A no-code BPMN engine models dialogs and processes, with rules, routing, experiments, and analytics.
Integration Layer (Connect): MCP and native connectors link CRMs, DWHs, PIM, payment, and custom REST/GraphQL services.

Why Agentic AI now?

Companies have identified Agentic Customer Service as a strategic priority. But the available tools fall short: rule-based chatbots fail on complex processes, LLM wrappers hallucinate, and integration with existing systems is missing. Building it in-house with cloud toolkits or internal LLM teams produces impressive demos, but rarely end-to-end, auditable processes, while the business team waits in the IT queue again. LoyJoy closes this gap. Our AI Agents securely connect AI with your knowledge sources, product data, and existing systems, so customer requests lead to actions under your governance, traceable, compliant, and measurable.

Core capabilities

Platform Features

AI Agents & Knowledge: Curated sources (PDF/DOCX/XLSX/PPTX, websites, knowledge bases). Guardrails and prompts you control. Optional BYO-LLM (OpenAI/Azure OpenAI, Anthropic, Google, Mistral, or open-source).
Latest AI Models: Always access to the latest AI models: GPT-5.5, Mistral Large 3 as well as open-source models like GLM-5.1 and Kimi K2.6.
AI Quality Check: AI reviews your dialogs and highlights optimization potential and missing data, for better deployment quality.
No-Code BPMN 2.0: Design dialog flows and real processes: conditions, loops, webhooks, human-in-the-loop.
AI Testing Automation: Upload test questions for automatic simulation, no manual chat operation needed. Quick verification for model or knowledge base changes.
Smart Product Advisor: GPT Recommender builds intelligent product advisors without programming, with follow-up questions, product suggestions, availability, and add-to-cart.
AI Phone Agents (Voice): AI agents on the phone that resolve requests end-to-end: low latency, natural voices, barge-in, and SIP telephony connection. Same agent as in chat, 40 languages, seamless handover to live agents.
Multi-Channel Deployment: Build once, deploy everywhere: web chat, WhatsApp, social messengers. Same AI Agent works across all channels, responsive, accessible, screen reader compatible.
OAuth Authentication in Chat: Secure customer identification with OAuth providers (Azure Active Directory, Keycloak), restrict access to registered users.
Avatar Integration: HeyGen, D-ID, and VidLab7 avatars integrate seamlessly into LoyJoy agents, for personalized and engaging customer experiences.
Live-Chat & Handover (async): Seamless switch from automation to human agents; users get notified and can continue later.
Versioning & Control: View history of your changes, restore older versions, the last five versions are always saved for complete project control.
Enterprise Role & Rights Management: Fine-grained user permissions and roles for large organizations, full control over access and authorizations.
MCP: Bidirectional Access: Every LoyJoy AI Agent is an MCP server, in both directions. Outbound: external AI agents access your services end-to-end. Inbound: Access LoyJoy Analytics and your Agents, directly in Claude, ChatGPT, or Gemini.
Multi-Language & Localization: 40 languages available including German, English, Spanish, French, Chinese, and Arabic (RTL), global rollouts and local adaptations.
Privacy, Security & Compliance: EU hosting, designed for GDPR, the EU AI Act, DORA and BFSG. For chat, LoyJoy hosts its own LLM (Gemma 4) in Germany. Encryption in transit and at rest, accessibility per WCAG 2.1 AA.

How LoyJoy works (3 steps)

From Connection to Resolution

1. Connect: Attach systems and data (CRM, ERP, DWH, PIM, ticketing) via connectors, MCP tools, or REST.
2. Orchestrate: Model dialog and business flow in BPMN, add rules and approvals, define guardrails.
3. Resolve: Let agents execute tasks end-to-end; hand over to humans when needed; measure KPIs in analytics.

Process Engine

Customer-facing AI Agents, built without coding

The LoyJoy Platform connects agentic AI and process automation at the customer interface. With over 100 business process modules, processes are realized. AI can execute these autonomously, within defined guardrails.

Excerpt from the 100 process modules:

Appointment booking, PDF creation, NPS, questionnaires, surveys, product gallery, photo upload with AI image recognition, scanner (e.g., barcodes, QR codes), opt-in collection, loyalty program, coupon codes, contests, quizzes, Google Maps, and many more.

Process Engine with 100+ business modules

Agentic AI

More powerful experiences, simpler for business

Agentic AI at LoyJoy enables more powerful experiences for customers, while maintaining simplicity for business.

Choose your preferred LLM

GPT-5.5, Mistral Large 3 as well as open-source models like GLM-5.1 and Kimi K2.6.

Use standard instructions

Large selection of ready-to-use instructions that give your agent personality, task structure, and guardrails.

Integrated tools

Knowledge search via RAG in your knowledge database and other tools integrated in LoyJoy.

AI Phone Agents

Voice service that actually resolves requests, not just routes them

The same AI Agent you build for chat also answers calls. It understands natural language, accesses your existing systems, and resolves requests end-to-end on the phone. When a human is needed, it hands over with full context to your live agents.

Natural conversation

Low latency, high-quality voices, and barge-in, customers can interrupt and are understood as in a real dialogue.

Your telephony, your data

Connect to your phone system (SIP) and existing systems via MCP and connectors. EU hosting, GDPR and AI-Act compliant.

One agent, all channels

Phone, chat, WhatsApp, and messengers from one model. 40 languages, built once, available everywhere.

Loy + Joy

Loyalty grows when requests are resolved. Joy grows when it feels effortless.

LoyJoy resolves requests end-to-end, that creates trust and loyalty. And customers whose problem is solved in seconds instead of minutes experience something rare: real joy in interacting with a company. That is what Loy and Joy stand for in our name. And that joy starts at build time: the first own AI Agent is often ready in 15 minutes, built by your business team, not by IT. Beyond that, the LoyJoy chat UI provides a high-quality, accessible interface, fully customisable to your brand, responsive and WCAG 2.1 AA-compliant. Because excellent customer experience comes not only from the outcome, but also from the journey there.

Templates & Use Cases

Ready-to-run templates

For Insurance, Banking/Finance, Energy & Utilities, B2B Manufacturing/MedTech, E-Commerce, and HR.

Phone Agent for Insurers

Claim intake, address change, status inquiry, and pre-qualification resolved end-to-end on the phone, with secure identification (OAuth) and handover to the right case handler.

Service Agent

Address change, appointment, claim/incident intake, ticket deflection with AI Quality Check.

Smart Product Advisor

GPT Recommender for intelligent product advice, customers describe needs, bot asks follow-up questions and suggests matching products. Optional with avatar integration.

HR & Careers

Candidate Q&A, role matching, and pre-qualification with automated test simulation.

Onboarding & CX Journeys

Welcome flows, ID capture, consent, and follow-up with complete version control.

Start with a template

Built for teams

Platform for Every Role

Business & CX: Launch journeys without code, own copy and variations, iterate with A/B tests. AI Quality Check supports optimization efforts.
IT & Security: Standardized integrations, identity, observability, SLAs, policies. Enterprise role & rights management for large organizations.
Ops: Multi-tenant rollout, localization in 40 languages, change control, releases. Complete versioning with history and OAuth authentication for secure user management.

Outcomes you can measure

Measurable Business Impact

Case closure

Automated resolution rates and time-to-resolution.

Deflection

Reduced call/chat volume; improved self-service share.

Conversion

Qualified leads, applications, or purchases via Product Finder.

CX

CSAT & NPS post-interaction; first-contact resolution.

FAQ

: Both. We combine AI agents, BPMN orchestration, and MCP to go from answers to actions.
: Yes. Use OpenAI/Azure OpenAI on your own subscription and manage prompts, policies, and data access. Also available: Anthropic Claude, Google Gemini, Mistral as well as open-source models like GLM and Kimi.
: Yes. The AI can only output information provided in the knowledge database. In each agent, you can precisely select which sources it may access.
: LoyJoy minimises hallucinations systematically: AI Agents respond exclusively based on your curated knowledge sources, guardrails limit outputs, and integrated AI testing continuously checks response quality. A 100-percent guarantee does not exist with probability-based systems. That is why we make quality measurable instead of promising it.
: Yes, all requirements are met. Detailed information can be found in our Trust Center at /en/trust-center.
: We aim to go live with the first agent in 2 to 4 weeks, from kickoff to go-live. Since LoyJoy is a no-code platform with many templates, you can often try a first version in just 15 minutes. It takes longer only due to legacy system integration, fine-tuning AI responses, process exception handling, and role and rights concepts.
: Traditional chatbots follow predefined paths and only respond. AI agents understand natural language, make decisions, and execute actions, from database queries to system integrations. They orchestrate complex business processes via BPMN and can securely access external tools and APIs through MCP.
: Asynchronous handover with full context and notifications; humans step in only when needed.
: The LoyJoy Platform meets comprehensive compliance requirements: GDPR compliance through Privacy by Design, EU hosting in Germany, AI-Act-compliant governance with configurable guardrails, DORA-aware operations for financial services, and encryption in transit and at rest. Detailed information on all compliance aspects can be found in our Trust Center at /en/trust-center.
: Yes. Every LoyJoy AI Agent is simultaneously an MCP server from the Professional plan onwards. You can connect your tenant to Claude Desktop, ChatGPT, Gemini, Cursor, or your own MCP client and query analytics, processes, your knowledge base, and other resources in natural language. Implementation support by our project team available on request.

Ready to move from answers to outcomes?

Book a 30-minute demo and see Agentic AI in action with your own use case.

Book a demo Try it yourself