Compose agents from reusable building blocks
Snap together datasets, skillsets, integrations, and models to assemble exactly the agent you need - then reconfigure it as fast as your product changes.
Building Blocks
The reusable parts behind every agent
Each block is defined once and reused across agents. Mix and match them to build exactly what you need.
Datasets
Ground agents in your knowledge. Upload documents, sync sources, and retrieve with built-in vector search and RAG.
Skillsets & Abilities
Give agents actions. Compose skillsets from 150+ pre-built abilities or wire in your own functions and APIs.
Integrations
Connect everything. Messaging channels, CRMs, databases, and custom APIs with built-in OAuth and MCP support.
Blueprints
Design visually. Assemble behavior, memory, and tools into a reusable Blueprint, then clone and remix it.
Models
Bring any model. OpenAI, Anthropic, Mistral, or your own - swap providers without rewriting your agent.
Spaces & Widgets
Deploy anywhere. Embed widgets, launch spaces, or ship to Slack, Discord, and WhatsApp from the same agent.
How It Works
From blocks to a running agent in four steps
Compose visually or in code. Both operate on the same reusable blocks.
Pick
Choose the building blocks your agent needs - datasets, skillsets, integrations, and a model.
Compose
Snap them together in a Blueprint. No glue code and no infrastructure to wire up.
Deploy
Ship to any channel - web widget, Slack, WhatsApp, API, or your own custom interface.
Reconfigure
Swap a model, add a skillset, or repoint a dataset as fast as your product changes.
Composable by design
Every capability is a managed, reusable block. Assemble production agents instead of plumbing infrastructure together.
pre-built building blocks ready to snap into any agent
connectors to channels, APIs, and data sources
one interface to compose with, swap anytime
a managed engine so you never touch infrastructure
Composable vs. Monolithic
Rebuild every time or reconfigure in minutes
A monolithic agent ties knowledge, tools, and channels into one rigid build. Composable blocks let you change one part without touching the rest.
FAQ
See the most frequently asked questions about composing agents from reusable building blocks on ChatBotKit.
What does it mean to compose an agent from reusable building blocks?
Instead of writing an agent from scratch, you assemble it from modular parts - datasets for knowledge, skillsets and abilities for actions, integrations for channels and APIs, a model of your choice, and a Blueprint that ties it all together. Each block is reusable across agents, so you build once and remix everywhere.
What are the core building blocks on ChatBotKit?
The main blocks are Datasets (knowledge and RAG), Skillsets and Abilities (tools and actions), Integrations (messaging channels and 150+ third-party providers), Blueprints (the visual design that composes an agent), Models (bring any provider), and Spaces and Widgets (where the agent is deployed). You mix and match them to build exactly the agent you need.
Can I reuse the same building blocks across multiple agents?
Yes. A dataset, skillset, or integration is defined once and can be attached to any number of agents. Update the block in one place and every agent that uses it picks up the change, so you avoid copy-and-paste drift.
Do I need to write code to compose an agent?
No. The visual Blueprint designer lets you snap building blocks together without code. Developers who want full control can do the same thing through the SDKs and API, and both approaches operate on the same blocks.
Can I swap the model or add a tool without rebuilding the agent?
Yes. Models, skillsets, abilities, and integrations are independent blocks, so you can switch from one provider to another or add a new tool without rewriting your agent logic. Reconfiguration is meant to be as fast as your product changes.
Which models and providers can I compose with?
ChatBotKit supports multiple model providers including OpenAI, Anthropic, Mistral, and your own custom or self-hosted models. You pick the model that fits each agent and change it later without touching the rest of the composition.
How is this different from building on raw LLM APIs?
Building directly on raw APIs means wiring up retrieval, tool calling, channel integrations, streaming, security, and observability yourself, then maintaining all of it. ChatBotKit provides those as managed, composable blocks on a single platform, so you assemble production agents instead of plumbing.
Is the platform secure and production-ready?
Yes. Every agent runs through configurable content moderation, PII filtering, policies, and access controls, with full observability and analytics built in. Security and governance wrap every block, so production behavior stays visible and controlled.
Blocks for everything you use
Connect your composed agents to the tools you already run. Messaging platforms, CRMs, databases, and custom APIs - all from a single platform.
Platform Features
Discover the building blocks and capabilities that make ChatBotKit a complete platform for composing production AI agents.
Customer Stories
Case studies from teams shipping AI
See how organizations use ChatBotKit to launch production AI assistants, validate new products, support customers, and create richer digital experiences.
Enterprise search
Quench
Discover Quench.ai, the enterprise search company founded by Husayn Kassai, the serial entrepreneur behind Onfido. Quench helps large organizations unify and discover their internal knowledge through natural language search. Built on ChatBotKit's Forward Deployment platform - the environment powering the "Quench Sandbox" - Quench prototypes, runs discovery, and validates AI products with real customers in days rather than quarters. Learn how this approach delivered 10x faster prototyping and won major enterprises including Yum Brands, MotorK, Podium, and numerous Fortune 500 companies, turning rapid customer iteration into a sustainable competitive advantage.
Healthcare charity
Debra
DEBRA UK is the leading charity for individuals with epidermolysis bullosa (EB), a rare genetic skin condition. Committed to providing lifelong care and seeking cures, DEBRA supports nearly 4,000 members across the UK. With over £22 million invested in research, DEBRA is the largest UK funder of EB studies. The organization addresses the complex information needs of patients and caregivers by offering reliable resources and support. Learn about DEBRA's innovative chatbot, providing 24/7 assistance for inquiries about EB, fundraising, and support services, ensuring accurate and compassionate communication. Explore DEBRA's mission to improve lives and advance research for those affected by EB.
Education wellbeing
Elggo
Discover Elggo, the MENA and Southeast Asia region's first AI-powered wellbeing platform for K–12 schools. Founded after the COVID-19 pandemic to close a gap in culturally relevant mental-health resources, Elggo delivers evidence-based curricula designed by regional psychologists and educators. By integrating ChatBotKit's conversational AI, embeddable widget, and multilingual support, Elggo provides students and teachers with always-on, personalized guidance on emotional literacy, decision-making, and growth mindset. Learn how a controlled trial of 12,000 students across 32 schools saw a 30% increase in student wellbeing, and how the platform scaled across seven countries while keeping content culturally responsive and data-driven.
Cultural heritage
Faro
Discover FARO, the Flemish government's cultural heritage organization, which enhances access to heritage collections through its innovative ErfgoedApp. Launched in 2015, the app utilizes augmented reality, IoT, and AI to provide on-site, multilingual guidance for museums and heritage sites. In celebration of its 10th anniversary, FARO has partnered with ChatBotKit to introduce AI chatbots, transforming the app into an on-demand heritage guide. Visitors can ask questions about artworks and historic landmarks at any time, while geofencing technology provides location-aware storytelling. With plans to expand this interactive experience across more sites, FARO is committed to making heritage discovery intuitive and personalized for everyone.
Customer service
Intelliway
Discover Intelliway, a Brazilian technology firm building AI-powered customer service solutions for businesses across Brazil and Latin America. Using ChatBotKit's API-first platform as their backend, Intelliway builds custom-branded interfaces on top of powerful conversational AI while retaining full control over the customer experience. Learn how native Brazilian Portuguese understanding, scalable cloud infrastructure, and advanced language models help Intelliway serve hundreds of clients across multiple industries, with one major retail client reporting a 40% increase in positive customer feedback. Explore how the platform-as-a-backend approach positions Intelliway to lead conversational AI across the Americas.
Ready to compose your agent?
Talk to our team. We will help you pick the right building blocks, connect your data, and get to production fast.