Build Agents That Think, Act, and Learn

View as Markdown

Choose your LLM provider, set autonomy boundaries, define tool access, and deploy production-grade agents that handle real-world tasks end-to-end.

Multi-LLM support

Switch between Anthropic, OpenAI, Google, Amazon Bedrock, DeepSeek, Mistral, Groq, xAI, OpenRouter, Qwen, Moonshot AI, Ollama (local), and custom OpenAI-compatible endpoints. Each agent can use a different, independently-configured provider.

Autonomy configuration

Three autonomy levels: Supervised approves every action before it runs, Semi-auto approves the plan up front and then executes it without further check-ins, and Autonomous runs end to end with no approval step at all.

Templates

Six pre-built templates to start from: Customer Support Agent, Research Assistant, Content Creator, Lead Generation Agent, Personal Assistant, and Discovery Agent.

Per-agent integrations

Each agent gets its own set of connected integrations, assigned individually, with no forced overlap between agents doing different jobs. See Integrations for the full catalogue.

Scheduled execution

Monitors let an agent run autonomously on a schedule, not just in response to a message.

Planning and delegation

A complex instruction becomes a plan you approve before it runs, and any agent can delegate part of that plan to another agent it has access to.

Technical specifications

Maximum context window varies by model: current-generation models support up to roughly 1 million tokens; see Models for what each provider offers
625 tools available via connected integrations
Agent capacity depends on your plan: Trial allows 1 agent, Core allows 3, Scale is unlimited, and Nexus is set by your license
Every configuration change is saved as a version automatically, for audit purposes

Core Concepts: how agents relate to conversations, tools, and memory
First Setup: creating your first agent
Models: choosing a provider and model for an agent