Introduction

​

What is Bedrock?

Bedrock handles the hard parts of building AI agents:

• Persistent Memory: Agents remember conversations across sessions with automatic summarization
• Tool Execution: Connect agents to SMS, email, calendars, or your own APIs via webhooks
• Autonomous Runtime: Agents run independently, waking and sleeping on schedules
• Full Observability: Every LLM call, tool invocation, and decision is traced

See a demo video here

​

Core Architecture

• Organization — your top-level account
  • Product — one per application, holds shared configuration
    • LLM Provider Keys (OpenAI, Anthropic)
    • System Prompt
    • Adapters (tool integrations)
    • Agent 1, Agent 2, … — deployed instances, each with its own Memory, State, and Tools

​

Key Concepts

• Product — Your application’s configuration template: system prompt, LLM keys, adapters. Configure it once in the portal.
• Agent — A deployed instance of your product with its own memory, contacts, and state. Create one per end-user.
• Adapter — An integration module (SMS, Email, CRM, etc.) that gives agents tools.
• Tool — A callable function an agent can invoke, either built-in or a webhook to your API.

​

Built-in Adapters

Bedrock includes these default integrations:

​

Custom Integrations

Build your own adapters to connect agents to any system:

1. Create an adapter — a named container for related tools
2. Add webhook tools — each tool POSTs to your API when called
3. Verify requests — check the X-Agent-Secret header to authenticate
4. Return data — your JSON response becomes the tool result the agent sees

See Custom Adapters for a full walkthrough.

​

How Agents Run

1. Wake agent (API call or scheduled)
2. Load memory context
3. Build prompt with tools
4. Call LLM (OpenAI/Anthropic)
5. Execute tool calls
6. Log to memory
7. Repeat until agent sleeps

Agents are autonomous—they decide when to sleep and what actions to take based on their tools and memory.

​

Use Your Own LLM Keys

Bedrock uses your LLM provider accounts:

• You control costs directly with OpenAI/Anthropic
• Use any model available on your account
• Prompt caching with Claude reduces costs significantly

​

Quick Links