Amazon Bedrock Agents for building autonomous AI agents with foundation model orchestration, action groups, knowledge bases, and session management.
SkillScore100Maintained
Automatic
◆AI Engineer pack
Last verified 8/18/2026
What it changes
Passed 22 of 22 test cases with the skill, and 21 of 22 without it.
Without skill95%
With skill100%
Checks it passed that the model alone missed
Identifies VERSIONED as a successful readiness status
1 fixed21 passed either way0 still failing0 broke
Pass-rate lift
+5 pp
Tokens
+847%
Agent turns
0%
Response time
-24%
Model gemini-3.6-flashMeasured 8/18/2026v122 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
A test case the skill fixed. Same model, same prompt, with and without the skill.
Prompt
After calling `prepare_agent` on an Amazon Bedrock Agent in Python, our deployment script polls `get_agent` until the status changes from `CREATING` or `PREPARING`. Which status values returned in `agentStatus` indicate that the agent is ready for use or alias creation?
What was checked, without and with the skill
Checked
Without skill
With skill
Identifies PREPARED as a successful readiness status
Passed
Passed
Identifies VERSIONED as a successful readiness status
Missed
Passed
case-19 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md1374 linessingle file
Amazon Bedrock Agents
Complete guide to building and managing Amazon Bedrock Agents - autonomous AI agents that orchestrate foundation models with action groups, knowledge bases, and multi-turn conversations.
Overview
Amazon Bedrock Agents enables you to create autonomous AI agents that can:
Orchestrate foundation models to execute multi-step tasks
Integrate with APIs and Lambda functions via action groups
Access enterprise knowledge through knowledge bases (RAG)
Maintain conversation context across sessions
Reason about complex problems and break them into steps
Invoke tools and APIs based on natural language requests
Control Plane: bedrock-agent client for agent configuration
Runtime Plane: bedrock-agent-runtime client for agent invocation
Core Concepts
Agents
The foundation model orchestrator that processes requests, plans actions, and coordinates responses.
Key Properties:
Agent name and description
Foundation model (Claude, Titan, etc.)
Instructions (system prompt defining behavior)
Action groups (tools the agent can use)
Knowledge bases (data sources for RAG)
Aliases (deployment versions)
Action Groups
Define tools and APIs the agent can invoke to accomplish tasks.