A full-stack agentic harness on AWS — spin up multi-agent chatbots, voice-to-voice AI, RAG, and an Agent Factory on Bedrock AgentCore. From idea to deployed agent, fast.
aws-samples/sample-agentic-chatbot-accelerator is a full-stack AWS system for designing, deploying, testing, and improving multi-agent chatbots with text, voice, retrieval, and evaluation components. Developers use its Agent Factory, managed runtime, web interface, tool and MCP-server connections, and feedback workflows, with the catalogue containing add-ons for working with the accelerator.
12 files for Claude Code: sample-agentic-chatbot-accelerator, ai-dlc, commit, design-doc and 8 more — 1,413 tokens loaded in every session.
CLAUDE.md A 1,413 tok .claude/settings.json A — .claude/skills/ai-dlc/SKILL.md A 27 tok .claude/skills/commit/SKILL.md A 12 tok .claude/skills/design-doc/SKILL.md A 22 tok .claude/skills/iac-config-generator/SKILL.md A 140 tok .claude/skills/mirror-cdk-to-terraform/SKILL.md A 120 tok .claude/skills/prep-pr/SKILL.md A 103 tok .claude/skills/spec-design/SKILL.md A 39 tok .claude/skills/story-new/SKILL.md A 23 tok .claude/skills/story-refine/SKILL.md A 19 tok .claude/skills/tasks/SKILL.md A 22 tok These files are aws-samples/sample-agentic-chatbot-accelerator's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.