DEV Community

#bedrock

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Field Notes: 25 seconds to detect and hand off. Nothing executes until a human says yes.

Field Notes: 25 seconds to detect and hand off. Nothing executes until a human says yes.

Comments
10 min read
Step Functions + Claude Tool Calls: Orchestrate AI Agents Without Lambda, Explained Simply

Step Functions + Claude Tool Calls: Orchestrate AI Agents Without Lambda, Explained Simply

1
Comments
8 min read
Claude Code on AWS Bedrock: Setup + Every Error You'll Hit (And How to Fix It)

Claude Code on AWS Bedrock: Setup + Every Error You'll Hit (And How to Fix It)

Comments
3 min read
A Field Guide to Beating Amazon Bedrock Throttling

A Field Guide to Beating Amazon Bedrock Throttling

Comments
9 min read
Building GenAI apps and AI agents on AWS: a hands-on path

Building GenAI apps and AI agents on AWS: a hands-on path

1
Comments
4 min read
Bedrock Guardrails Explained Simply: How to Enforce Safe LLM Outputs in Node.js

Bedrock Guardrails Explained Simply: How to Enforce Safe LLM Outputs in Node.js

1
Comments
7 min read
Build an Agentic AI Workflow on AWS: Generative AI for Production Automation

Build an Agentic AI Workflow on AWS: Generative AI for Production Automation

Comments
7 min read
Edge AI with CloudFront: How to Serve Claude Responses at the Edge Using Lambda Web Functions, Explained Simply

Edge AI with CloudFront: How to Serve Claude Responses at the Edge Using Lambda Web Functions, Explained Simply

1
Comments
10 min read
Temporal Policies in AgentCore: 98 Denied Deploys and a 409 That Never Came

Temporal Policies in AgentCore: 98 Denied Deploys and a 409 That Never Came

Comments
17 min read
LangGraph builds the agent. AgentCore runs it.

LangGraph builds the agent. AgentCore runs it.

Comments
8 min read
Opus 5.5 Leads a Four-Model OWASP Java Test by 7 to 9 Points. Kimi K3, GLM 5.3, and GPT-6 Sol Tie.

Opus 5.5 Leads a Four-Model OWASP Java Test by 7 to 9 Points. Kimi K3, GLM 5.3, and GPT-6 Sol Tie.

Comments
9 min read
The ML you need to operate LLMs, not train them

The ML you need to operate LLMs, not train them

Comments
6 min read
Before You Build an Agent: Five Amazon Bedrock Fundamentals, Measured

Before You Build an Agent: Five Amazon Bedrock Fundamentals, Measured

Comments
35 min read
Claude Tool Use Explained: How to Let the Model Call Your API from Node.js

Claude Tool Use Explained: How to Let the Model Call Your API from Node.js

1
Comments
8 min read
I Gave My Agent a Deployment Tool. It Could Finally Answer.

I Gave My Agent a Deployment Tool. It Could Finally Answer.

Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.