ai-agents

When a coding agent underperforms, the reflex is a stronger model. On bounded tasks the harness moves the score at least as much; a rule for which lever to pull.

ai-agents · ai-tools · llm +3

How AWS Dogwood adds temporal conditions to Cedar policies, lowers them back to plain Cedar, and enforces agent guardrails at the Amazon Bedrock AgentCore gateway.

authorization · security · ai-agents +2

Agents made code-writing essentially free, but judgment about when and how much to use them is still entirely yours. An Aristotelian frame to separate the two skills.

ai-tools · claude-code · ai-agents +3

A CDK guide for deploying a minimal Strands agent on AgentCore Runtime: parameterized stack, arm64 build, deploy and invoke, with IAM and Marketplace prerequisites.

aws-bedrock · ai-agents · aws-cdk +3

A practical repo layout that keeps Claude Code, Codex, Copilot, Cursor, and OpenCode reading the same rules, with honest notes on where portability breaks.

ai-tools · claude-code · github-copilot +3

How Zapier MCP gives AI agents action-level whitelisting, credential isolation, and human-in-the-loop approval, a managed alternative to custom scoped proxies.

mcp · security · ai-agents +4

Why production teams replace broad MCP access with scoped API proxies. Atlassian, Google Workspace, and Notion via FastAPI proxy, CLI wrapper, and n8n.

mcp · api-design · python +4

An implementation-focused glossary for developers navigating the AI/LLM landscape - from tokens to agents, RAG to fine-tuning, with code examples.

llm · ai-agents · rag +6

Securing AI agents in production with AWS Bedrock Guardrails, defense-in-depth, and patterns that prevent prompt injection, tool misuse, and multi-agent attacks.

ai-agents · aws-bedrock · security +3

The architectural evolution from rule-based chatbots to autonomous AI agents, covering ReAct, Plan-and-Execute, and multi-agent patterns in TypeScript.

ai-agents · llm · architecture +2

Build production serverless workflows with Step Functions: Standard vs Express, Distributed Map, error handling, and cost optimization with working CDK examples.

step-functions · aws-cdk · serverless +4

Lessons from running LangChain in production: the anti-patterns that cause failures, the patterns that work, with code examples and cost optimization strategies.

langchain · llm · production +5

How AWS Bedrock AgentCore solves the infrastructure challenges of deploying agentic AI at scale, with runtime, memory, gateway, and multi-agent coordination.

aws-bedrock · ai-agents · aws +3

How GitHub's Spec Kit turns loose AI code generation into structured, maintainable output through a four-phase specify-plan-tasks-implement loop.

ci-cd · ai-tools · code-quality +4