AWS Archives - Page 20 of 23

Bedrock Converse API: Tool Choice Modes for Production Coding Agents

Bedrock Converse Tool Use for Coding Agents: toolChoice Modes and Strict JSON Tool Contracts

Bedrock Converse tool use for coding agents: toolChoice auto/any/tool, strict tool schemas, typed toolResult errors, versioned tools and a safe agent loop.

Cursor Rules for AWS CDK: Stop AI From Inventing IAM Wildcards

AI AWS

Cursor Rules Aws Cdk: Stop AI From Inventing IAM Wildcards

A senior-engineer guide to Cursor rules AWS CDK, with production-ready patterns, trade-offs, and practical examples.

AI AWS Debugging

LLM Incident Runbooks: Ground On-Call Answers in CloudWatch Signals

A senior-engineer guide to LLM incident runbooks, with production-ready patterns, trade-offs, and practical examples.

Lambda Powertools for Node: Structured Logs That Survive On-Call

AWS

Lambda Powertools Node.Js: Structured Logs That Survive On-Call

A senior-engineer guide to Lambda Powertools Node.js, with production-ready patterns, trade-offs, and practical examples.

Lambda Timeouts, Retries, and DLQs: Idempotent Failure Handling

AWS

Lambda Timeouts Retries: Idempotent Failure Handling

A senior-engineer guide to Lambda timeouts retries, with production-ready patterns, trade-offs, and practical examples.

Lambda Cold Starts on Node 20: Measure, Cut, and Keep Cutting

AWS

AWS Lambda Cold Starts on Node.js and Python: Measure, Cut, and Keep Cutting

Measure and cut AWS Lambda cold starts on Node.js and Python: Init Duration, bundling, lean imports, memory, SnapStart and provisioned concurrency.

AI AWS Machine Learning

AI Code Review Bot IAM: Least-Privilege Secrets and Pipelines

AI code review bot IAM done right: GitHub App tokens, scoped Bedrock InvokeModel, Secrets Manager, and ephemeral jobs that see a PR diff — not monorepo admin PATs.

AI AWS Machine Learning

Amazon Bedrock Prompt Caching and Batch Inference: Cut Coding-Agent Latency and Cost Without Stale Rules

Bedrock prompt caching vs batch inference for coding agents: cachePoint placement, TTL, usage fields, JSONL batch jobs and stale-rule pitfalls.

AI AWS Machine Learning

OpenSearch vs pgvector vs S3 Vectors for Codebase RAG on AWS

OpenSearch vs pgvector vs S3 Vectors for code RAG on AWS: filtered ANN, pgvector iterative scans, OpenSearch hybrid search with RRF, S3 Vectors metadata pre-filtering, freshness and recall evaluation.

AI AWS Machine Learning

AWS Lambda Coding Agent Sandbox: Safe Tool Isolation for LLM Agents

Build an AWS Lambda coding agent sandbox: ephemeral tool Lambdas, tiny IAM, deny-by-default networking, and structured results — so agents can run tests without owning the account.