OpenTelemetry for LLMs: Trace Prompt Latency Across Microservices
A senior-engineer guide to OpenTelemetry for LLMs, with production-ready patterns, trade-offs, and practical examples.
LLM Cost Controls on Bedrock: Token Budgets per PR and per Engineer
Token budgets per PR and per engineer on Amazon Bedrock: attribution with requestMetadata and inference profile tags, reserve/settle enforcement, EMF metrics, Budgets actions.
Appsync Bedrock: GraphQL Resolvers That Call Tools Safely
A senior-engineer guide to AppSync Bedrock, with production-ready patterns, trade-offs, and practical examples.
Bedrock Batch Inference for Overnight Refactors: Shard, Run, Validate and Apply in Daytime PRs
Overnight repo refactors with Bedrock batch inference: package shards, Converse-format JSONL, job IAM, result parsing, offline validation and daytime stacked PRs.
Posted inAI AWS Machine Learning
SageMaker JumpStart vs Bedrock: When Fine-Tuning Beats Prompting and RAG for Coding Assistants
SageMaker JumpStart vs Amazon Bedrock fine-tuning for coding assistants: decision gate, SFT vs RAG, Bedrock-conversation-2024 data, Nova hyperparameters, on-demand deployment and evaluation.
Amazon Bedrock Guardrails: Block Prompt Injection Inside Internal Dev Tools
A senior-engineer guide to Amazon Bedrock Guardrails, with production-ready patterns, trade-offs, and practical examples.
Posted inAI AWS Machine Learning
Bedrock Knowledge Bases Chunking Strategies That Fit Code RAG
Bedrock Knowledge Bases chunking for code RAG: prefer AST-aware symbol chunks, metadata filters, and hit-rate@k evals over fixed 300-token windows that shred functions mid-signature.
Amazon Q Developer: Custom Context Packs for Private Monorepos
A senior-engineer guide to Amazon Q Developer, with production-ready patterns, trade-offs, and practical examples.
Posted inAI AWS Machine Learning
Codebase Embeddings: Refresh Pipelines When Git SHAs Keep Moving
A senior-engineer guide to codebase embeddings, with production-ready patterns, trade-offs, and practical examples.
Posted inAI AWS Machine Learning
Rag Evaluation Aws: Hit Rate, Faithfulness, and Cost Curves
A senior-engineer guide to RAG evaluation AWS, with production-ready patterns, trade-offs, and practical examples.