Lambda Warm Pools: Low-Latency Backends for Coding Agent Tools
A senior-engineer guide to Lambda warm pools, with production-ready patterns, trade-offs, and practical examples.
Posted inAI
AI Pair Programming Metrics: Cycle Time Without Vanity Accept Scores
A senior-engineer guide to AI pair programming metrics, with production-ready patterns, trade-offs, and practical examples.
Bedrock Knowledge Base Sync: Git Webhooks That Prevent Index Drift
A senior-engineer guide to Bedrock knowledge base sync, with production-ready patterns, trade-offs, and practical examples.
Posted inAI
Jira Prompt Injection: Sanitize Jira Before Agents Read Issues
A senior-engineer guide to Jira prompt injection, with production-ready patterns, trade-offs, and practical examples.
Spec-First AI Development: Keep OpenAPI the Only Source of Truth for Coding Agents
Spec-first AI development with OpenAPI: generated TypeScript types, agent impl-region gates, JSON Patch spec proposals, route drift tests and oasdiff breaking-change checks in CI.
Glue Bedrock Rag: Offline Doc Enrichment Before Online Code RAG
A senior-engineer guide to Glue Bedrock RAG, with production-ready patterns, trade-offs, and practical examples.
Posted inAI System Design
AI Migration Assistants: Strangler Fig Cuts With Contract Tests
A senior-engineer guide to AI migration assistants, with production-ready patterns, trade-offs, and practical examples.
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.
Posted inAI
Semantic Diff Review: AI That Flags Behavioral Drift Only
A senior-engineer guide to semantic diff review, 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.