All articles — page 3

Showing 12 of 122 articles on AI systems, retrieval, backend engineering and DevOps.

PostgreSQLCDCSemantic Cache
How to Prevent AI Context Poisoning using PostgreSQL CDC for Real-Time Semantic Cache Invalidation in Node.js
Learn how to stop stale semantic caches from poisoning your AI agents. Build a real-time invalidation pipeline with PostgreSQL CDC, a Node.js worker, and an embedding similarity radius to flush outdated cache entries instantly.
Oct 3, 2026
LangGraph.jsZodAI Agents
How to Build a Self-Healing Tool Call Execution Loop using Zod and LangGraph.js
Learn how to build a self-healing tool call loop in LangGraph.js. Validate LLM tool arguments with Zod, route failures to a correction node, and let local models fix their own invalid JSON.
Oct 2, 2026
AI AgentsNode.jsVector Database
How to Build an Agentic Memory Garbage Collector in Node.js to Prevent Vector Store Context Poisoning
Learn how to build a Node.js memory garbage collector for AI agents. Implement time-weighted relevance decay, semantic deduplication, and safe pruning to stop vector store context poisoning and hallucination cascades.
Oct 1, 2026
LangGraphPostgreSQLAI Agents
How to Implement Transactional State Rollbacks for AI Agents in LangGraph and PostgreSQL
Learn how to wrap LangGraph tool nodes in PostgreSQL savepoints, roll back partial failures deterministically, and stop duplicate billing before your LLM retries.
Sep 28, 2026
LangGraph.jsAI AgentsContext Engineering
How to Implement Hierarchical Context Compaction in LangGraph.js to Prevent Agent Context Drift
A practical, code-first guide to building a hierarchical context compaction layer in LangGraph.js — using Ollama for local summarization and PostgreSQL checkpointing to stop long-running AI agents from drifting off-goal.
Sep 27, 2026
pgvectorPostgreSQLNode.js
How to Sync pgvector Embeddings in Real-Time using PostgreSQL Triggers and Node.js Background Workers
Stop relying on cron jobs for vector search. Learn how to build a real-time, event-driven pipeline using PostgreSQL triggers, an outbox table, and isolated Node.js background workers to keep pgvector embeddings fresh without locking your production database.
Sep 26, 2026
Node.jsLLM SecurityPII Masking
How to Build a Two-Way PII Masking and Re-hydration Middleware in Node.js for Enterprise LLM Pipelines
A production-focused guide to building an Express.js middleware that detects, tokenizes, and re-hydrates PII in real time — keeping GDPR- and HIPAA-sensitive data out of your LLM prompts without breaking conversational context.
Sep 25, 2026
AbortControllerNext.jsNode.js
How to Kill Zombie LLM Streams: Propagating AbortController from Next.js to Node.js and Ollama
Stop paying for tokens nobody reads. Learn how to propagate AbortController from Next.js through Express, LangChain and Ollama so closing a tab or clicking Stop actually halts GPU inference.
Sep 24, 2026
AI SecurityPrompt InjectionNode.js
How to Build a Zero-Trust AI Sanitization Middleware in Node.js to Prevent Indirect Prompt Injection
Learn how to build a zero-trust sanitization middleware in Node.js and TypeScript using Express and js-tiktoken to defend against indirect prompt injection, enforce hard token limits, and stop untrusted RAG data from hijacking agentic tool calls.
Sep 23, 2026
DockerNode.jsAI Agents
How to Build a Secure Docker-Isolated Code Execution Sandbox for AI Agents in Node.js
Learn how to safely run untrusted LLM-generated code using Node.js and the Docker Engine API. A practical guide to ephemeral containers, cgroup limits, network isolation, and seccomp profiles for AI agent sandboxes.
Sep 22, 2026
RAGRagasOllama
How to Automate RAG Regression Testing and Hallucination Checks in GitHub Actions Using Ragas and Ollama
Learn how to automate RAG regression testing in GitHub Actions. Run Ollama in CI, score pull requests with Ragas (faithfulness, answer relevancy, context recall), and block merges that introduce hallucinations or retrieval drift.
Sep 21, 2026
AI SecurityPrompt InjectionNext.js
How to Protect Your AI Application from Prompt Injections using Llama Guard and Next.js Edge Middleware
A practical 2026 guide to securing RAG and LLM applications against prompt injection and jailbreak attacks using Llama Guard, Ollama, Next.js Edge Middleware, and PostgreSQL-based threat logging aligned with the OWASP Top 10 for LLMs.
Sep 16, 2026

Browse by topic