Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: guardrails
AI Agent Foundations: Purpose, Prompt Design and Model Selection
How to lay the groundwork for a production AI agent: define purpose and success metrics, write prompts with goals and guardrails, then pick the right model.
21 min readAI Architecture for Production Agents: Failure Modes and Control Layers
A layer-by-layer architecture guide for production agent systems: failure modes, guardrails, evals, observability, cost control, zero trust and governance.
12 min readBedrock Agents: Memory Summarization, Versioned Guardrails and Knowledge Base
Terraform-driven Bedrock agent controls: session memory with a custom summarization prompt, versioned guardrails with detect-then-block rollout, and S3-backed RAG.
15 min readThe Two Ways MCP Servers Fail and a Guardrail Layer to Stop Them
MCP servers fail through over-broad tokens and task-blind tools. Scoped tokens, audience checks, sanitized errors and tool caps make a guardrail layer.
8 min readBuild a Support Agent with Agentspan: Tools, Approvals, Guardrails
Create a Python customer support agent on Agentspan and Groq with Pydantic output, a human approval gate for refunds, an input guardrail and live event streaming.
11 min readLoop Engineering for AI Agents: Five Parts, Four Shapes and a LangGraph Build
Loop engineering for AI agents: five parts, four common shapes, a verify-and-retry research agent in LangGraph, guards against failure, and when not to loop.
15 min readGuarding Agent Tool Calls with Jev and LangGraph Before They Execute
Add pre-execution safety checks and post-execution completion review to a LangGraph agent, using Jev typed decisions to block risky actions like large refunds.
8 min readThe Five Layers of an Agent Harness, With Code That Fails Without Them
The five layers of an agent harness, each with code that fails without it: execution boundary, sandboxing, memory, verification loops and the context pipeline.
14 min readPII and PCI redaction at query, context, and answer in a RAG graph
PII and PCI redaction at three points in a RAG graph: before search, before the prompt and before the UI, with golden tests for clean, card and SSN cases.
8 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.