
Agent engineering: MCP, subagents and agentic systems · 1. What an agent is, minus the marketing
Agent engineering: MCP, subagents and agentic systems · Chapter 1 of 14 · AI Engineering · new...
Tag archive

Agent engineering: MCP, subagents and agentic systems · Chapter 1 of 14 · AI Engineering · new...
How to orchestrate, evaluate, and guard LangGraph multi-agent systems in production, with concrete patterns for cost, failure modes, and control.
A production agent bridge dropped a date constraint while turning a model tool call into a real web request, then returned a plausible count over the

TencentDB Agent Memory Storage is the layer that turns an AI agent’s temporary observations into...

From Prompt to Context to Harness: how three years of AI engineering vocabulary kept renaming the same problem until 40% of agent projects started failing for the same boring reason.

If you have two AI agents writing the same Postgres row, you have probably already added a...

Gartner says 40% of agentic AI projects get canceled. Here are the five failure modes that kill agents in production and the discipline that ships the rest.
There's a diagram making the rounds that splits the world into "prompt engineering" and "loop...

What survived contact with real usage maintaining an MCP server across three clients I never built for: fail-close defaults, replayable observability, and tool descriptions as the real interface.
Open Anthropic's pricing page — or OpenAI's, or any other major frontier provider's — and the unit...
A recent piece called "The Bottleneck Was Never the Code" makes the right argument at the right time....
Most AI projects fail somewhere between demo works and production ships. The gap is rarely the model....