
The AI agent stack, layer by layer (and the one that gets skipped)
Six layers, three verticals, and why the durable runtime between your framework and compute decides what a crash costs.
Tag archive

Six layers, three verticals, and why the durable runtime between your framework and compute decides what a crash costs.

Durable execution guarantees that a workflow's completed steps survive a crash and do not run again,...
Dapr, the Distributed Application Runtime, a graduated OSS project within the CNCF, has released a...

A Multi-Agent Workflow With MCP Tools in About 60 Lines An MCP agent demo is usually one agent...

The Dapr MCP server turns a Dapr sidecar's building blocks into Model Context Protocol tools. It's...

Small feature, outsized leverage: Dapr Agents lets you register hooks around the agent loop where the...

Agentic architecture is repeating service-oriented architecture's two worst mistakes, the smart pipe and the synchronous chain.

Introduction Your agent drafted a reply to an annoyed customer. It's good. It's probably...

Run it under a durable workflow, so every tool call is saved as it completes. For CrewAI durable...

Introduction You have a list of items to process, and each item takes a while. Running...
You can't stop untrusted text from reaching a model. If your agent reads public GitHub issues, anyone...

Short answer: a Dapr workflow's history only grows, and continue-as-new is the operation that starts...