Agentic Engineering Patterns

kept by eddie mar 06

Effective agentic coding requires a robust test harness, letting AI explore ideas freely, and maintaining a scratch pad of learnings between sessions.

StrongDM Software Factory
StrongDM describes building a Software Factory where agents write code from specs and scenarios, validated by a Digital Twin Universe, without any human-written or reviewed code.
also on StrongDM, Claude, #ai-agents, #ai-coding, #software-engineering, #developer-tools
Levels of Agentic Engineering
The article proposes an 8-level ladder of AI-assisted coding autonomy, from manual prompting to fully autonomous multi-agent software factories.
also on StrongDM, Claude, #ai-coding, #software-engineering, #developer-tools
How to really stop your agents from making the same mistakes (via @garrytan)
LangChain's LangSmith testing platform uses trajectory evals and trace-to-dataset pipelines to prevent AI agents from repeating mistakes, despite its high valuation and funding.
also on #testing, #ai-agents, #software-engineering, #developer-tools
Introducing the Safari MCP server for web developers
Apple released a Model Context Protocol server for Safari that lets AI agents inspect DOM, network requests, screenshots, and console output to debug websites autonomously.
also on #testing, #ai-coding, #software-engineering, #developer-tools
Harness design for long-running application development
Anthropic engineer Prithvi Rajasekaran builds a multi-agent harness with planner, generator, and evaluator agents that produces full-stack applications over multi-hour autonomous coding sessions.
also on Playwright, Claude, #ai-agents, #ai-coding, #software-engineering, #developer-tools