lucas (@lucas_flatwhite)

2026년 현재 코딩 중심 개발에서 에이전트 엔지니어링으로 패러다임이 이동하는 전환기라는 점을 강조한다. Andrej Karpathy의 Sequoia Ascent 2026 발언을 통해 개발자의 역할 재정의 필요성을 제시한다.

https://x.com/lucas_flatwhite/status/2051304700822298934

#agentengineering #aidevelopment #sequoia #karpathy

lucas (@lucas_flatwhite) on X

2026년 지금 우리는 코딩에서 에이전트 엔지니어링으로 패러다임이 이동하는 과도기에 있어요. 안드레 카파시가 Sequoia Ascent 2026에서 이야기한 내용을 보면서 나 자신에 대한 역할을 재정의가 필요하다고 느끼실 수도 있습니다. 절대로 이해하는걸 포기하지 마세요.

X (formerly Twitter)

Title: P2: I was preparing for interview for Agentic AI Engineer. [2025-05-15 Thu]

interpretable outputs (e.g., natural language
explanations) to facilitate human-in-the-loop oversight.

standards:
- FIPA Standards/specifications (e.g., FIPA-ACL)
- IEEE 1471 (ISO/IEC 42010)

I thing, first step of planning multi-agent system is to
measure what intellectual capabilities we can accure
and manage. #dailyreport #multiagent #agents #agentoriented #agentengineering

Title: P1: I was preparing for interview for Agentic AI Engineer. [2025-05-15 Thu]

- Event-Driven Communication: (e.g., Apache Kafka, RabbitMQ)
- Standardized Communication Protocols: like FIPA
(Foundation for Intelligent Physical Agents) for agent
communication, ensuring interoperability and structured message
passing (e.g., ACL - Agent Communication Language).
- Explainability in Communication: Ensure agents provide #dailyreport #multiagent #agents #agentoriented #agentengineering

Title: P0: I was preparing for interview for Agentic AI Engineer. [2025-05-15 Thu]

Main steps in Agent-Oriented Software Engineering:
1) analyzing requirements - what to do and how fast
2) defining system scope and limits - where to run and
how much money we have
3) identifying agent roles
4) selecting architectures
5) choosing tools

best practices:
- microservices REST or gRPC #dailyreport #multiagent #agents #agentoriented #agentengineering

I like the word harness 🤗
The parallels between leading organisations and building agents are a bit … uncanny

https://www.sarincasm.com/blog/i-like-harness

#AgentEngineering #DevEx #Leadership

I like the word Harness

The uncanny parallels between leading organisations and building agents

Akshay (@akshay_pachaar)

AI 에이전트의 진화가 모델 자체의 성능보다 주변 환경과 하네스 엔지니어링 개선에 더 크게 좌우됐다는 관점을 제시합니다. 2022~2026년 사이 에이전트 기술이 weights, context, harness engineering 중심으로 발전해 왔다는 흐름을 정리한 분석입니다.

https://x.com/akshay_pachaar/status/2044763357300027842

#aiagents #agentengineering #harness #llm #ai

Akshay 🚀 (@akshay_pachaar) on X

from weights → context → harness engineering (evolution of agent landscape from 2022-26) the biggest shift in AI agents had nothing to do with making models smarter. it was about making the environment around them smarter. here's how agent engineering evolved in just 4

X (formerly Twitter)
The State of Agent Engineering Report offers a comprehensive overview of where AI agent development stands today. The report demystifies key terminology and provides supporting evidence for the current landscape of agent engineering. https://www.kdnuggets.com/the-state-of-agent-engineering-report-overview #AIagent #AI #GenAI #AgenticAI #AgentEngineering
The State of Agent Engineering Report Overview - KDnuggets

Check out the current state AI agent engineering the accessible way: demystifying the jargon, and seeking supporting evidence.

KDnuggets

Everyone’s excited about AI agents. But a harder question remains: what would need to be true for them to actually stay aligned with the human job-to-be-done over time? Not just at the prompt, but across decisions, context, and collaboration. Curious how others think about this.

#AgentArchitecture #AgentEngineering #AgentMemory #RuntimeEvaluation #IntentModeling #LLMSystems #AgenticAI #AI #ArtificialIntelligence #JTBD

https://www.designative.info/2026/03/08/preventing-agent-drift-designing-ai-systems-that-stay-aligned-with-human-intent/

Preventing Agent Drift: Designing AI Systems That Stay Aligned With Human Intent » { design@tive } information design

What would it take for AI agents to truly support human work—capturing intent, preserving context, and staying aligned with real jobs-to-be-done?

{ design@tive } information design

tonyy (@ttonydev)

@simonw의 블로그 글(에이전트 공학 패턴)에 영감을 받아 작성한 글로, 작성자가 BDD(행동 주도 개발)를 활용해 여러 에이전트를 조정(coordinate)하는 방법을 정리했다는 내용입니다. 에이전트 설계·운영 관점의 실무적 패턴 공유입니다.

https://x.com/ttonydev/status/2029659372213674175

#agentic #bdd #agents #agentengineering

tonyy (@ttonydev) on X

Inspired by @simonw’s blog post on agentic engineering patterns, I wrote down how I use BDD to coordinate my agents 👇

X (formerly Twitter)

Agent Engineering is the future of AI.
It's an iterative blend of product thinking, engineering, and data science that transforms unpredictable LLMs into reliable, production-ready agents.

Ship fast,
observe deeply,
refine constantly.

#AgentEngineering #AI #LLM