SATO Naoki (Neo)

RT @GitHubJapan: 世界最大級のカンファレンス「GitHub Universe 2026」がサンフランシスコにて開催！ AIによる開発の未来やGitHub Copilotの最新機能など、見逃せないセッションが盛りだくさんです！ セッションはオンラインにて無料でご視聴いただけます🎥 開催日程：10月28日（水）〜29日（木）（サンフランシスコ時間） オープニングキーノート：10月29日（木）1:00〜1:45（日本時間） 【無料チケットに含まれる内容】 ・キーノートのリアルタイム配信 ・オンライン限定コンテンツ ・録画セッションのオンデマンド配信（公開後） 詳しくはこちら↓

RT @findy_tools: マーティン・ファウラー氏来日登壇決定！ アーキテクチャの「いま」に出会う2日間 📍ベルサール羽田空港/オンライン 📅11月26日（木）・27日（金）9:25~18:55

RT @thoughtworks: AI is moving beyond generating content to making decisions. 🤖 October’s Tech to Know explores decision models, specialized AI, governance and what it takes to keep AI actions under control. Explore the latest issue 👉

RT @Dhruvkumar16797: Andrew Ng just dropped the best 2-hour course on Graph Engineering: from single agent to full automation 9:14 - your first agent 33:11 - loop engineering 1:02:46 - graph engineering 1:30:15 - agents that rewrite themselves 1:49:05 - full graph system two hours, and it replaces every agent tutorial you bookmarked this year Prompts → Agents → Loops → Graphs most people will stop after the first agent and call it automation he saves the last forty minutes for the graph that runs it without him same model, same tokens, completely different week watch it today

RT @0xShoopy: Google just dropped a 9-page PDF on building agents that run for days - 6 layers to an agent that waits in line, survives a crash and never charges you twice: the formula: Long-Running Agent = Trigger + Runner + State + Resumable Workflow + Human Gate + Guards here's how to build your own in 6 layers: layer 1 → trigger - the model can't set a timer. a scheduler hits a /wake endpoint and the agent runs again layer 2 → runner - adk web is a dev tool. your server owns the runner, the sessions and the storage layer 3 → state - session in a real database, preferences under user:, facts in memory. a restart loses nothing layer 4 → resumable workflow - kill the server mid-queue. it resumes at the same node. finished steps never run twice layer 5 → human gate - the agent asks for a budget and waits for a yes. the pause survives restarts too layer 6 → guards - re-check the seat before buying, one idempotency key per order. a retry never charges twice most agents die when the request ends. this is how you build one that doesn't. the workflow in layer 4 is a graph. how to design the whole agent system that way is in my article below

RT @addyosmani: Before adding another subagent ask what problem it's solving. A bloated system prompt is often the issue. Skills and tool search can fix that without splitting context across agents. My rule of thumb is to keep a subagent when the work is parallel, needs fresh context or one agent really can't pick the right tools. Otherwise, fold it into the main loop, turn its prompt into a skill, run your evals and keep whatever wins. Good write-up:

RT @windowsdev: 🐧📦 Keep building with WSL containers on Windows. Build, run, and deploy Linux containers directly on Windows with built-in container workflows. Ready to try it? Run `wsl --update` and start building. Learn more:

RT @omarsar0: Unfortunately, CLI agents are no longer the ideal interface for working with agents. This has been the case for months now. It hurts to say because I have been a heavy CLI user. The reality is that new interfaces like Grok Bot, the Codex app, and others are so good that they make it easier to take advantage of the new ways to work with agents. They also make it easier to scale agent work, collaborate with complex multi-agent systems, build from anywhere, and manage the development lifecycle smoothly (with little overhead). This shift will become even more obvious in the coming months as LLMs continue to improve at things like persistence, coordination, parallelization, tool calling/MCP, memory, harness optimization, multimodal capabilities, intent understanding, UI generation, etc. The point of contact keeps getting simpler as agents continue to improve. I expect that pattern to continue. My rule of thumb now is that I don't want to use an interface that holds the model back or keeps me from leveraging it to its absolute limits.

I am transitioning away from using CLI agents for development. On my last project I transitioned to using grokbots.

＜実践！AI駆動開発＞AI時代の生産性メトリクス再設計 #ELD2026_findy

RT @tmak_tw: 全体的に改訂されています おすすめ / RESTful Web API 実装のベスト プラクティス - Azure Architecture Center | Microsoft Learn

始まった。 #ELD2026_findy

RT @tmak_tw: WindowsやAzureのコードのRust移行など、大規模なマイグレーションにコーディングエージェントを活かしている。仕様駆動開発にTLA+など形式手法を組み合わせることに挑戦中 / Cheap code, precious trust: Code modernization at scale - Command Line

RT @dai___you: 「Engineering Leaders Day 2026」本日開催です🎉 #ELD2026_findy

／ 本日開催🎉 「Engineering Leaders Day 2026」 BUILD IS CHEAP. ― AI時代、競争優位を生み出す開発組織へ ＼ いよいよ本日10:00スタートです！ ご来場の皆さま、大崎の会場でお待ちしています。 ☕ 9:00〜 モーニングネットワーキング 申込不要・先着50名。開場直後から開発リーダー同士の交流をお楽しみください。 🍽️ 12:45〜 ランチネットワーキング 申込不要・先着100名 🎤 各セッション後は Ask the Speaker 登壇者に直接質問できるチャンスです 🤝 共催企業ブース GitLab、AWS、オーティファイ、FindyによるAI駆動開発の相談・デモも 💻 オンライン視聴は今からでもお申し込みいただけます 当日の感想や気づきは #ELD2026_findy でぜひシェアしてください！

現地参加。 #ELD2026_findy

Rapidly scaling online storage to serve over 1 billion ChatGPT users (Part II) | OpenAI How we optimized Azure Cosmos DB in our application storage platform, Habitat, to manage unprecedented growth.

RT @ryuzee: 発売から約5年、『チームトポロジー　価値あるソフトウェアをすばやく届ける適応型組織設計』が8刷の増刷になりました!! AI時代だからこそストリームアラインドチームとプラットフォームチームの重要性がますます上がっているような気もします。まだ読んでいない方はぜひ!!

The Japan team within Microsoft Frontier Company’s engineering (formerly ISE: Industry Solutions Engineering) is hiring for the following open positions. We look forward to receiving your applications!

Microsoft Frontier Company Microsoft Frontier Company: お客様のインテリジェンスを拡張し、保護する AI エンジニアリング

Microsoft FDE - Software Engineerの役割と キャリアの魅力 Microsoft FDE - Data Scientistの役割とキャリアの魅力 共同開発の最前線：Microsoft ISE TPMの役割とキャリアの魅力