home.social

#agenticai — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #agenticai, aggregated by home.social.

  1. GOSIM Shenzhen 2026 (Oct 16-17) Ticket Guide Released!

    Topics:Agentic AI , Open Source Robotics& Models, Edge AI, Agentic OS & Apps, and others.
    Early bird tickets :Student ¥75, Standard ¥299, All-Access ¥399,Rust: ¥299, VIP ¥2699 (limited).

    Grab your spot: bagevent.com/event/gosimshenzh
    More details: shenzhen2026.gosim.org/zh

    #GOSIM #AgenticAI #OpenSource #AI #Shenzhen #TechEvent

  2. GOSIM Shenzhen 2026 (Oct 16-17) Ticket Guide Released!

    Topics:Agentic AI , Open Source Robotics& Models, Edge AI, Agentic OS & Apps, and others.
    Early bird tickets :Student ¥75, Standard ¥299, All-Access ¥399,Rust: ¥299, VIP ¥2699 (limited).

    Grab your spot: bagevent.com/event/gosimshenzh
    More details: shenzhen2026.gosim.org/zh

    #GOSIM #AgenticAI #OpenSource #AI #Shenzhen #TechEvent

  3. Five Model Context Protocol servers that genuinely enhance AI agent capabilities, chosen for what they do to an agent's actual performance rather than their star count on GitHub. Worth wiring into a high-performance development setup. kdnuggets.com/top-5-mcp-server #AIagent #AI #GenAI #AgenticAI

  4. Five Model Context Protocol servers that genuinely enhance AI agent capabilities, chosen for what they do to an agent's actual performance rather than their star count on GitHub. Worth wiring into a high-performance development setup. kdnuggets.com/top-5-mcp-server #AIagent #AI #GenAI #AgenticAI

  5. These are important engineering nuances people pick up in our agentic cohort, by building real-world apps. 🚀

    Join us in August for the next run.
    Link in the first comment.👇

  6. Cadence has launched AuraStack, an agentic AI platform that automates printed circuit board (PCB) and advanced chip packaging design. Unlike traditional AI assistants, AuraStack coordinates multiple specialized AI agents that can plan, simulate, and optimize engineering workflows from system design to manufacturing.

    #BestSoln #BestSolution #Cadence #AgenticAI #AI #ArtificialIntelligence #Semiconductors #ChipDesign #EDA #PCB #NVIDIA #Engineering #Technology #TechNews

  7. Cadence has launched AuraStack, an agentic AI platform that automates printed circuit board (PCB) and advanced chip packaging design. Unlike traditional AI assistants, AuraStack coordinates multiple specialized AI agents that can plan, simulate, and optimize engineering workflows from system design to manufacturing.

    #BestSoln #BestSolution #Cadence #AgenticAI #AI #ArtificialIntelligence #Semiconductors #ChipDesign #EDA #PCB #NVIDIA #Engineering #Technology #TechNews

  8. Cadence has launched AuraStack, an agentic AI platform that automates printed circuit board (PCB) and advanced chip packaging design. Unlike traditional AI assistants, AuraStack coordinates multiple specialized AI agents that can plan, simulate, and optimize engineering workflows from system design to manufacturing.

    #BestSoln #BestSolution #Cadence #AgenticAI #AI #ArtificialIntelligence #Semiconductors #ChipDesign #EDA #PCB #NVIDIA #Engineering #Technology #TechNews

  9. Cadence has launched AuraStack, an agentic AI platform that automates printed circuit board (PCB) and advanced chip packaging design. Unlike traditional AI assistants, AuraStack coordinates multiple specialized AI agents that can plan, simulate, and optimize engineering workflows from system design to manufacturing.

    #BestSoln #BestSolution #Cadence #AgenticAI #AI #ArtificialIntelligence #Semiconductors #ChipDesign #EDA #PCB #NVIDIA #Engineering #Technology #TechNews

  10. Wer noch übers Prompten diskutiert, verpasst den echten Statikwechsel: Das Zeitalter autonomer KI-Agenten.

    Wenn Algorithmen im Namen von Traditionsmarken agieren, braucht es klare Antworten zu Haftung, Befugnissen und Vertrauen. Estland macht es vor – der Mittelstand muss kommunikativ nachziehen.

    Warum B2B-Tech ein Schutzschild für KI-Governance braucht:

    pr-exclusiv.de/wenn-der-algori

    #AgenticAI #KI #B2B #Mittelstand #TechPR #Governance

  11. tkhunt.com/2454074/ 【広告運用はAIか人か】インターネット広告の現在地/AIの台頭と広告代理店不要論/AI時代こそ「常駐型支援」/一次情報の重要性/元サイバーエージェント営業局長が仕掛ける/広告代理店の再発明 #AgenticAi #AI #ArtificialIntelligence #pivot #インターネット広告 #エージェント型AI #サイバーエージェント #ロットネスト #人工知能 #常駐型 #常駐型支援 #広告 #広告代理店 #広告会社 #広告運用 #運用型広告

  12. tkhunt.com/2454074/ 【広告運用はAIか人か】インターネット広告の現在地/AIの台頭と広告代理店不要論/AI時代こそ「常駐型支援」/一次情報の重要性/元サイバーエージェント営業局長が仕掛ける/広告代理店の再発明 #AgenticAi #AI #ArtificialIntelligence #pivot #インターネット広告 #エージェント型AI #サイバーエージェント #ロットネスト #人工知能 #常駐型 #常駐型支援 #広告 #広告代理店 #広告会社 #広告運用 #運用型広告

  13. Hugging Face: Security incident disclosure — July 2026. “Earlier this week, we detected and responded to an intrusion into part of our production infrastructure. This one was different from anything we had handled before in one important way: it was driven, end to end, by an autonomous AI agent system – and we detected and dissected it largely with AI of our own.”

    https://rbfirehose.com/2026/07/19/hugging-face-security-incident-disclosure-july-2026/
  14. Hugging Face: Security incident disclosure — July 2026. “Earlier this week, we detected and responded to an intrusion into part of our production infrastructure. This one was different from anything we had handled before in one important way: it was driven, end to end, by an autonomous AI agent system – and we detected and dissected it largely with AI of our own.”

    https://rbfirehose.com/2026/07/19/hugging-face-security-incident-disclosure-july-2026/
  15. Hugging Face: Security incident disclosure — July 2026. “Earlier this week, we detected and responded to an intrusion into part of our production infrastructure. This one was different from anything we had handled before in one important way: it was driven, end to end, by an autonomous AI agent system – and we detected and dissected it largely with AI of our own.”

    https://rbfirehose.com/2026/07/19/hugging-face-security-incident-disclosure-july-2026/
  16. Hugging Face: Security incident disclosure — July 2026. “Earlier this week, we detected and responded to an intrusion into part of our production infrastructure. This one was different from anything we had handled before in one important way: it was driven, end to end, by an autonomous AI agent system – and we detected and dissected it largely with AI of our own.”

    https://rbfirehose.com/2026/07/19/hugging-face-security-incident-disclosure-july-2026/
  17. Hugging Face: Security incident disclosure — July 2026. “Earlier this week, we detected and responded to an intrusion into part of our production infrastructure. This one was different from anything we had handled before in one important way: it was driven, end to end, by an autonomous AI agent system – and we detected and dissected it largely with AI of our own.”

    https://rbfirehose.com/2026/07/19/hugging-face-security-incident-disclosure-july-2026/
  18. #Anthropic publishes a #CISO guide to #Agentic #AI! According to it the goal isn't zero risk, but making risk legible & bounded.

    Evaluate agents by tracking untrusted content, identity, blast radius and observability.

    Read the guide:
    #AgenticAI
    👇
    claude.com/blog/ciso-guide-to-

  19. #Anthropic publishes a #CISO guide to #Agentic #AI! According to it the goal isn't zero risk, but making risk legible & bounded.

    Evaluate agents by tracking untrusted content, identity, blast radius and observability.

    Read the guide:
    #AgenticAI
    👇
    claude.com/blog/ciso-guide-to-

  20. "You can sit anywhere on the spectrum from vibe coding to agentic engineering with the same agent. The thing that decides where you land is verification.

    The right spot on the spectrum depends on the stakes. The skill is knowing where to draw the line for each task.
    There are two mechanisms. Tests cover the deterministic parts: this input, that output. Evals cover the parts that aren’t deterministic, and the paper splits them in a way I found useful. Output evaluation asks whether the final result is correct. Trajectory evaluation asks whether the path it took to get there, the tool calls and the reasoning, was sound. You want both. An answer that looks right but skipped its checks is more dangerous than one that’s obviously broken.

    If I had to hand a leader one line from the paper, it’s this: Set the bar at the eval, not the demo. A demo shows an agent can work once. An eval suite with a real rubric shows it works reliably. I keep making this argument; see “Agentic Code Review.”

    AI compresses the lifecycle, but unevenly, and the unevenness is the whole story. Implementation drops from weeks to hours. Requirements, architecture, and verification stay slow because they’re judgment work. So specification quality becomes the bottleneck, and verification moves to the middle."

    oreilly.com/radar/the-new-soft

    #AI #GenerativeAI #AIAgents #AgenticAI #AgenticEngineering # #VibeCoding #SDLC #SoftwareDevelopment #Programming

  21. "You can sit anywhere on the spectrum from vibe coding to agentic engineering with the same agent. The thing that decides where you land is verification.

    The right spot on the spectrum depends on the stakes. The skill is knowing where to draw the line for each task.
    There are two mechanisms. Tests cover the deterministic parts: this input, that output. Evals cover the parts that aren’t deterministic, and the paper splits them in a way I found useful. Output evaluation asks whether the final result is correct. Trajectory evaluation asks whether the path it took to get there, the tool calls and the reasoning, was sound. You want both. An answer that looks right but skipped its checks is more dangerous than one that’s obviously broken.

    If I had to hand a leader one line from the paper, it’s this: Set the bar at the eval, not the demo. A demo shows an agent can work once. An eval suite with a real rubric shows it works reliably. I keep making this argument; see “Agentic Code Review.”

    AI compresses the lifecycle, but unevenly, and the unevenness is the whole story. Implementation drops from weeks to hours. Requirements, architecture, and verification stay slow because they’re judgment work. So specification quality becomes the bottleneck, and verification moves to the middle."

    oreilly.com/radar/the-new-soft

    #AI #GenerativeAI #AIAgents #AgenticAI #AgenticEngineering # #VibeCoding #SDLC #SoftwareDevelopment #Programming

  22. Ten open-source no-code platforms now let developers build LLM apps, RAG systems and AI agents through visual tools and plain-English prompts. The roundup covers verified open-source licences and best-fit use cases. marktechpost.com/2026/07/18/10 #AIagent #AI #GenAI #AgenticAI

  23. Ten open-source no-code platforms now let developers build LLM apps, RAG systems and AI agents through visual tools and plain-English prompts. The roundup covers verified open-source licences and best-fit use cases. marktechpost.com/2026/07/18/10 #AIagent #AI #GenAI #AgenticAI

  24. NVIDIA has released DeepStream 9.1, bringing agentic AI to vision AI with 13 skills that let coding agents like Claude Code build multi-camera video analytics pipelines from natural-language prompts. The update includes Multi-View 3D Tracking and automatic camera calibration. marktechpost.com/2026/07/18/nv #AIagent #AI #GenAI #AgenticAI

  25. NVIDIA has released DeepStream 9.1, bringing agentic AI to vision AI with 13 skills that let coding agents like Claude Code build multi-camera video analytics pipelines from natural-language prompts. The update includes Multi-View 3D Tracking and automatic camera calibration. marktechpost.com/2026/07/18/nv #AIagent #AI #GenAI #AgenticAI

  26. Google Cloud has released an Always-On Memory Agent that replaces traditional RAG and embeddings with continuous LLM consolidation using Gemini 3.1 Flash-Lite. The agent runs 24/7, storing structured memory in SQLite rather than vector databases. marktechpost.com/2026/07/18/go #AIagent #AI #GenAI #AgenticAI

  27. Google Cloud has released an Always-On Memory Agent that replaces traditional RAG and embeddings with continuous LLM consolidation using Gemini 3.1 Flash-Lite. The agent runs 24/7, storing structured memory in SQLite rather than vector databases. marktechpost.com/2026/07/18/go #AIagent #AI #GenAI #AgenticAI

  28. Have you tried building your own agent loop and what has been your biggest challenge making it work in production?

  29. Have you tried building your own agent loop and what has been your biggest challenge making it work in production?

    #python #agenticai #aiengineering