Stop Building Chatbots and Start Building Agentic Workflows
Moving from simple prompt-response loops to iterative, self-correcting agentic patterns in your LLM applications.
#Agents
4381 articles tagged with Agents
What I Learned Building an AI Agent Whose Only Goal Is to Disagree With You
We just opened the waitlist for Something, and the part that surprised me most while building it...
Your AI Agent Keeps Failing After 50 Clean Demos, Stop Treating the LLM Like a Black Box
Why your AI agent works perfectly in demos then fails in production. Real patterns for debugging LLM output, system prompts, and building reliable agent loops.
From "someone should fix this" to a working demo, with an AI agent
The problem A colleague still working FIM/MIM support flagged it plainly: the TechNet Wiki...
The 88 Percent: AI Agent Security Incidents Are Now the NormA 2026 enterprise survey found most organisations reported c...
The 88 Percent: AI Agent Security Incidents Are Now the NormA 2026 enterprise survey found most organisations reported confirmed or suspected AI agent security incidents in the pas...
StepFun Reportedly Preparing Its First AI Smartphone with Native AI Agent Capabilities
Igeekphone News: Chinese artificial intelligence company StepFun is reportedly preparing to enter the consumer hardware market with its first AI-powered smartphone, marking a signi...
Flint: Microsoft's New Tool Could Finally Make AI Agent Debugging Less of a Black Box Nightmare
Alright folks, let's talk about something that genuinely caught my eye amidst the usual AI hype...
Amazon’s next Alexa upgrade could handle complex tasks, but it’ll cost a fortuneAmazon's plan to make Alexa an AI agent ...
Amazon’s next Alexa upgrade could handle complex tasks, but it’ll cost a fortuneAmazon's plan to make Alexa an AI agent comes with a nine-figure problem.https://www.androidauthorit...
Flint: Microsoft's AI Agent 'DevTools' Just Dropped, And It's a Game Changer
Alright, folks, let's talk about something genuinely interesting that just hit my radar. Microsoft,...
Hyundai Motor Securities Becomes First Mid-Sized Broker to Adopt Cloud AI Agent
Hyundai Motor Securities becomes the first mid-sized Korean brokerage to adopt a cloud-based AI work support service, HAI 1.0, powered by Claude Sonnet 4.5, with plans to expand to...
トレノケート、AWS生成AI・Agentic AIの中・上級トレーニングを日本初開催へ | トレノケート株式会社 のプレスリリース https://www.yayafa.com/2839499/ #AgenticAi #AI #Artifi...
トレノケート、AWS生成AI・Agentic AIの中・上級トレーニングを日本初開催へ | トレノケート株式会社 のプレスリリース https://www.yayafa.com/2839499/ #AgenticAi #AI #ArtificialGeneralIntelligence #ArtificialIntelligence #PrTimes #エー...
Building an AI Agent System with the ReACT Pattern in Java
How we gave Jarvis the ability to reason, act, and observe using Spring Boot 4, Spring AI 2.0, and the ReACT pattern.
GitLost: How We Tricked GitHub's AI Agent into Leaking Private Repos - Noma Security #leak #ai #breach #dataprivacy http...
GitLost: How We Tricked GitHub's AI Agent into Leaking Private Repos - Noma Security #leak #ai #breach #dataprivacy https://noma.security/blog/gitlost-how-we-tricked-githubs-ai-age...
Your AI agent re-adds code you reverted last month
AI agent re-adds reverted code? revert_guard.py is an offline, keyless pre-commit gate that reads your git revert history and blocks it before commit.
AI Agent Autonomy Ladder: Let Agents Act Without Losing Control
Design an AI agent autonomy ladder with manual, copilot, autopilot, and supervised modes so agents can act safely with budgets, approvals, undo, and audit trails.
SpaceXAI debuts Grok 4.5 model for coding, agentic AI tasks
Elon Musk's AI venture, SpaceXAI (formerly known as xAI), has unveiled its latest artificial intelligence model, Grok 4.5.
Benchmarking Mitii AI Agent: 78% Success Rate on 500+ Tasks Using a Local Qwen3-Coder (30B)
Building an AI agent that doesn't just confidently hallucinate but actually writes safe, reliable...
Nvidia touts Vera CPU's single-threaded performance as its agentic AI advantage, reveals next-gen 'Rigel' Arm CPU cores ...
Nvidia touts Vera CPU's single-threaded performance as its agentic AI advantage, reveals next-gen 'Rigel' Arm CPU cores — frame…Nvidia lifts the veil a little bit more on its Vera ...
Hakuhodo DY ONE、博報堂と共同でAIエージェントが購買を代行する時代を見据えたエージェンティックコマース領域の統合ソリューション「Agentic Commerce ONE(TM)」を始動 https://www.yayafa....
Hakuhodo DY ONE、博報堂と共同でAIエージェントが購買を代行する時代を見据えたエージェンティックコマース領域の統合ソリューション「Agentic Commerce ONE(TM)」を始動 https://www.yayafa.com/2839324/ #AgenticAi #AI #ArtificialGeneralIntelligence #...
Anthropic、「Claude Code」のシステムプロンプトを80％削減 「モデルの創造性を解放するため」（1/2 ページ） – ITmedia AI＋ https://www.yayafa.com/2839316/ #Agentic...
Anthropic、「Claude Code」のシステムプロンプトを80％削減 「モデルの創造性を解放するため」（1/2 ページ） – ITmedia AI＋ https://www.yayafa.com/2839316/ #AgenticAi #AI #Anthropic #AnthropicClaude #ArtificialGeneralIntelli...
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
Visual generators excel at rendering, but they confidently fabricate what they do not know. User requests are unbounded, evolving, and deeply long-tailed: new characters, trending ...
AI Agent Security Happens at the Tool Call | Focused Labs
AI agent security belongs at the runtime-owned tool-call boundary where principal, grant, resource, capability, data flow, and audit get checked.
Many thanks to Diana Kelley for presenting her talk: "Protecting Trust Boundaries in Agentic #AI: Defending Against Prom...
Many thanks to Diana Kelley for presenting her talk: "Protecting Trust Boundaries in Agentic #AI: Defending Against Prompt Injection and Context Poisoning" at #OWASP London meetup ...
I replaced the chat window for my local AI agent with a face
I run a local LLM agent (Hermes) on my own machine. The problem was never the model — it was the...