Ashley Nader

1% better everyday

@iamfrankforyou @itsArthurAI you can't fix what you can't see!

@Ashley_Nader @itsArthurAI Observability is the difference between debugging with a flashlight and debugging blind. Most AI systems ship without it and then wonder why failures look random.

"Building an agent" doesn't mean what most people think. Most people hear "AI agent" and picture an autonomous system making complex decisions on its own. The reality is much more practical and accessible. Our product manager, @Ashley_Nader, built an open-source AI-powered workflow called Louisa 🐶 that automatically generates polished, user-facing release notes every time a new release ships. She built Louisa using @claudeai Code, deployed it on @vercel, and integrated it with the Arthur Engine for observability and tracing. The real insight isn't the tool, it's the mindset. Building an “agent” starts with one question: What am I doing repeatedly that I could automate? You don't need to be an engineer. You don't need a massive framework. You just need a clear problem, a good prompt, and the observability to know when things go sideways. Louisa is open source (link in comments) 👇 #aiagents #ai

Product taste is the new superpower. What is worth building? What's the right way to build it?

@neatlogs @iamfrankforyou @itsArthurAI 🫶

@Ashley_Nader @iamfrankforyou @itsArthurAI agreed ashley, we've got your back and your agent's :)

@AleksejAros @claudeai @AnthropicAI @vercel @itsArthurAI Arthur has the ability to build custom LLM as a Judge evaluations, which help us in catching hallucinations at every step of the agentic workflow.

@Ashley_Nader @claudeai @AnthropicAI @vercel @itsArthurAI Curious how arthur catches hallucinated features specifically - is it diffing against the actual changelog/commits or more of a semantic check? that distinction matters a lot

I got tired of writing release notes. So I built an AI "agent" with @claudeai @AnthropicAI @vercel. Built-in observability w/@itsArthurAI Engine monitors output quality & catches hallucinated features before they ship. 👇Open source. Setup in minutes. arthurai-staging.webflow.io/blog/what-buil…

@iamfrankforyou @itsArthurAI This is why observability for any AI use case is so important!

@itsArthurAI @Ashley_Nader Most of the confusion is "agent can take actions" vs "agent can reason about when NOT to act." Demos always show the happy path. Production shows you edge cases where an autonomous decision goes sideways at 2am with no human watching.

@Dave412025 @itsArthurAI This is correct, Louisa is technically an ai-powered workflow!

@itsArthurAI @Ashley_Nader An AI agent doesn't have to make many decisions, yeah, but some are built just for that purpose. Yours is much more closer to a workflow, I guess.

I wanted to share a bunch of my favorite hidden and under-utilized features in Claude Code. I'll focus on the ones I use the most. Here goes.

Welcome to the best city to build. 🌴

☁️ Arthur is now available in @googlecloud ! Many of our customers are building on Google Cloud and leveraging the latest Gemini and agent frameworks, so we partnered with Google to make Arthur available directly within your GCP environment. This means data never leaves your GCP environment, procurement is seamless through the Marketplace, and deployment fits naturally into your existing workflows and stack. With the explosion of agents, teams lose visibility into which agents are running and lack insight into failures. As enterprises race to adopt Agentic AI, a comprehensive agentic governance approach is crucial to preventing chaos, security nightmares, and business continuity issues. That’s why we launched Arthur’s Agent Discovery & Governance (ADG) Platform on Google Cloud. With Arthur on Google Cloud, you can: 🔍 Automate Discovery: Instantly find and catalog agents company-wide 📈 Unify Monitoring: Monitor and govern internally-developed and third-party agentic solutions 🛡️ Centralize Policy Management: Enforce acceptable use and security policies for all agent interactions 🔄 Continuously Evaluate: Monitor performance aligned specifically to agent tasks Read full announcement → arthur.ai/blog/arthur-la…

Everyone’s talking about AI agents. No one’s talking about how to govern them. We are. Meet @itsArthurAI ADG platform: visibility + trust for the agent era. More here: prnewswire.com/news-releases/…

Today, we're launching The Agent Development Lifecycle (ADLC) - a methodology to build reliable AI Agents 🚀 💡 The problem is clear: SDLC was built for traditional software, not the probabilistic nature of Agentic AI. Getting an agent to a demo state is quick and easy, but making it reliable is where the real work lies. ⚡The ADLC methodology reimagines the development lifecycle for this new era. It provides a concrete approach that empowers you to experiment and ship agent updates reliably - without risk of introducing regressions. Learn more about the full ADLC methodology on our blog (link in the comments).

We are adding a coding section to all of our Product Managers interviews at @Shopify. We'll start with APM interviews. We expect candidates to build a prototype of the product they suggested in the case interview. There is no excuse for PMs not building prototypes.

*writing was previously the primary representation of clear thinking

Marc Andreessen’s career advice for the AI era:

Don't forget that this is the whole point: to create, more

Wow, what a week!🚀 Kicked off #NYTechWeek with an @ArthurAi_ Hackathon, co-hosted an epic Future of AI Builders event w/ @vercel, @deskree_backend & @Shopify, and capped it off with an AI Leaders Social w/ @awscloud. Excited to continue building the future of AI!👾 @a16z

🚀 Say hello to Arthur Evals Engine — the first #opensource, real-time #AI evaluation engine built for builders, hackers, and teams that care about quality, security, and speed. @itsArthurAI #GenAI #ML #FreeTools youtu.be/U4M7CqinPYU