alchen.eth (🍔,🍔)

How I use @claudeai to provide the best experience to our customers at @rungalileo

🔒Agent Control from @rungalileo is an open source project providing policies and guardrails on your agents down to individual function signatures in your application code (just requires a @control decorator).

@rungalileo +1 for open source!

Every agent your team ships has its own hardcoded guardrails, its own bespoke logic, its own failure modes. That's not governance. These brittle controls soon become a liability. Galileo is proud to announce the open-source launch of Agent Control 🚀 Agent Control is the open-source control plane that solves for the open, centralized governance needs for all your AI Agents. 💬 "We've had a front-row seat to agent development at Fortune 500 and digital-native companies. They have been struggling to hard-code safety rules and controls into each agent which makes them brittle. With Agent Control, developers can now create policies in one place and then use those to enforce guardrails everywhere." — @YashSheth46, Co-founder & CTO, Galileo Agent Control integrates seamlessly with all your agents using the @ control hook or just by leveraging our native integrations with some of the leading agent frameworks. No redeployment. No code changes. No vendor lock-in. 💬 “Centralized management of policies can help organizations to manage AI agent behaviors. A unified control plane and centralized governance of agents can help organizations efficiently deploy AI agents at scale. Organizations that embrace eval engineering as a core competency will shorten the time to value for their AI investments. By taking a lifecycle approach, organizations can achieve a continuous improvement loop for AI systems.” – Tim Law, @IDC Research Director, AI and Automation Agent Control is already backed by partners including @awscloud, @Cisco AI Defense, @crewAIInc, @glean, @ServiceNow, and @rubrikInc, and it works with the guardrail providers you already use, from our Luna models to NVIDIA NeMo or AWS Bedrock. The repo is live, built in the open with contributions from some of the largest AI infrastructure companies in the world, try it out today: agentcontrol.dev Watch Yash walk through how it works in the video below, and check the comments for links to our launch webinar, announcement blog, and full press release. 👇

⛓️ When you cannot trust, you are vulnerable. This tutorial walks through what @rungalileo metrics are, how to use them, and the typical workflow to steer your agentic apps in the right driection.

Example code here: github.com/rungalileo/sdk…

😎Example integration between @elevenlabs and @rungalileo to better evaluate the performance and quality of your voice agents. Shout out to @mike_branc and Kam Chehresa for building out this example 🙌

@LangChain From agentic workflows I'm seeing in the workplace, apps sometimes will have multiple architectures. Architecture also evolves as models improve/quality degrades. Example is @RLanceMartin's Bitter Lesson post where he started with Orchestrator-Worker then Subagents then Router

📊 New blog: Choosing the right multi-agent architecture Start with a single agent. But when you need multi-agent capabilities, pick the right pattern: 👥 Subagents - Centralized orchestration for multiple domains 💡 Skills - Progressive disclosure, load capabilities on-demand 🔄 Handoffs - Sequential workflows with state transitions 🧭 Router - Parallel dispatch across specialized agents Includes performance benchmarks, decision framework, and code examples. 📖 Read the full guide: blog.langchain.com/choosing-the-r…

@dexhorthy @humanlayer_dev @sampleite @github @usepylon @Confluence @LiamBush20 @langchain Here are the slides: canva.com/design/DAG6faN…

@dexhorthy @humanlayer_dev @sampleite @github @usepylon Claude scans our codebase, docs, @Confluence, and @usepylon to gather appropriate context. @LiamBush20 published a blog post showing a similar approach @langchain uses for their chatbot: blog.langchain.com/rebuilding-cha…

☎️ Here are the slides I shared at last week's NY AI eng meetup hosted by @modal. I discussed on how our team uses @AnthropicAI to answer technical questions about @rungalileo 🧵

🎄Hosting and end of year NYC AI engineer meetup at @modal's new office on December 10th! Hosted by @modal and @rungalileo. RSVP here: luma.com/1cz2ejll

👟I joined the field engineering team at @rungalileo to help bring AI applications across the last mile to production. Here's a demo of an SDR outreach assistant where I use Galileo's context engineering and observability features to improve the app.

@HamelHusain @jobergum The counterargument might be horizontal tools (e.g. spreadsheets) that you can mold to fit your team's specific processes and workflows. while not silver bullets, i'd argue no-code tools were a paradigm shift in how people could bring their opinionated ways of working to the tool

This is happening in 30 minutes with @jobergum 🍿 maven.com/p/933026/you-d…

@HamelHusain @jobergum @jobergum's point about mapping a process to a software stack reminds me of trying to shove the complexities of the SDLC and agile project mgmt into Jira or [pick your proj mgmt tool]

👀

In @langchain's deep research project, a "think tool" helps direct the agent's research (it's just a descriptive system prompt). @RLanceMartin said this was inspired by an @AnthropicAI blog post. To optimize, the system prompt should be domain-specific (2nd screenshot).