#general
Jul 20July 21, 2026
Hi everyone, I am Jonathan, solution architect in a mid-size insurance company. We are currently considering building our enterprise ai platform based on archestra and step 1 is to use it as LLM gateway to bedrock but failing with a simple claude code call.
"message": "Route POST:/v1/bedrock/<our-uuid>/model/eu.anthropic.claude-sonnet-4-5-20250929-v1:0/invoke-with-response-stream not found",
"error": "Not Found",
"statusCode": 404```
is there like a channel where we can adress these kind of things ? Issue tracking in github is enabled only for contributors
Hey all! 👋 I’m Loïc, VP Eng @ Initiativ. I just started evaluating Archestra as our primary AI platform, very excited about the Knowledge ingestion and Apps builder. For testing purposes. I’m currently using my ChatGPT sub, but I can only see GPT 5.5 and 5.1 Codex. Is there a way to see the most recent 5.6 models?
👋2
3 replies
Hey everyone! 👋
I'm Omkar, a third-year engineering student from India. I'm passionate about DevOps, cloud technologies, and building scalable systems. A friend of mine recently referred me to the Archestra Hackathon, and I'm excited to be here! It feels like the perfect opportunity to showcase my DevOps skills, especially since one of the hackathon tracks aligns closely with a project I'm currently building.
I'm looking forward to connecting with everyone, learning from the community, and collaborating throughout the hackathon. Excited to be part of this journey! 🚀
👋2
1 reply
Hi everyone! 👋
I'm Sunny, a Software Engineer with a background in building backend systems and cloud-based applications. Lately, I've been focusing on learning DevOps through hands-on practice, especially tools like Docker, Kubernetes, Terraform, Ansible, and CI/CD. I found Archestra through a LinkedIn post about the hackathon and joined because it seemed like a great place to learn by building real projects and connect with people who share similar interests. Looking forward to learning, collaborating, and getting to know everyone!
👋3
1 reply
Hello all, we have been trying to do a POC with archestra as our llm proxy for github copilot for a 1k+ devs. We are facing difficulties though when we try to utilize it through VS Code copilot chat. Is there a proper way to do it? Has anyone managed to accomplish it or give us any direction? When using the openai style endpoint it doesnt return any available models and when using the copilot one we get that only /chat/completions is supported.
Hi
I am Nitin. Working as DevOps engineer since last 6 years . I am very new to the slack.
Excited to join this hackethon as this is my first attempt at hackethon. I will try to solve one of our real problem which we face at our organization. Let's see how it goes as it's learning for me as well
🙌1👋1
👋 Hi everyone! Wanted to introduce myself.
I’m Ricardo Dizon Pozon. I’m a senior full-stack and applied AI engineer , with about eight years shipping production software. I started in traditional web and backend work, then moved into applied AI when it became clear the hard part wasn’t calling an API, it was making LLM systems reliable enough for real operators to depend on.
My work today is less “demo in a notebook” and more embed, discover, ship, and hand off. I’ve built LLM-powered products, RAG pipelines, agent workflows, and the evaluation habits to know whether something actually works in production.
What I actually do day to day:
• Translate messy business problems into shipped software when the spec is still forming
• Build AI workflows end to end: integrations, APIs, internal tools, and operator-facing surfaces
• Work in Python (FastAPI) and TypeScript/React depending on what the product needs
• Design for handoff: code quality, reliability, and documentation so the capability stays after the engagement
• Run discovery with non-technical stakeholders and turn that into architecture and priorities, not just tickets
• Prototype fast with modern AI dev tools (Cursor, etc.) without skipping production discipline
One thing I’ve learned: AI doesn’t remove engineering judgment, it raises the bar for systems thinking. Better outputs come from clearer constraints, better data boundaries, evals, and architecture, not just better prompts.
Excited to be here and work alongside operators who care about outcomes, not slideware. If you’re building agent workflows, internal AI tools, or thinking about how to ship AI in a PE portfolio context, I’d love to compare notes.
🙌2👋1
Hi everyone! I'm Laiba Mannan. I have +2 years of experience in DevOps and Cloud Engineering, working with AWS, Azure, GCP, Kubernetes, Docker, Terraform, CI/CD pipelines, and DevSecOps practices. My experience includes cloud infrastructure automation, container orchestration, deployment automation, security integration, monitoring, and maintaining reliable production environments. Over the past year, I've also been building AI-powered solutions and developing various AI agents within the DevOps domain, including agents for cloud operations, incident response, infrastructure troubleshooting, security analysis, and workflow automation. I'm particularly interested in how agentic AI can help engineering teams reduce operational overhead and improve productivity. For the Archestra Apps Hackathon, I'm excited to explore MCP-powered applications and build a practical solution that addresses real-world operational challenges through AI and automation.
Looking forward to learning from the community, collaborating with fellow builders, and seeing the innovative projects everyone creates.
🙌2👋1
Hi everyone! I'm Vamsi, a DevOps Engineer with around 3 years of experience working with AWS, Kubernetes, Docker, Terraform, CI/CD, and Linux.
I'm passionate about cloud infrastructure, automation, and solving real-world engineering problems. I'm excited to participate in this hackathon, collaborate with talented builders, and create something impactful using AI and modern cloud technologies.
Looking forward to connecting and building with you all!
Read-only live mirror of Archestra.AI Slack
👋Join the discussion withAI enthusiasts!