@ArizePhoenix: This week in Phoenix, a big one for agentic workflows: Slash commands & skills in PXI - Phoenix's built-in agent now ha…
Summary
Arize Phoenix's built-in agent PXI now supports slash commands and skills, allowing users to invoke custom workflows directly from chat.
View Cached Full Text
Cached at: 06/13/26, 04:49 PM
This week in Phoenix, a big one for agentic workflows:
🎉 Slash commands & skills in PXI - Phoenix’s built-in agent now has a user-invokable skill menu and local slash commands right in chat. Teach it your workflows, then trigger them in a keystroke. https://t.co/5OO9NCDhN3
Similar Articles
Octomind – open-source AI harness that saves your tokens, static rust
Octomind is an open-source, Rust-based CLI-first AI coding agent runtime that gives LLMs access to repos through MCP tools, supporting interactive, piped, daemon, WebSocket, and ACP sub-agent modes with TOML-based guardrails, budgets, and adaptive compression.
Native computer-use app for driving autonomous work
Vantage is an open-source Windows 11 app that turns a typed prompt into autonomous desktop actions, using AI models to read actual window text via UI Automation, click, type, and run PowerShell rather than relying on screenshots. It brings your own API key for any OpenAI-compatible provider, stores everything locally, and is an early-stage project still seeking failure-case feedback.
@GKev1n: Stop obsessing over having Sub-agents review each other's code — you think it's "stepping on your own foot to reach the sky," but it's really "pickpocketing yourself." I couldn't agree more with poteto's take today!! She said outright that adversarial code review is mostly just burning tokens ——
The author agrees with poteto, criticizing adversarial code review between sub-agents as a waste of tokens, pointing out its three fatal flaws — meaningless nitpicking, over-engineering, and mismatched compute — and noting that top teams are shifting toward real testing, formal verification, and actual red-teaming to find issues.
Limit what agents learn about private repos with enclaves (17 minute read)
GitHub Next introduces enclaves, an experimental security primitive for GitHub Agentic Workflows that lets agents work across repositories while deterministically constraining what they can communicate back, mitigating private-to-public data leaks like the GitLost attack.
@rohanpaul_ai: DeepSeek is promoting Creator Mode, that lets its open-source Harness agent build working plugins from plain-language r…
DeepSeek is promoting Creator Mode in its free Harness AI agent app, which lets an open-source agent build, install, and test working plugins from plain-language requests. The company released a demo video and prompts behind seven examples, highlighting Harness's 268.7K GitHub stars as a potential plugin-building community.