It's Wednesday, April 15th: This week, builders can plug AI coding agents directly into a live Shopify store, turn any Confluence page into charts or interactive apps, and deploy long-running cloud agents without building any infrastructure themselves.
Head over to our Events Portal to get the latest on upcoming AI Collective events near you. Search by city, date, or event format, and join thousands of builders at events across 100+ chapters on every continent (except Antarctica, for now).
Find an event in your city using the link below.👇
In Today’s Top Tools, we spotlight some of the most innovative, creative AI apps that we recommend adding to your stack.
🛒 Shopify AI Toolkit, Your Store Controlled by Plain English
Shopify open-sourced a free plugin on April 9 that connects AI coding agents directly to your store. Point Claude Code, Cursor, or VS Code at it, and you can update products, manage inventory, run bulk SEO changes, and execute pricing rules in plain English. No dashboard login needed. It ships as an auto-updating plugin covering 16 distinct agent skills, and setup takes one or two steps.
How It Works
The toolkit builds on Shopify's Dev MCP Server and connects to Claude Code, Cursor, VS Code, Gemini CLI, and OpenAI Codex. The 16 skills cover four jobs: learning the Shopify API surface, pulling live documentation, validating code before it runs, and executing store operations through the Shopify CLI.
What You Can Do
Describe a product collection in plain English — the agent writes and executes the correct GraphQL API calls
Run bulk SEO updates, discount configurations, and product image swaps without opening the admin
Introspect the full GraphQL schema in real time before writing any code
Validate Liquid theme and Hydrogen component code blocks before deploying
How to Get Started
Free and MIT-licensed. You only pay for your existing AI agent subscription. One or two setup steps in Claude Code; plugin plus MCP config for Cursor and VS Code. Store execution requires Shopify CLI authentication and a Partner account. Standard API rate limit: 1,000 cost points per minute.
📄 Confluence Remix, Turn Any Doc Into a Visual in Seconds
Atlassian launched Remix in open beta on April 8 for Confluence Cloud users with Rovo. Highlight any section of a Confluence page — a table, a paragraph, or an entire document — and Remix generates a chart, infographic, or scorecard layered on top of it. The original content stays intact, and the visual updates automatically as the underlying page changes. Three partner agents also launched the following week, connecting Confluence pages directly into Lovable, Replit, and Gamma.
How It Works
Rovo, Atlassian's AI layer, adds a visual layer on top of existing Confluence pages without touching the source. Supported output formats: data visualizations, infographics, scorecards, and charts. You choose from preset formats or write a freeform prompt. According to Atlassian's own data, pages with at least one visual element are nearly 2x as likely to be read by a wider audience, and 18% more likely to get views overall.
What the Partner Agents Do
Three MCP-backed agents launched in open beta the week of April 13:
Lovable: turns a product spec into a working interactive prototype
Replit: converts a technical document into a starter app you can fork
Gamma: transforms meeting notes into a polished presentation
How to Get Access
Open beta for Confluence Cloud customers with Rovo. No custom scripting required. Admins enable the partner agents through Atlassian Administration. A Rovo trial is available through the Atlassian marketplace.
🤖 Claude Managed Agents, Ship Cloud Agents Without the Infrastructure Work
Anthropic launched Claude Managed Agents in public beta on April 8. Instead of building your own agent loop, execution sandbox, and error handler from scratch, you define the task and Anthropic runs the infrastructure. The service covers sandboxed code execution, state management, context compaction, and end-to-end tracing out of the box. Early adopters include Notion, Rakuten, and Asana. It is available to all Claude API accounts today.
How It Works
You create an Agent (model, system prompt, tools), an Environment (cloud container with your packages and network rules), and a Session (the running task). Claude executes autonomously, reading files, running shell commands, browsing the web, writing and running code and streams results back via server-sent events. Event history persists server-side and is fetchable in full at any point. The session can also be steered or interrupted mid-execution.
Built-in Tools
Bash — run shell commands in the container
File operations — read, write, edit, glob, grep
Web search and fetch — live research and content retrieval
MCP server connections — plug in any external tool provider
Best For
Tasks that run minutes to hours with multiple tool calls — code review pipelines, research and summarization agents, data processing workflows, automated QA runs. For low-latency, synchronous calls, the standard Messages API is the right fit.
How to Get Access
Available to all Claude API accounts in public beta. The Anthropic SDK sets the required beta header automatically. Pricing: standard Claude token rates plus $0.08 per session-hour for active runtime. Research preview features — outcomes, multi-agent orchestration, and persistent memory — require a separate access request.
In this section, we feature a few standout opportunities leading AI companies, non-profits, and other organizations. Each role is selected for impact and relevance to our community.
🔬 Work at a Lab / AI Safety
Roles at frontier labs, safety organizations, and research institutions
RESEARCH ENGINEER / SCIENTIST, ALIGNMENT SCIENCE — Anthropic | San Francisco, CA (Competitive Salary + Equity)
ML ENGINEER, SECURE AI LAB — Carnegie Mellon University SEI | Pittsburgh, PA / Washington, DC (Competitive Salary)
DATA SCIENTIST, ALIGNMENT — AE Studio | Remote (USA) / Los Angeles, CA (Competitive Salary + Equity)
INSIDER RISK INVESTIGATOR, TECHNICAL AND HUMAN INTELLIGENCE — Anthropic | San Francisco / New York / Seattle (Competitive Salary + Equity)
STANDARDS RESEARCHER — SaferAI | Paris / London (Competitive Salary)
🚀 Work in Industry
Roles at funded AI startups and private companies
ML ENGINEER, PHYSICAL AI — Encord | San Francisco, CA ($150K–$200K)
FORWARD DEPLOYED ML ENGINEER — Triomics | New York, NY ($170K–$190K)
AI ENGINEERING LEAD — Aden | San Francisco, CA / Remote ($250K–$350K)
SENIOR SOFTWARE ENGINEER — Confido | New York, NY ($210K–$280K)
SOFTWARE ENGINEER, DATA PLATFORM — OneChronos | New York / Amsterdam / London / Tokyo ($115K–$200K)
🏛️ Work in AI Policy / Governance
Roles in government, think tanks, NGOs, and policy organizations
POLICY ADVISOR / SENIOR POLICY ADVISOR — Control AI | Washington, DC (Competitive Salary)
SENIOR ANALYST / COUNSEL, AI GOVERNANCE — Future of Privacy Forum | Washington, DC (Competitive Salary)
POLICY DIRECTOR — Institute for AI Policy and Strategy | Remote, DC / London / SF preferred (Competitive Salary)
RESEARCH MANAGER, AI GOVERNANCE — Pivotal Research | London, UK (Competitive Salary)
🌁 MongoDB.local London: For Founders Building What's Next (Old Billingsgate, May 7)
Join AI founders at .local London to scale from prototype to production. Hear from CJ Desai, 20VC’s Harry Stebbings, Sequoia, Hugging Face, and more.
Apply for your complimentary Founder Pass using the link below.
🤝 Thanks to Our Premier Partner: Roam
Roam is the virtual workspace our team relies on to stay connected across time zones. It makes collaboration feel natural with shared spaces, private rooms, and built-in AI tools.
Roam’s focus on human-centered collaboration is why they’re our Premier Partner, supporting our mission to connect the builders and leaders shaping the future of AI.
Experience Roam yourself with a free 14-day trial!
🫵 Do You Belong on Our Newsletter?
Share your message with the world’s largest AI community. To inquire about partnership availability, reach out to our team below.
The AI Collective is a community of volunteers, made for volunteers. All proceeds directly fund future initiatives that benefit this community.
Before You Go…
💬 Join Slack: AI Collective
🧑💼 LinkedIn: The AI Collective
📸 Instagram: The AI Collective
𝕏 Twitter / X: @_AI_Collective
Get Involved in Your Community
Thank you to the thousands of volunteers around the world who make this work possible. We truly could not do this without you.
About Noah Frank
Noah is a researcher, innovation strategist, and ex-founder thinking and writing about the future of AI. His work and body of research explores the economics of emerging technology and organizational strategy.
About Joy Dong
Joy is a news editor, writer, and entrepreneur at the forefront of the emerging tech landscape. A former educator turned media strategist, she currently writes TEA, where she demystifies complex systems to make AI and blockchain accessible for all.