ReportAnthropic created an entire suite of abstractions to ensure credentials never have to touch the sandbox — an incredibly important decoupling. Every container that has access to any secret uses totally fake secrets that don't actually work if used to call the real API; credentials are substituted for real values only at the egress proxy layer on the way out of the container. So there is no way physically to prompt Claude or access the sandbox and get the credential off the sandbox or off Claude's brain. Take credential safety seriously — by default you should not be able to foot-gun yourself into leaking credentials when using Claude Managed Agents.
described
AI Engineer · Why One AI Agent Isn’t Enough (And How to Run 1,000) - CJ Avilla & Harrison Stall, Anthropic
ReportWhen a task has too many pieces for one agent, dynamic workflows let the agent write the workflow itself and a server runs it in the background.
AI Engineer · Why One AI Agent Isn’t Enough (And How to Run 1,000) - CJ Avilla & Harrison Stall, Anthropic
ReportA new code layer can be created directly on the Figma canvas, with presets on the right panel for starting from particular sizes, and work begins by prompting directly into the layer.
Figma · Explore ideas in code | Figma
ReportA code layer can be started from existing code by uploading a local folder or cloning a GitHub repository (with a connected, authorized GitHub account), keeping the repo on the main branch.
Figma · Explore ideas in code | Figma
ReportHitting the preview button on a code layer shows the app running live on the canvas; a cloned repository becomes a fully live, previewable app (e.g., a marketplace browsing experience plus a map view).
Figma · Explore ideas in code | Figma
ReportThe extract designs feature pulls code into Figma as actual editable design layers: extract the current state of a code layer, select an individual element to extract just that element, or record a flow (navigate pages, then stop) to capture multiple screens as full layers.
Figma · Explore ideas in code | Figma
Principle · MoneyMoving to a 3PL was probably the best move the brand made; self-fulfillment is fun until it isn't, and the decision ties back to being present with your kids rather than living in a warehouse 12 hours a day.
Foundr · We Started Dad Gang with $750 and One Hat - and did $40M in 4 Years
Principle · MoneyThe guest offers the theory that going product-first turns you into a product-led brand instead of a community-led one. Dad Gang built community by being themselves rather than being strategic, running a private Facebook group of 15,000 dads who interact with them and give product input, and talking with community members daily in DMs, emails, and comments instead of automating engagement.
partial
Foundr · We Started Dad Gang with $750 and One Hat - and did $40M in 4 Years
Creator perspective · MoneyBuild the audience first before expanding the product line; starting product-first risks becoming a product-led brand rather than a community-led brand, and if you have an audience to listen to, build it first before guessing what new colors to release.
Foundr · We Started Dad Gang with $750 and One Hat - and did $40M in 4 Years
Principle · MoneyKeep overhead low by outsourcing functions like 3PL and customer service; a lean structure also lets founders go full-time sooner.
Foundr · We Started Dad Gang with $750 and One Hat - and did $40M in 4 Years
Principle · MoneyThe founders advise focusing on getting really good at selling one product (their black-and-white trucker hat) before adding other colors or SKUs, because there's a timing for everything; adding many SKUs early is a massive headache for apparel brands, and outside noise will push you to complicate your life with new colors, shapes, t-shirts, and sweatpants.
Foundr · We Started Dad Gang with $750 and One Hat - and did $40M in 4 Years
Creator perspective · MoneyThe speaker argues that moving to a 3PL was probably the best move they made because they could scale alongside a partner growing at the same time, and recommends choosing a 3PL that is also a growing startup so you can go through growing pains together.
Foundr · We Started Dad Gang with $750 and One Hat - and did $40M in 4 Years
Principle · MoneyThe speaker asserts that the biggest signal for building a high-performance team is who you fire — even bigger than promotions. He immediately qualifies this: he is not advocating a fire-everybody culture. The point is to enforce a minimum bar, not to treat termination as the default tool.
Alex Hormozi · My honest advice on how to raise your team’s bar
Creator perspectiveIf models can identify the chemist from the molecule alone, they may be inferring chemist intent rather than learning physics — meaning they may not learn what you're trying to teach them. Hunt down model-cheating failure modes in high-dimensional biological data before trusting results, and chase down noise sources like instrument identity if a model can predict which instrument a dataset was run on.
Latent.Space · Lab-in-the-Loop at Compute Speed — Ian Quigley, Leash Bio
Principle · MoneyHarish Gaggar says every tool defined in an MCP server must be fully reviewed by the internal security team so only authorized tools reach production, and tools should enforce filters, limits, and block fields that are not required to go to the LLM.
AI Engineer · Paving the Road to Production: Governed Enterprise AI Agents — Harish Gaggar, Credit Karma
Creator perspective · MoneyAt the core of the NX incident is that a malicious actor was able to use a trusted dependency to talk directly to an unsandboxed agent. Because dev coding tools were already trusted local tools with full file system access, they were the single most effective search tool already sitting on the machine, ready to be corrupted. The agent's environment had everything from SSH keys to cloud credentials to tokens for every service the developer used a coding agent to touch. The failures were: agents running locally on the actual computer itself, package content reaching the agent completely unfiltered, and the agent having unrestricted access to both the file system and the outbound network — which is how it was able to both find the secrets and exfiltrate them.
AI Engineer · Your AI Isn’t the Problem. Your Infrastructure Is. — Jiachen Jiang, Coder
Creator perspective · MoneyGiving agents all three lethal trifecta capabilities is an open door to compromise the whole organization. The trifecta is illustrated by the Replit incident: an agent with access to private data, a path to the internet, and a route to production could run destructive commands, exfiltrate data, and cover its tracks.
AI Engineer · Your AI Isn’t the Problem. Your Infrastructure Is. — Jiachen Jiang, Coder
Principle · MoneyThe big lesson from the Copilot incident is that we cannot let AI tooling have more access than it needs, especially to the point where it gets to totally bypass controls that human employees are subject to. Just because the attacker had access to Copilot, they were able to get around the vast majority of the company's access controls, and they were able to pull internal information about data exfiltration and bypassing DLP measures that the compromised finance user should have no business asking about.
AI Engineer · Your AI Isn’t the Problem. Your Infrastructure Is. — Jiachen Jiang, Coder
Principle · MoneyMove checks that run in CI to earlier in the development lifecycle (shift left) — it's cheaper to catch issues earlier and reduces downstream bottlenecks. Moving some checks left also significantly reduces the test load on CI.
AI Engineer · Rebuilding CI for AI-Scale Commit Volume — Gautam Korlam, Sonar
Principle · MoneyNever let the agent that made a change approve its own change, because that would not be zero trust; ensure the change was approved and tested by someone who did not write it.
AI Engineer · Rebuilding CI for AI-Scale Commit Volume — Gautam Korlam, Sonar