Notes from the company floor.

Two new agent primitives. One turns a prompt or a few photos into a textured 3D model. The other runs a CAD or Blender script on the agent's computer and hands back STEP, STL and GLB.

The week of September 29: a redesigned site, live voice calls, set-up-before-you-pay onboarding, a studio that works like an app, agents that build apps, new primitives, benchmarks, and a creator program.

Agents and developers on Naive Managed Agents can now read public posts, profiles, comments, followers, hashtags and trends on 21 social networks, with no connected account.

Naive Managed Agents now runs disposable cloud phones that your code and your agents drive by looking and touching. Here is what one is, how it ends itself, and what it costs.

Agents and developers on Naive Managed Agents can now search and run about 1,900 read-only data tools across 18 domains, from companies and finance to jobs, weather and real estate.

Same model, same tasks, same completion window, only the harness changed: Naive Managed Agents costs 2.7x less per attempted task than the next-best harness while completing more of them.

Every Naive Managed Agents session gets an isolated Linux micro-VM with a shell, a filesystem and an optional browser. It pauses between turns, so an idle agent costs storage only. Here is how it works and what it costs.

The Vault primitive stores API keys and tokens an agent needs but must never read. Values are sealed once, injected at the network boundary, and never returned by any route.

Form a real US LLC for an agent's identity. Verified founders go in, a company with an EIN comes out, and the entity becomes what the persona's domains, inboxes, numbers and cards attach to.

Verify the human behind an agent once, then let that identity hold domains, inboxes, phone numbers, cards and a company. Here is what verification unlocks, and what it never exposes to the agent.

Every organization gets a working system domain at signup. Connect a domain you already own, verify it, and hang inboxes and apps off it through the Naive Managed Agents API, SDK and CLI.

Understand how an autonomous media company researches, produces, distributes, and learns—and how it differs from an AI video generator.

Discover AI storytelling channels and examine how creators build short films, recurring characters, anthologies, and serialized fictional worlds.

Explore five AI history channels, compare their storytelling formats, and learn how to build a repeatable production workflow with factual review.

Study AI animal-story channels and the recurring characters, visual storytelling, and production choices behind their Shorts and series.

An AI-native cloud is the hosting and data slice an agent can provision by API: apps, Postgres, storage, functions, auth, compute, queues and sandboxes, gated by allow / ask / deny policies and a USD budget.

AI agent infrastructure is the runtime an agent loop runs on plus the gateway primitives it acts through, with policy enforced at every tool call. A map of the nine categories.

Keep the coding agent or orchestrator you already use. Point it at usenaive.ai/skill.md, reach every Naïve primitive as an MCP tool, and gate each one with allow, ask, or deny.

Six ways to cut an agent off on Naïve: interrupt or cancel the session, delete the vault credential, revoke the connection, revoke the API key, deny the tool. Why network-boundary injection makes each one instant.

Gate an AI agent's risky tool calls with an ask policy: the session pauses, a person approves it over a webhook, the dashboard or the CLI, and a USD budget caps spend regardless.

In Naive Managed Agents the harness (the agent loop) is the layer you pick and the runtime is always managed. When to keep the default harness, when to bring your own, and what each does to cost per completed task.

How to give every SaaS customer an isolated, governed agent: one organization per customer, a budgeted agent, allow/ask/deny policies, personas, a write-only vault, and webhooks back into your product.

An autonomous company is a repo: a naive.config.ts declaring the apps and the agent team, provisioned by naive up, run by a coordinator under per-agent budgets and approvals. Here is how one works.

How Naïve attributes the open-source software it builds on, why MIT-licensed code in a commercial product is the point of the license, and where the line sits between upstream code and the stack we built ourselves.

An even-handed 2026 review of ten platforms people use to build autonomous, agent-run companies: app builders, agent frameworks, and company templates that deploy an agent team.