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.

A step-by-step guide to running an AI would-you-choose channel: an agent team writes a premise and a run of absurd options in one theme, generates each as its own glossy shot, and queues each video for you to approve.

A step-by-step guide to running an AI glass food channel: an agent team generates foods made of glass sliced slowly on a cutting board, and queues each video for you to approve.

A step-by-step guide to running an AI fruit drama channel: an agent team tells reality-show dramas with one recurring fruit cast and queues each episode for you to approve.

A step-by-step guide to running an AI food slime channel: an agent team generates one real-looking food kneaded into glossy slime, with ASMR sound, and queues each video for you to approve.

A step-by-step guide to running an AI cat stories channel: an agent team invents a cat family, tells short stories of their human lives in a few scenes, and queues each video for you to approve.

A step-by-step guide to running an AI dancing animals channel: an agent team generates one animal from your niche up on its hind legs, dancing on the beat, and queues each video for you to approve.

A step-by-step guide to running an AI comics channel: an agent team writes short original comic stories, generates them as moving panels in one inked look, and queues each video for you to approve.

A step-by-step guide to cloning a viral channel's format with AI: an agent team studies a channel you name and generates new videos in that format, never its clips. You approve every post.

Start an SEO and GEO agency by deploying a ready-made naïve company template: a team of AI agents, a CRM, a lead-capturing website, and per-client specialists that win classic search and AI answers.

A step-by-step guide to running an animals eating video channel: an agent team researches what works, generates videos of one healthy animal eating a big feast, and queues each one for you to approve. Nothing to film.

A step-by-step guide to running an AI recruiting agency: candidates are sourced and screened against a role brief, and a scored shortlist awaits your approval.

A step-by-step guide to running an AI paid ads agency: an agent team per account picks angles, makes creative, and rebalances spend under a cap it cannot raise.

A step-by-step guide to running an AI newsletter: an agent team reads your beat daily, drafts each issue from sourced stories, grows the list, and queues every send for your approval before it reaches anyone.

A guide to running an AI mythology channel: a team of AI agents fact-checks each myth, generates it at painterly scale, narrates it, and queues it for approval.

Run an AI clipping channel: point an agent team at a podcast, stream, or back catalogue you own, and it cuts hook-first verticals and queues each for your approval.

A step-by-step guide to starting an AI automation agency: a CRM, a public site whose enquiry form feeds it, a workspace per client, and an agent team that works the pipeline, content, and site. You bring the trade.

Run a talk clips channel: an agent team finds quotable moments in talks you have rights to, cuts them vertical with captions, and queues each clip for your approval.

A step-by-step guide to running a sports highlights channel: an agent team watches the games you have rights to, cuts the clutch plays vertical with the score on screen, and queues them for you to approve.

A step-by-step guide to running a podcast clips channel: an agent team finds the moments in your episodes that stand on their own, cuts them vertical with captions, and queues each clip for you to approve.

A step-by-step guide to running a news clips channel: an agent team watches sources you have rights to, cuts the moment that explains each story into a captioned vertical clip, and queues it for your approval.

A step-by-step guide to running a long-form video channel: an agent team takes one subject a day, sources every claim, plans it against a real video of the same length, and queues the finished file for your approval.

A guide to running a gaming clips channel: a team of AI agents cuts the clutch plays from streams you own into vertical clips and queues each for your approval.

Start a faceless video channel: deploy a ready-made naïve company template — an agent team, dashboard, posting accounts, and budgets in one step — then pick a niche and approve every post it queues.

A step-by-step guide to running a faceless AI UFC channel: an agent team researches fight trends, writes and generates original fight videos, and queues them for you to approve. No footage, no camera, no real fighters.

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.