Notes from the company floor.
How the companies actually run.
How agent-run companies work, what the primitives underneath them do, and what we learned building Vetta.
- Launch/sessions
Vetta: the most efficient managed agent for long horizon tasks
Same model, same tasks, only the stack changed: Vetta finishes a task 2.7x cheaper than the next-best harness while completing more of them. We built every layer of the stack to make that number possible.
LaunchAugust 17, 2026·8 min - /computer /computer /computer /computer /computer /computer /computer /computer /computer /computer/computer /computer /computer /computer /computer /computer /computer /computer /computer /computer/computer /computer /computer /computer /computer /computer /computer /computer /computer /computer/computer /computer /computer /computer /computer /computer /computer /computer /computer /computer/computer /computer /computer /computer /computer /computer /computer /computer /computer /computer/computer /computer /computer /computer /computer /computer /computer /computer /computer /computer/computer /computer /computer /computer /computer /computer /computer /computer /computer /computer/computer /computer /computer /computer /computer /computer /computer /computer /computer /computer/computer /computer /computer /computer /computer /computer /computer /computer /computer /computer/computer /computer /computer /computer /computer /computer /computer /computer /computer /computer/computer /computer /computer /computer /computer /computer /computer /computer /computer /computer/computer /computer /computer /computer /computer /computer /computer /computer /computer /computer/computer /computer /computer /computer /computer /computer /computer /computer /computer /computer/computer /computer /computer /computer /computer /computer /computer /computer /computer /computerLaunch/computer
Introducing the computer: a micro-VM for every agent session
Every Vetta session gets an isolated Linux micro-VM with a shell, a filesystem and an optional real browser. It pauses between turns, so an idle agent costs storage only. Here is how it works and what it costs.
LaunchAugust 2, 2026·8 min - /what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /whatGuidenaïve
What is an AI-native cloud? The hosting slice an agent operates
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.
GuideJuly 30, 2026·8 min - Guidenaïve
What is AI agent infrastructure? The runtime and gateway layers
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.
GuideJuly 30, 2026·8 min - Guide/skills
Naïve inside your agent framework: skill.md, MCP tools, policies
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.
GuideJuly 15, 2026·8 min - /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log/audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log/audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log/audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log/audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log/audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log/audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log/audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log/audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log/audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log/audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log/audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log/audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log/audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-log /audit-logGuide/audit-log
How to revoke an AI agent's access instantly
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.
GuideJuly 11, 2026·8 min - Guide/approvals
How to add human approval to an AI agent
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.
GuideJuly 11, 2026·8 min - /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router/model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router/model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router/model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router/model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router/model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router/model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router/model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router/model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router/model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router/model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router/model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router/model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router/model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-router /model-routerGuide/model-router
Hosted vs bring-your-own harness for AI agents
In Vetta 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 choice does to cost per completed task.
GuideJuly 11, 2026·8 min - /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets/budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets/budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets/budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets/budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets/budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets/budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets/budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets/budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets/budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets/budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets/budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets/budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets/budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgets /budgetsGuide/budgets
Building AI agents into your SaaS: the multi-tenant playbook
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.
GuideJuly 3, 2026·8 min - Launch/vault
Introducing Vault: write-only secrets your agent uses but never sees
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.
LaunchJuly 1, 2026·7 min - /what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /what/what /what /what /what /what /what /what /what /what /whatGuidenaïve
What is an autonomous company? A founder's guide
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.
GuideMay 21, 2026·8 min - Launch/formation
LLC formation for AI agents: a real US company, KYC to EIN
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.
LaunchMay 2, 2026·7 min - /verification /verification /verification /verification /verification /verification /verification /verification /verification /verification/verification /verification /verification /verification /verification /verification /verification /verification /verification /verification/verification /verification /verification /verification /verification /verification /verification /verification /verification /verification/verification /verification /verification /verification /verification /verification /verification /verification /verification /verification/verification /verification /verification /verification /verification /verification /verification /verification /verification /verification/verification /verification /verification /verification /verification /verification /verification /verification /verification /verification/verification /verification /verification /verification /verification /verification /verification /verification /verification /verification/verification /verification /verification /verification /verification /verification /verification /verification /verification /verification/verification /verification /verification /verification /verification /verification /verification /verification /verification /verification/verification /verification /verification /verification /verification /verification /verification /verification /verification /verification/verification /verification /verification /verification /verification /verification /verification /verification /verification /verification/verification /verification /verification /verification /verification /verification /verification /verification /verification /verification/verification /verification /verification /verification /verification /verification /verification /verification /verification /verification/verification /verification /verification /verification /verification /verification /verification /verification /verification /verificationLaunch/verification
Introducing KYC: identity verification for your agent, done once
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.
LaunchMay 1, 2026·7 min - Launch/domains
Introducing Domains: DNS, email and apps for your agent's identity
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 Vetta API, SDK and CLI.
LaunchApril 16, 2026·8 min - Comparisonnaïve
Top 10 platforms to build autonomous companies in 2026
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.
ComparisonApril 8, 2026·8 min - Engineeringnaïve
Naïve and Paperclip: attribution, MIT, and what we actually build
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.
EngineeringApril 8, 2026·7 min