Cuttlefish connects your real tools, code, infrastructure, and internal systems as governed capabilities — not a raw toolbox handed to a model. It learns what each system can do, decides what is safe before it acts, and keeps proof of everything it does.
Most AI tools wire a system in and let the model call it directly. Cuttlefish takes the opposite path: it brings your systems in as governed capabilities, where every action is named, classified, and answerable — so reach and control are both true at once.
Connect a system as a plain tool and the model gets whatever that tool can do — read, write, delete — with little between intent and consequence. The blast radius is the whole tool, and you find out what happened afterward.
Cuttlefish turns each system into named actions, and each carries a clear boundary: look only, draft only, ask first, or off-limits. The model never sees a firehose of raw commands — it sees a small, governed vocabulary of exactly what you allowed.
The usual choice is a sealed chat box you can trust or an open tool you can't. Cuttlefish removes it: your people get AI that works inside real systems, and your organization keeps the permissions, limits, and record on the whole time. This is the core of what makes Cuttlefish different.
Review a system’s available operations and the access your organization intends to allow. Setup can include authorized connection and health checks. Permission to discover a system does not grant permission to change it.
Review the connected system and its available operations within the access you have authorized. Connection and health checks may contact that system; they do not grant broader access or permission to change it.
The system's possible operations become a clean set of named actions the assistant can use — instead of a pile of raw commands no one can govern.
Every action gets a boundary before it can be used — look only, draft only, ask first, or off-limits — so the assistant sees safe affordances, never raw power.
Approved work runs in the real system, pauses for your OK when it matters, and leaves a tamper-evident record of what it touched and what changed.
When you connect a system, Cuttlefish reads a manifest: a plain description of the actions a system offers and the boundary on each one. It is how a team says, once and in one place, what AI is allowed to do here — read this, draft that, ask before changing this, never touch that.
A manifest lists the real things a system can do — read a ticket, draft an update, change a setting — instead of exposing the whole system as one all-or-nothing tool. Each action is something a person can read and understand.
Beside every action sits its rule: read-only, prepare-only, approval-required, or blocked. A new action that isn't described defaults to off — Cuttlefish does nothing it wasn't clearly allowed to do.
A manifest describes what a system does, never the keys behind it. Credentials stay in secure storage and are never shown in conversation or handed to a model — the connection uses them; nobody sees them.
This fictional example describes operator-visible permissions and review. It is an illustration, not an import file. Configure real connections through your organization’s approved setup path.
EXAMPLE AUTHORIZED ENVIRONMENT
Illustration only — not an import file
Client Operations · fictional service desk
Read Inspect assigned tickets and service status
Prepare Draft an update for review
Approve Apply an update after the required approval
Block Delete resources outside the allowed scope
Approval owner Authorized operations lead
Review Action record and supporting evidenceRead it top to bottom and you can answer the only question that matters: what is AI allowed to do in this system, and what will it never do? That answer is set by your team, not by the model.
Every action a system exposes gets one of four boundaries the moment it is connected. That classification is what lets Cuttlefish work fast on the safe things and stay deliberate on the serious ones.
Look, don't touch. Cuttlefish can inspect or pull information but cannot change anything. Example: read the status of a deployment or summarize an open support ticket — nothing in the system is altered.
Draft and stage, but stop short of doing it. Cuttlefish can write a proposed change and lay it out for you, while the real action waits. Example: draft an update to a ticket or plan a configuration change you then review.
Review required changes. Cuttlefish shows the proposed target and effect when organization policy requires approval. Existing permissions govern allowed reads and preparation. Example: review a ticket update before applying it when that action requires approval.
Off-limits, full stop. The action is either shown as unavailable or never exposed at all, and no approval can override it from inside a conversation. Example: deleting a resource your team marked as never-allowed.
An action that hasn't been described and allowed simply doesn't run. There is no path where an uncertain check quietly becomes a yes — when Cuttlefish isn't sure it's allowed, it does nothing and tells you why. You widen what a system can do on purpose, in one place, whenever you're ready.
For anything Cuttlefish does in a connected system, you can open a plain record of what happened — written for a person, confirmed genuine, and impossible to quietly change after the fact.
Governed actions leave a record of what Cuttlefish used, what it changed, who approved it, and where the result went. You read it in seconds — no log diving, no jargon, no need to understand anything technical to know the work is sound.
Each record is sealed so that if even one detail were altered afterward, you would know. A quiet line at the top confirms the record is the original and hasn't been touched. The check runs by itself; you just see the plain result.
Everything Cuttlefish has done gathers into one running history, so audits, reviews, and "who said yes to that" questions have a straight answer. Reviewers and auditors can confirm the record is real and unaltered for themselves.
The plain reading is the default. If your security team ever wants the full technical confirmation behind a record, it's there behind an optional view — out of the way until the rare moment you need it. See how proof and control work.
Cuttlefish isn't a stripped-down personal app and a separate enterprise edition. It's one product with two postures — the same governed runtime, with an admin layer on top when an organization needs it.
Connect compatible local tools and models on your computer within the permissions you allow. Original files and device resources remain there, while selected conversation content, memories, and action evidence can be handled by hosted account services. See the Privacy Policy before choosing a data route.
Administrators configure supported sign-in, shared connections, allowed operations, and required approvals. Authorized reviewers can inspect available work records. Stop and revocation controls prevent further activity within their scope; they do not reverse external changes already made.
More on the team route: Cuttlefish for enterprise · for operators, IT & MSP teams and platform engineering.
Your organization defines the systems assistants may use and the permitted operations. Reads and preparation stay within approved access, changes require the applicable authority, and action records support review. Connection setup does not grant unrestricted access.
Each assistant works within the access allowed for its assigned task. Revoked access or a missing required approval prevents further unauthorized activity.
Saved work, approvals, and results remain available for authorized users to review and continue independently of a model provider.
Governed work can update what it was asked to change, publish a durable result, and attach a signed, tamper-evident record of who acted, under what authority, and what changed.
Download Cuttlefish and connect a system in minutes, or talk to us about a guided pilot in your environment.