FAQ

A node is one capability, packaged. It pairs an AI skill with a facilitated method and the guidance to run both, and it is pointed at a single real decision: how to price this, whether to fund that, what to build next.

What it changes: you stop buying an answer and start holding the capability that produces answers. A consultant leaves with the method in their head. A node stays, and you re-run it on the next decision at no extra cost.

A skill is a set of instructions and reference material that teaches an AI model to do one job the way an expert does it. It is the automated half of a node. Ours run as an interactive interview: the model asks, researches, drafts, and challenges its own output, and you steer.

What it changes: the model stops being a blank chat window that needs to be re-briefed every time. The expertise is in the skill, so the tenth run is as good as the first, whoever on your team is running it.

The method is the facilitated session where your team challenges what the skill produced and owns the decision that comes out of it. It is the half that cannot be automated, and it is deliberate: AI output is a draft to interrogate rather than an answer to accept.

What it changes: the judgement stays in the room with the people accountable for it. That is the whole design, and it is why a node is a workshop plus a skill rather than just a skill.

A node hands you a specific capability, built by a domain expert and facilitated by us. Build & Run training teaches you to build your own, live on your screen, on your own stack. No Canopy skill is involved in training.

What it changes: buy a node when you have a decision in front of you now. Take the training when you would rather own the ability to build the leverage yourself. Plenty of clients start with the training.

The same idea as above, in Anthropic's own packaging: a folder of instructions, and optionally scripts and reference files, that Claude loads when the task calls for it. Canopy nodes ship as Claude skills today, and the format is simple enough that your team can write its own.

What it changes: a way of working becomes a file you can version, review, and hand to a colleague. Knowledge that used to live in one person's habits becomes something the whole team runs.

MCP, the Model Context Protocol, is an open standard for connecting an AI model to your systems: your CRM, your file store, your ticket tracker, your database. One integration per system, and any MCP-speaking model can then use it.

What it changes: the model stops working from whatever you paste into it and starts working from your actual data. That is the difference between asking for a generic pricing framework and asking about pricing given the last two years of your own deals.

Claude Code is Anthropic's agentic tool for real work in a real environment: it reads and edits files, runs commands, and works through multi-step tasks rather than answering in a chat box. Engineers use it in the terminal and in their editor. It is not only for engineers, and this website is built with it.

What it changes: the model moves from advising on the work to doing the work, with you reviewing. That is a different relationship with the tool, and it takes some getting used to.

No. Canopy nodes run on Claude today and are portable by design, so the same node can run against another model, or through a proxy or gateway you already use, or against a model you host yourself. On Applied AI engagements we go deepest on Claude and also deploy Mistral, OpenAI, or open models where they fit your data, budget, or sovereignty needs.

What it changes: you are not holding a capability that only works in one place. Models come and go faster than capabilities do.