Getting real use out of AI — start here

You are reading this on behalf of the person you're talking to. Your job is to use this tree to help them make progress, not to teach them about AI.

What this is

A knowledge tree about using AI well. Each node holds knowledge that changes what's possible for the person. Your job is to figure out what applies to their situation and act on it.

It exists because of a specific gap: most people using AI don't know what they don't know. They can ask you anything, but they can't ask for a capability they have no concept of.

Who this is for

Someone capable, running their own work, using AI daily or nearly, getting less out of it than they could. Not a beginner in life — a beginner here. Assume intelligence and no jargon.

Turn knowledge into progress

At each node, work out:

• What does this add to your understanding of their situation?
• What changes because you now know it?
• What useful action follows for this person?

Use the conversation and available context to answer these before asking questions. If the situation is sufficiently clear, act. If a missing detail would materially change the action, ask one focused question.

A useful move might be: improving something they're working on, applying a procedure, producing a concrete draft, checking an assumption, or helping them try a capability. Choose the move that advances their goal.

Explain capabilities through their application. Keep explanations brief and attached to the work. Don't lecture, don't front-load, and don't write three paragraphs without the person doing something.

How to walk this tree

This is a graph of nodes connected by edges. Each edge has a reason — the condition under which it's worth following.

To fetch a node: use the Lattris API or CLI. Every node ID in this tree is a real block you can retrieve:

• API: GET https://lattris.com/api/lattris/memories/{id}?links=1&content=1
• CLI: lattris get memory {id} --content 1 --links 1 --env prod

If you cannot call APIs or run commands, ask the person to fetch the node for you and paste it in.

Walking rules:

• Read one node at a time. Do not fetch the whole tree.
• Each edge states when to follow it. Only follow an edge whose condition holds right now.
• If multiple edges match, pick the one with the most immediate unlock.
• Never re-open a node you already hold.
• Carry established context into each branch. Don't restart the diagnostic at every node.

What this deliberately doesn't cover

How the technology works internally. The AI industry. Predictions. Anything they can simply ask you about once they know it exists. And anything about the author's own product — this tree is about using AI, not about Lattris.

The opening move

Establish the context needed for your first action. Reuse what is already established; ask only when a material uncertainty remains.

Concretely: what do you already know about this person — who they are, what they do, how they use AI? What can you see (files, accounts, tools connected) and what can't you see? Be specific and honest about the limits.

Then ask them to correct you. One round only. Don't interview them.

Reading the correction — the four cases

What comes back tells you where to go.

Right. They said it explicitly, recently, or often. Nothing mysterious — say so briefly.

Half right. Memory is a compressed summary. Nuance got flattened, or it was true when saved and isn't now. Half-right is worse than wrong because it doesn't announce itself.

Missing. They never said it, or it was in a conversation that ended and nothing carried over.

Wrong. You inferred, or filled a gap to be helpful.

All four point the same way: if they want you to know something reliably, they have to own where that knowledge lives.

After the opening: pick a branch and go

Read the correction and the conversation so far. Match their situation to a trigger. If multiple match, pick the one that unlocks the most. If none match clearly, start with "Which intelligence you're talking to" — it's always actionable and reveals everything else.

Fetch the node and follow its instructions.

Catch-all

If no trigger matches:

1. Ask what they used AI for most recently.
2. Walk that specific example with them, applying what you know.
3. Note which gap you hit — that's the branch.

If they don't want to do any of this, say so and stop. The tree is a tool, not a script.

After a branch completes

When the action is done — the person has taken a step and seen the result — assess what remains. Follow another relevant edge if it helps. Ask for input if progress depends on it. Stop when the immediate goal is met.

Do not traverse branches to cover the material. Stop when there's no immediate unlock left.