Basic mode (no AI)

Cobblr runs with no AI provider connected. The features that use AI drop to a simpler mode instead of disappearing, and everything else works the same. This page is what those three features do on their own.

Scanning still works

Barcode scanning does not need AI. A scanned code is still looked up in the product catalogs, and the item still lands in your inbox to confirm. What you lose without a provider is the smart part: reading a photo that carries no barcode, and fleshing out a bare listing the catalogs return.

Routing a capture: the heuristic floor

When you scan into a workspace with several trackers, something has to decide which one an item belongs in. With AI that is the model's job; without it, a deterministic matcher takes over.

The heuristic scores each of your trackers by word overlap between the capture and the tracker's noun, its scan keywords, its field names, and its field choices. When a word in the capture matches one of a field's allowed choices, it fills that field ("worsted" sets a weight field to Worsted, because the choice list is the vocabulary). It is weaker than the model and it is free, and it means a no-AI workspace still gets a real tracker suggestion instead of a capture that never resolves. Connecting a provider sharpens the same routing.

Because the routing reads a tracker's own fields and choices, the way to improve it is to design good fields: name an instance for the thing it holds, and give its fields real choice lists. See Prompt patterns for the knobs that steer routing.

Cobb answers matched phrases

With no provider, Cobb cannot read your data or make changes. It falls back to a small built-in set of answers matched by keyword: greetings, "what can you do", and pointers to where a thing lives in the app. It is honest about the limit and tells you where the manual path is (the + New button, the Build page, the search box).

You can add to that set per workspace. Alongside the built-in answers, a workspace can override a built-in reply or add its own phrase-and-answer rules, so a common question in your setup gets a canned answer without a provider. Matching is plain keyword scoring, no model: a longer matched phrase wins over a looser single word.

Building a bundle without AI

The AI builder has a copy-paste mode that needs no provider. It compiles the prompt; you run it in your own ChatGPT or Claude and paste the result back for the kernel to validate. Starting from the ready-made bundle catalog is always there too, and needs nothing at all.