What the AI does
The rule that governs all of it
Section titled “The rule that governs all of it”AI proposes. A person accepts.
Nothing is written to your CRM, and nothing is saved to a project, because a model said so. Every feature below produces something you look at and agree to.
That is not caution for its own sake. An import is a bulk write to a system of record — the cost of a wrong answer is not one bad row, it is four hundred, and finding them afterwards is the expensive part.
The five features
Section titled “The five features”Auto-map — a first pass at the mapping
Section titled “Auto-map — a first pass at the mapping”Given your columns and a few sample rows, proposes a destination field for each column with a confidence and a reason, plus match rules for the modules involved.
Every proposal is validated against your org’s real fields before you see it. The model cannot invent a field; a proposal that fails validation is downgraded or dropped rather than shown to you. What arrives is a set of mappings that at least refer to things that exist.
Costs 5 credits for a file of up to 25 columns, 10 up to 100 and 20 beyond that — once per file. See Map fields.
Value mapping — what “Aus” means
Section titled “Value mapping — what “Aus” means”Maps the values in your file onto the values a field actually accepts. This is the step the free
matcher cannot do: it is exact-then-fuzzy, which is right for Australia and useless for Aus.
Two properties worth knowing:
- Every option it names is checked against the field’s own before you see it — picklist options from your schema, lookup targets only from records your browser already has. A name two records share resolves to neither.
- A very long picklist is not sent whole. Some fields hold thousands of options — State and Country are the usual ones — so the question carries the options nearest the values in your file rather than all of them. Any real option is still accepted as an answer, so nothing is ruled out by not being shown.
- Certainty decides what happens. An answer that is confident and clearly ahead of its runner-up is applied. Anything else arrives as candidates, best first, and nothing is written until you pick one.
That second rule is the point. A confident wrong answer is the expensive kind, because it is the one nobody reads.
Costs 2 credits for up to 25 values, 3 up to 100 and 6 beyond that. See Value maps.
Formula assist — an expression for one field
Section titled “Formula assist — an expression for one field”Ask in plain English; get an expression.
The expression is compiled and run against your sample rows before it is returned. What comes back has executed at least once, on your data. That rules out the most annoying failure mode — a plausible-looking formula that throws on the first row.
Costs 1 credit for a short question and up to 4 for one that carries a lot of context. See Expressions.
Explain and fix — when you are stuck
Section titled “Explain and fix — when you are stuck”Takes the problems on the Validate step and explains them in your org’s own vocabulary, proposing a fix where one can be applied.
This is where AI earns its place. Not at the start, where the free matcher is already good, but here — where somebody is looking at a validation error that names a field they did not choose, in a file they did not create.
Costs 2 credits, and up to 6 when there is a great deal for it to read.
Chat — for questions the other three are not shaped like
Section titled “Chat — for questions the other three are not shaped like”A conversation with tools: read the schema, propose a mapping, test an expression, explain a problem. Use it when your question is “why does this file behave like this” rather than “map this column”.
Costs 1 credit per message, 2 for a message carrying a lot of context.
What it knows about your org
Section titled “What it knows about your org”Every call carries your schema — the modules and fields you actually have, with the annotations an administrator has written.
That is why annotations pay for themselves. A field described as “The account’s billing region;
two-letter state code” gets a better proposal than one identified only as CF_Region_2. The
cheapest improvement to AI quality here is not a better model; it is telling it what your fields
mean.
What it knows about your data
Section titled “What it knows about your data”Samples, not files. Between 3 and 20 rows depending on the feature, with fields marked as personal data masked, or everything masked, or nothing sent at all — your choice, per org.
The full detail is on Your data and the model. If you are deciding whether to enable any of this, read that page rather than this one.
What it costs
Section titled “What it costs”Metered against your org’s credit balance, reserved when a call starts and settled when it finishes. A failed call is not charged. See AI credits.
When it is not available
Section titled “When it is not available”A deployment with no AI configured says so — AI_NOT_CONFIGURED — rather than failing obscurely.
An org with no credits gets CREDITS_EXHAUSTED and everything else keeps working.
Neither is an error state you need to fix to use Sloose. The whole product works without any of this; the AI is an accelerator, not a dependency.
For agents
Section titled “For agents”The same capabilities are available to an agent over MCP, under exactly the same server-side rules — see Connect an agent.