# Maplith for sales and CRM

How the AI agent a sales team already uses sees one customer split across several records, and a CRM that is days behind the customer — shown on fictional companies’ exports.

The CRM is only as good as the keys that tie it to everything else: the customer in the shop, the company in the ledger, the yes in an email. Where those keys are names typed by hand, one customer becomes several and a deal closes days after the customer said yes. Your agent can see through it — if it knows which key joins what, and how far to trust it. Maplith gives it exactly that.

LinguaNord ApS is a fictional translation agency built as our first test company: the company, its people, its customers and its translators are all invented, and nothing in the data comes from any customer.

Fjeldrev Outdoor ApS is a fictional web shop built as a test company: the company, its people and its customers are all invented, and nothing in the data comes from any customer.

## Between the systems

Recurring problems between the CRM and the systems a customer also lives in. Each was raised by a scan of a worked example’s exports.

- **One customer, several records.** Every new email address becomes a new customer, and the order history and the newsletter consent split with it. (Fjeldrev Outdoor ApS · raised by a scan of its exports.)
- **The same customer, spelled differently in every system.** The project system, the CRM and the ledger each spell the customer their own way, so any join between them by name is fragile. (LinguaNord ApS · raised by a scan of its exports.)
- **A deal that closes after the customer said yes.** The CRM records the win two to six days after the customer accepted by email, so sales-cycle figures read from the CRM alone are late. (LinguaNord ApS · raised by a scan of its exports.)

## Workflows

One workflow from the outdoor shop’s recorded scan. Everything in it ships today.

### One customer, several customer records

The same person buys under several email addresses, and each becomes a customer of its own.

**Without Maplith.** The shop makes a new customer for every email address. In the worked example one person holds three customer records under three addresses, with four orders spread across them and the newsletter tag on only one. Every figure per customer — lifetime value, consent, order count — inherits the split, and no system shows it.

**With Maplith:**

1. **Findings** — A scan of the exports raises it as a finding: the customer records that are one person, the orders spread across them, the tag applied to one of them, and a recommendation.
2. **The map** — The map shows that the email address is the only key joining customers, orders and tickets, so an agent reading a figure per customer knows the split travels with it.
3. **Ask** — `ask`: “which key identifies a customer here, and what should I not rely on?” — answered from the map, citing the objects and joins it rests on.
4. **The action gate** — `request_action` to merge the records, if the business declared that operation: the business decides per key whether a person approves each merge.
5. **Record and value** — `record_action` writes what was merged, so the next task context on the same thing shows it.

Worked example: [Fjeldrev Outdoor ApS](/industries#fjeldrev).

## The pieces

| Piece | Tool | What it gives the agent | Status |
|---|---|---|---|
| The map | `get_object` | Where each thing lives and how the systems join, with the rate Maplith measured for every join it could test. | live |
| Findings | `list_findings` | Where the systems disagree, raised by a scan of the exports — each with the evidence it rests on and a recommendation. | live |
| Ask | `ask` | One question in plain language, answered from the map with citations — never from rows. | live |
| The action gate | `request_action` | Allowed, pending a person, or denied — before the agent acts, with a grant good once. | live |
| Record and value | `record_action` | What was done, so the next judging does not raise it as though nobody had looked — and counted in “What you got”. | live |

## The worked examples

- **[LinguaNord ApS](/industries#linguanord)**, a translation agency. The findings and processes quoted from it come from a recorded scan of its exports. There is no public map or key for it.
- **[Fjeldrev Outdoor ApS](/industries#fjeldrev)**, a web shop selling outdoor gear. The findings quoted from it come from a recorded scan of its exports. There is no public map or key for it.

Every department: [Solutions](/solutions). The worked examples: [Worked examples](/industries).