Nothing keeps its own copy.
Extraction, rating, workflows, reporting and the assistant all resolve against the same objects, attributes and relationships. One graph underneath, so a correction lands once and is true everywhere.
One value, and everything that reads it. A figure lands on a record once. It is then what prices the risk, what the workflow branches on, and what the roll-up counts.
Documents land on your objects.
An extractor names the object and the path through your relationships a field belongs to. What comes back is a proposed change to those records, not a summary of the file.
Rating reads the record.
A rate table names the object it rates, and a rating run pulls its inputs by querying that record. The premium it computes is written straight back onto it.
Workflows watch the attribute.
A trigger names the attribute it watches and the value that should fire it. The run opens with the changed row already in scope.
Metrics are queries, not exports.
A portfolio metric is a saved query over your records. Group it by any attribute you can reach from the object it counts, then split that by product and by lifecycle state.
“We stopped arguing about which system was right. There is one record now, and the rating, the referral and the month-end report all move with it.”
The assistant sits inside the graph. Ask Riska works from your object model and your records, not from a general reading of insurance documents.
It knows what you call things.
The assistant is handed your object model in your own words, with every object and every relationship carrying the label your team gave it. Rename an attribute and its picture of the model updates on the change, not on a schedule.
It holds what it just touched.
Every record the conversation touches is kept with its real id, its object and its label. Ask about the second one and it resolves to that record, then opens where you would have clicked.
It cannot invent a figure.
Totals are computed over the whole filtered set and returned with the population they cover. When it draws you a table, it points at the query result rather than retyping the rows.
One address, and the rest comes free. Every record is reachable the same way, so the things most systems rebuild per module are built once here and work on all of them.
One search box
Records, files, notes, tasks, comments, companies and people, from a single field.
One history
A record's activity tab is its change log: who moved which columns, when, and what the row read before.
Notes on anything
Notes, threaded comments and mentions attach to any record type, including the objects you added yourself.
Favorites and recents
Pin or return to anything you can open, in folders you arrange yourself.
References that resolve
A pointer to a record carries its display label, so the same chip reads correctly on a task, a comment and an audit row.
One set of permissions
Agents and automations call the same interfaces your team does, and see exactly what the caller is allowed to see.
Three kinds of change, one history. A person, a release or an agent can move the same record, and the record keeps one account of all three.
Someone edits the record
The edit is written once and logged with the actor, the time and the columns that moved. Open the entry to see the row before and after.
You change the model
Objects, attributes, views, document types and rate books are versioned together as one release. Publish it and every surface reads the new shape at the same moment.
An agent changes it
An agent write is stamped with the agent and the conversation it came from, and a change to a record waits for a person to approve it before it lands.
The surfaces that share it.
Every one of these reads and writes the same records. Start wherever the work starts.
See it on one account.
Bring an account you keep in three systems today. We will model it once, then show you the same record in the workbench, in the pricing, in the report and in the assistant.
Usually 30 minutes, with an underwriter on the call.