Bricks
Modular semantic
evaluation units
A Brick evaluates one clearly defined concept inside a conversation and returns structured data. It doesn't summarise - it extracts.
How bricks work
One check.
One structured output.
Each Brick uses LLM semantic reasoning against a defined rubric. It returns a typed, deterministic value - not a paragraph.
A Brick does
A Brick does not
Output types
Four output types.
All machine-readable.
Every Brick returns one of four typed outputs. All are JSON-serialisable, queryable, and suitable for automation.
Boolean
True or false. Was this thing present or not?
Numeric / Score
A number or 0–100 score. How much of this thing happened?
Categorical / Enum
A classification from a defined set. What kind of thing happened?
String List
An ordered array of strings. Which items were detected?
Examples
A library of semantic checks
Bricks can evaluate anything expressible as a semantic check. Here are examples across common use cases.
Confirms a clear next action and owner were agreed
Detects roles and decision makers mentioned
Checks for measurable pain, not vague interest
Finds timing signals and urgency cues
Detects pricing talk and captures context
Identifies objection themes mentioned
Identifies competitor names mentioned
Detects explicit budget confirmation or commitment
Checks whether the economic buyer was on the call
Evaluates whether decision criteria were explored
Calculates speaker balance between rep and prospect
Checks if the rep set an agenda within the first 5 minutes
Why bricks
Lego, not concrete.
Traditional systems bundle evaluation into one monolithic score. Bricks preserve nuance by breaking evaluation into composable, measurable primitives.
Reusable across Kits
Build a Brick once, use it in multiple Kits. next_step_confirmed works in Discovery, Forecast Risk, and Deal Hygiene Kits.
Independently versioned
Update a Brick's rubric without touching others. A/B test evaluation logic. Freeze versions for compliance.
Shareable across teams
RevOps, Enablement, and Analytics can share the same Bricks while assembling different Kits for their workflows.
Traditional call scoring
Semarize Bricks
Build your first Brick.
Get structured signals back.
No ML engineering needed. Define what you want to evaluate, and Semarize handles the rest.