Skip to main content
​
November 2025

​
Semilattice MCP

Semilattice MCP is a Model Context Protocol server that gives AI assistants and AI-powered agents the ability to predict how specific audiences answer questions.Learn how to connect your AI assistant, IDE, or agentic tooling here.
​
September 2025

​
Batches, faster predictions, new methods, and new names

API v1.1.0 SDK v0.6.0

​
Batches

  • You can now include batch object when creating multiple predictions to provide a name and description for the set.
  • Predictions which are part of a batch will have a batch field set with an ID for the batch.
  • This ID can be used to fetch all predictions in the batch: /predictions/batch/{batch_id}

​
Faster predictions

​
New methods

We have added two new methods:
  • GET /populations returns all population models available for simulation
  • GET /predictions|tests/batch/{batch_id} returns batch details and all batch predictions for a batch

​
New names

We have renamed some methods and object fields to simplify the API. Old methods and fields still work but are marked as deprecated.New method names:
  • POST /answers -> POST /predictions
  • POST /answers/benchmark -> POST /tests
New field names on predictions (previously called answers):
  • simulated_answer_percentages -> predicted_answer_percentages
New field names on tests (previously called answers):
  • simulated_answer_percentages -> predicted_answer_percentages
  • kullback_leibler_divergence -> information_loss
  • normalised_kullback_leibler_divergence -> normalised_information_loss
  • root_mean_squared_error -> squared_error
New field names on populations:
  • avg_mean_absolute_error -> average_accuracy (inverted)
  • avg_mean_squared_error -> average_squared_error
  • avg_normalised_kullback_leibler_divergence -> average_normalised_information_loss
​
July 2025

​
The Semilattice API: user insights as infrastructure

API v1.1.0 SDK v0.5.2V1 release of the Semilattice API. Predict user behaviour like you make database queries. Read the blog post and get started.
  • Create population models with custom seed data
  • Test model accuracy with built-in cross-validation
  • Test model accuracy on external ground truth data
  • Predict new questions