Presis Brings Self-Hosted Classification to Boost.ai’s Agent Platform

boost.ai announced the launch of Presis on November 10, 2026, a self-hosted language model for classification decisions around AI agent conversations. The company said internal testing found it at least 2.5 times faster than the models it replaces, with the difference most noticeable during peak-demand hours and in voice AI.

Presis decides which part of an AI agent should respond, whether a question is in scope, whether an answer is safe to show an end user, and how completed conversations are reviewed. In voice deployments, those routing and safeguard checks must finish before a response can begin, putting classification directly on the response-time path. The company says Presis already powers those platform decisions, with its broader rollout across the platform continuing over the coming weeks.

Performance and Infrastructure

The company’s internal testing reports an average 33% reduction in token costs and accuracy improvements across all five classification features, ranging from 0.5 to 7.9 percentage points depending on the feature.

CTO Rasmus Hauch said controlling “every part of the stack it runs on” allows the classification-specific model to keep improving. Its Version 14 documentation places the fine-tuned models on internally managed, dedicated server clusters, with low response times and high capacity as the stated goals.

Presis runs on AWS in the same region that already serves each customer instance, so the documented processing location does not change. AWS is already an approved sub-processor, meaning the model introduces no new sub-processors and requires no data processing agreement change or additional agreement.

The company says this end-to-end control removes routing, scope and safeguard decisions from exposure to third-party outages, timeouts and capacity swings.

Version 14 Splits Generation and Classification

Version 14 divides the platform’s language-model work between generation and classification. GPT-5.1 is mandatory for built-in text-generation features and the default for new agentic actions, while Presis handles the classifier component of Agent orchestrator, Few shot, AI review, the out-of-scope detector and system guardrails. Customers must configure GPT-5.1 before upgrading; without it, the system migration will fail.

That architecture reduces model-provider choice for built-in classification. External Bring Your Own Model support and provider configuration options are being removed for those tasks, while BYO remains available for generative Agentic Actions, LLM Actions and Guardrails.

Migration and Model Transition

The company ties the broader transition to Microsoft’s scheduled April 2027 retirement of GPT-4o, GPT-4.1, GPT-4.1-mini and GPT-4.1-nano on Azure. Early migration and testing capabilities began with Version 12.8.3 in August 2026, and the mandatory Version 14 changes were scheduled to start reaching production in mid-October 2026.

Presis is the renamed Boost Native Model; boost.ai says the Norwegian name conveys accuracy and timeliness and that the change did not alter how the model works.

The company is also evaluating a similar dedicated-model approach for generative features. For customers, the immediate trade-off is tighter platform control and reported efficiency gains alongside less provider freedom for built-in classification; any broader move into generation remains an evaluation rather than a committed launch.