Think fast.

Compiled Decision Intelligence is a new approach that uses a large language model (LLM) as a teacher to generate training data offline, then compiles that intelligence into a small, fast model that runs in production. The result is LLM-quality decisions in under 100 milliseconds, at a fraction of the cost of direct LLM calls. The LLM teaches. The compiled model decides.

Traditional LLM APIs charge per request — at scale, this means hundreds of thousands of dollars per year for high-volume use cases. Sparkient shifts this from a variable cost to a fixed cost. The LLM is only used during training to generate synthetic data and label examples. Once the model is compiled, it runs in production with dramatically lower inference cost. You pay to compile the intelligence once, then run it at a predictable monthly price.

Sparkient decisions typically complete in under 100 milliseconds (p95), with many tabular-dominant decisions completing in under 10ms. This is 3–10× faster than the fastest LLM inference providers like Groq (150–300ms) and 30–100× faster than standard LLM APIs (1–3 seconds). Fast enough to sit in any latency-sensitive hot path.

No. You can bring your own training data, or start with none — Sparkient generates training data using an LLM teacher. You define your decision type in plain English — what the options are, what rules should always apply — and Sparkient handles synthetic data generation, labelling, model training, and deployment. No machine learning team required.

Yes. Sparkient works as a standard REST API. You can create decision types in the dashboard, call the /decide endpoint from any language, and manage everything without an AI agent. Agents are one integration path — not the only one.

Sparkient runs on Google Cloud Platform (EU region). All data is encrypted in transit and at rest. Input data is used only for your decision types and is never shared across organisations. You can configure data retention policies per decision type, and delete all your data at any time via the API.

Each training run uses 2,000 credits from your balance. This covers model compilation — the process of training and exporting your decision model. Example generation and labelling are billed separately as individual API calls. Trial users get 5,000 credits — enough to train and test one model.

The free trial includes 5,000 credits, 1 decision type, and 250 total decisions. This gives you enough to train a model and verify it works. Subscribe to any paid plan for unlimited decisions.