Welcome to Sparkient
Decision intelligence infrastructure for developers whose compiled path targets under 100ms.
What is Sparkient?
Sparkient is decision intelligence infrastructure for developers building applications and agents. It turns repeated, measurable decisions into task-specific models whose compiled path targets under 100 milliseconds and must be measured on each workload. Four controlled synthetic runs reported 33–42ms average time per item in batched inference. Cloud deployments can optionally escalate configured low-confidence cases to an LLM.
The initial users are developers already using coding agents, from technical solo founders to software teams of any size. The applications those developers ship create the path into larger production teams and accounts. Moderation, routing, scoring, support, fraud, marketplace review, gaming safety, and agent guardrails are application domains—not separate primary customer segments.
The Decision Pipeline
Every decision flows through a three-stage pipeline:
- Hard Rules — Deterministic business rules, usually evaluated in sub-millisecond time. If a rule matches, it returns the configured result without running the classifier.
- ML Classifier — A compiled model trained from LLM-generated examples. It handles nuance and edge cases that rules miss, with an under-100ms compiled-stage target that must be measured on the intended workload.
- LLM Escalation — Optional metered fallback for configured low-confidence cloud decisions. New decision types do not enable it automatically.
Every response is structured and consistent. The timing below only illustrates the response shape; live responses contain the measured request value:
{
"decision": "approve",
"confidence": 0.94,
"reason_codes": ["safe_content", "verified_user"],
"latency_ms": 8.3,
"stage": "classifier",
"escalate": false
}Why Not Just Use an LLM?
| Approach | Runtime profile | Billing profile | Best fit |
|---|---|---|---|
| Rules engine | Usually <1ms | Application compute | Deterministic conditions |
| Sparkient compiled path | <100ms target; 33–42ms batch average per item in four controlled synthetic runs | Plan credits | Repeated decisions with stable outcomes |
| Live LLM | Model, prompt, provider, and load dependent | Current provider token or request pricing | Open-ended generation or changing tasks |
Sparkient uses LLM-generated or user-provided labelled examples to train a task-specific model, then meters decisions and supporting operations through plan credits without a live LLM call in the normal runtime path.
Authentication at a Glance
| Method | Use Case |
|---|---|
API Key (Bearer YOUR_API_KEY) | Programmatic access — /decide, decision types, examples, training |
Firebase JWT (Bearer <id_token>) | Dashboard — account, billing, API key management |
See Authentication for full details.
Training Example Field Names
When adding training examples, use the canonical field names: input_payload, expected_decision, and reason_codes (a list). The shorter aliases input, decision, and reason_code (singular string) are also accepted for convenience.
Programmatic Access
Building an integration or using an AI agent? These machine-readable resources are available:
- API Base URL:
https://api.sparkient.ai - OpenAPI Spec: docs.sparkient.ai/openapi.json — full API schema
- Plain text docs: docs.sparkient.ai/llms-full.txt — complete documentation in markdown
- LLM summary: docs.sparkient.ai/llms.txt — concise overview for AI agents