API Reference

API Reference

Complete reference for all Bolor Intelligence API endpoints. All requests require authentication via Bearer token.

Base URL: https://api.bolor.ai/v1
Format: JSON
Auth: Bearer token

OrchestrAI

/v1/orchestrai
POST/v1/orchestrai/route

Route a query to the optimal model based on complexity, cost, and latency constraints

GET/v1/orchestrai/models

List all available models and their capabilities

GET/v1/orchestrai/route/{id}

Get routing decision details and performance metrics

POST/v1/orchestrai/evaluate

Evaluate model performance on a given task without routing

AgentGuard

/v1/agentguard
POST/v1/agentguard/verify

Verify an agent action against safety rules before execution

POST/v1/agentguard/rules

Create a new safety rule for agent verification

GET/v1/agentguard/rules

List all configured safety rules

GET/v1/agentguard/audit

Retrieve the audit trail for agent decisions

MindVault

/v1/mindvault
POST/v1/mindvault/store

Store a fact or relationship in the knowledge graph

POST/v1/mindvault/query

Query the knowledge graph using natural language or structured queries

POST/v1/mindvault/recall

Retrieve contextually relevant memories for a given input

DELETE/v1/mindvault/facts/{id}

Remove a specific fact from the knowledge graph

ComplianceGraph

/v1/compliance
POST/v1/compliance/check

Run a compliance check against configured regulatory rules

GET/v1/compliance/reports

List compliance audit reports with timestamps and results

POST/v1/compliance/policies

Create or update a compliance policy

GET/v1/compliance/policies

List all compliance policies and their status

DataReady

/v1/dataready
POST/v1/dataready/analyze

Analyze a dataset for AI-readiness, quality issues, and bias

GET/v1/dataready/reports/{id}

Get a detailed data quality report with recommendations

POST/v1/dataready/schema/validate

Validate a data schema against best practices

EvoAgent

/v1/evoagent
POST/v1/evoagent/populations

Create a new agent population for evolutionary optimization

POST/v1/evoagent/evolve

Run an evolution cycle on an agent population

GET/v1/evoagent/populations/{id}

Get population status, fitness scores, and generation data

GET/v1/evoagent/populations/{id}/best

Retrieve the best-performing agent from a population

VerticalAI

/v1/vertical
POST/v1/vertical/deploy

Deploy an industry-specific AI pipeline from a starter kit

GET/v1/vertical/templates

List available industry templates (healthcare, finance, legal, manufacturing)

GET/v1/vertical/deployments/{id}

Get deployment status and configuration

Example: OrchestrAI Routing

Route a query through OrchestrAI with cost and latency constraints. The system selects the optimal model and returns the response with full routing metadata.

Request

POST
/v1/orchestrai/route
curl -X POST https://api.bolor.ai/v1/orchestrai/route \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "Analyze this contract for compliance risks and summarize the key obligations for both parties.",
    "constraints": {
      "max_latency_ms": 5000,
      "max_cost_usd": 0.05,
      "min_accuracy": 0.95
    },
    "context": {
      "domain": "legal",
      "task_type": "analysis"
    }
  }'

Response

200 OK
application/json
{
  "id": "route_8f3k2j1h",
  "model": "claude-3.5-sonnet",
  "provider": "anthropic",
  "reasoning": {
    "selected_because": "Legal analysis requires high accuracy and nuanced reasoning. Claude 3.5 Sonnet scores highest for legal document analysis in our benchmarks.",
    "alternatives_considered": [
      {
        "model": "gpt-4-turbo",
        "reason_rejected": "Slightly lower accuracy on legal domain tasks"
      }
    ]
  },
  "constraints_met": {
    "latency_ms": 2340,
    "estimated_cost_usd": 0.032,
    "accuracy_score": 0.97
  },
  "response": {
    "content": "Based on my analysis of the contract...",
    "tokens_used": 1847,
    "finish_reason": "stop"
  },
  "metadata": {
    "routing_time_ms": 12,
    "total_time_ms": 2352,
    "nsaf_confidence": 0.94
  }
}

Rate Limits & Response Codes

Rate Limits by Plan

Free100 req/min
Pro1,000 req/min
Enterprise10,000 req/min

HTTP Status Codes

200Success
401Unauthorized
429Rate limited
500Internal error