Skip to main content

Reasoning Engine Overview

What Is the Reasoning Engine?

The Reasoning Engine is an AI-powered analysis platform that takes structured data -- time-series metrics, categorical measurements, numeric datasets -- and produces validated, actionable insights through a coordinated team of specialized AI agents. Each agent handles one analytical discipline (statistics, pattern recognition, correlation, narrative generation, fact-checking), and they collaborate in a defined pipeline to deliver results no single model could produce alone.

The engine is format-agnostic: it accepts data from any source format through intake adapters and delivers results in any target format through output adapters. The core analytical logic remains unchanged regardless of where data originates or where results are consumed.


Who Is This For?

Product teams use the Reasoning Engine to power data-driven features without building analytical logic from scratch. Provide structured data and a question, and the engine returns a validated narrative with confidence scores, key findings, and actionable recommendations.

Integration teams use it as a composable analytical building block. Connect your data source via an intake adapter and your output target via an output adapter, and the same pipeline works across applications without modification to the core engine.

Data analysts use the engine's structured output -- temporal statistics, correlation coefficients, detected patterns -- as a foundation for further analysis or reporting.


What Makes It Different?

ApproachLimitationReasoning Engine
Single LLM callOne model does everything; hard to tune individual aspects10 registered agents, each independently tunable
Rule-based analyticsRigid; cannot handle nuance or unexpected patternsDual-mode processing: algorithmic baselines + AI enhancement
Black box analysisNo verification of output accuracyBuilt-in validation agent fact-checks every claim against source data
Hardcoded formatsNew data sources require core changesAdapter pattern: add new formats without touching the engine

Pipeline at a Glance

The engine executes a 7-step sequential pipeline. Each step builds on the accumulated output of prior stages:

StepWhat HappensAgents Involved
0. PreflightValidates input structure, optionally determines which steps are neededStep Orchestrator (optional)
1. Temporal AnalysisComputes statistics and identifies trends across time-series dataTemporal Agent
2. Pattern RecognitionDetects behavioral patterns, recurring cycles, and warning indicatorsPattern Agent
3. Correlation AnalysisComputes and interprets statistical relationships between metricsNormalizer + Analysis Agents
4. Domain KnowledgeRetrieves relevant external knowledge based on detected findingsQuery Generator + Domain Retrieval Agents
5. ExplanationSynthesizes all findings into a structured, user-facing narrativeExplanation Agent
6. ValidationFact-checks every claim in the narrative against the computed dataValidation Agent

Every step supports dual-mode processing: deterministic algorithms execute first (reliable, reproducible), then AI agents layer semantic understanding on top (nuanced, contextual). The pipeline always produces a baseline result even if an agent is temporarily unavailable.


Format-Agnostic Architecture

The engine does not know or care where data comes from or where results go. Adapters handle all format-specific logic at both ends of the pipeline:

Intake adapters transform source-specific data into a canonical schema the engine understands. Output adapters transform the canonical result into whatever format the consumer requires. Multiple applications can share the same analytical pipeline -- only the adapters change.

Supported Adapter Types

Intake:

  • JSON Array Adapter -- nested object arrays
  • API Payload Adapter -- structured API responses
  • CSV Adapter -- tabular data from external systems
  • Auto-detection -- the system can automatically select the correct adapter based on input structure

Output:

  • Dashboard Formatter -- JSON optimized for UI rendering
  • Report Formatter -- structured data for PDF generation
  • API Response Formatter -- REST-friendly JSON
  • Plain Text Formatter -- human-readable summaries

Canonical Input Structure

The engine accepts a standardized input regardless of the original source format:

FieldTypeRequiredDescription
objectivestringYesThe analytical question to answer
seriesarrayNoTime-series data (timestamp + value pairs per metric)
datasetsarrayNoNumeric arrays for correlation analysis
hintsstring[]NoAdditional context to guide the analysis
outputProfilestringNoTarget output format (e.g., dashboard, text, api-v1)

At least one of series or datasets must be provided alongside the objective.

Example Input

{
"objective": "Help me understand my stress patterns this week",
"series": [
{
"id": "stress_level",
"label": "Daily Stress",
"points": [
{ "t": "2025-01-06T00:00:00Z", "v": 3.5 },
{ "t": "2025-01-07T00:00:00Z", "v": 4.0 },
{ "t": "2025-01-08T00:00:00Z", "v": 4.5 },
{ "t": "2025-01-09T00:00:00Z", "v": 3.8 },
{ "t": "2025-01-10T00:00:00Z", "v": 4.2 }
]
},
{
"id": "sleep_quality",
"label": "Sleep Quality",
"points": [
{ "t": "2025-01-06T00:00:00Z", "v": 7 },
{ "t": "2025-01-07T00:00:00Z", "v": 6 },
{ "t": "2025-01-08T00:00:00Z", "v": 5 },
{ "t": "2025-01-09T00:00:00Z", "v": 6 },
{ "t": "2025-01-10T00:00:00Z", "v": 5 }
]
}
],
"hints": ["User reports difficulty sleeping on work nights"],
"outputProfile": "dashboard"
}

Output Structure

The engine produces a structured analytical result. The key fields are listed below. For the complete schema with nested field definitions and a JSON example, see Output Schema.

FieldDescription
taskIdUnique task identifier for tracing
objectiveOriginal analysis objective
temporalComputed statistics and trend assessments per metric
patternDetected behavioral patterns with confidence scores
correlationPairwise metric relationships with coefficients
domainExternal knowledge relevant to detected findings
explanationSynthesized narrative (2-4 paragraphs), recommendations, and sources
validationFact-check results (pass/fail with specific issues)
resultSummary, key insights, recommendations, and overall confidence score
executedStepsWhich pipeline steps ran, were skipped, or failed
timingExecution duration

Confidence Levels

LevelData RequirementOutput Characteristics
LowFewer than 5 data pointsPreliminary language, explicit uncertainty caveats
Medium5 to 14 data pointsModerate certainty, patterns noted with limitations
High14+ data pointsStrong confidence, specific claims backed by robust data

Key Design Principles

Dual-Mode Processing

Every analysis step runs deterministic algorithms first, then layers AI enhancement on top. This guarantees a baseline result even when agents are unavailable, and ensures reproducible statistical foundations beneath the AI-generated interpretations.

Fail-Safe Pipeline

When any agent fails or returns invalid output, the pipeline continues with degraded results rather than terminating. The failed step is logged and downstream agents operate on available data. The validation agent flags the gap so consumers are aware of reduced coverage.

Selective Execution

The Step Orchestrator Agent evaluates the user's question against the available data to determine which steps are needed. A simple statistical query skips pattern detection, correlation, and domain retrieval -- reducing latency and eliminating unnecessary API cost.

Configurable Agent Behavior

Each agent's system prompt and model configuration can be updated without redeployment. Changes take effect immediately through automatic cache invalidation. Different agents can target different model deployments, enabling cost and quality optimization per analytical stage.


Next Steps