Skip to main content
YAML Engine

Configuration replaced code.

200 lines of Python state management becomes 15 lines of YAML. Zero custom code. Full production capability — validation, conflict detection, compliance, all included.

Before and after

The same fitness intake agent — one with raw Python, one with TrueNorth.

Without TrueNorth200+ lines
state = {}
conversation_history = []
current_field_index = 0
retry_count = 0
# ... 60 more lines of state ...
 
def validate_age(value):
if not isinstance(value, int):
raise ValidationError(...)
if value < 0 or value > 120:
raise ValidationError(...)
# ... 40 more validators ...
 
def detect_conflict(prev, curr):
# ... 50 more lines ...
 
def score_confidence(field, val):
# ... 40 more lines ...
With TrueNorth15 lines
id: fitness_plan
persona: "You are Alex, a fitness coach."
 
fields:
- name: age
type: integer
range: [16, 90]
required: true
- name: goal
type: enum
options: [weight_loss, muscle_gain]
 
# Validation ✓ Conflict detection ✓
# Confidence scoring ✓ Firewall ✓ Compliance ✓
ValidationConflict detectionConfidence scoringHallucination firewallDPDP 2023

How it works

Three steps from schema to structured output.

Step 01
Write your schema in YAML
Define fields, types, ranges, personas, and output templates. One file is all you need.
Step 02
TrueNorth builds the pipeline
Validation, conflict detection, confidence scoring, hallucination firewall — all compiled from your YAML.
Step 03
Get structured JSON out
The engine runs the conversation and returns fully validated, typed JSON — ready for your database or API.

Supported field types

Every type handles natural language extraction — not just exact string matching.

TypeDescriptionExtracted from
textFree-form string input"I'm Priya Sharma"
integerWhole number with optional min/max range"I'm 28" → 28
floatDecimal number"about 5 and a half" → 5.5
dateDate in any format, normalized to ISO 8601"born in 1995" → 1995-01-01
enumConstrained to one of predefined optionsweight_loss | muscle_gain | endurance
booleanYes / no values, normalised from natural language"yeah sure" → true
emailValidated email addresspriya@example.com
phoneValidated phone number, India-first+91 98765 43210
listArray of values extracted from a single response["Python", "Go", "Rust"]

Try the YAML Engine now

Write a schema in the playground, run it live, and see structured JSON come out of a real conversation.