The heart of NLS is our unique, proprietary hybrid reasoning engine.

The heart of NLS is our unique, proprietary hybrid reasoning engine.

The Engine combines Boolean rules of any complexity with mathematical reasoning (formulas, Excel spreadsheets), multi-factor reasoning (weighted scorings), and a wide range of external tools, as illustrated.

The Engine automatically integrates all these forms of reasoning—calling upon them as needed to drive an application and solve a problem. Authors can build very large and complex applications in individual, small, comprehensible segments that are easier to create and much easier to maintain.

The Engine is designed and configured at Amazon Web Services for security, fault tolerance, high availability, and easy scaling to assure good performance at high levels of use.

Reasoning Engine

A full suite of reasoning tools at your disposal

1. Situation Sets

Modular, reusable combinations of variables and values to be used in rules and other reasoning, e.g., City = Boston AND Season = Winter OR Spring.

2. If/Then Mappings

Linear representations of if/then rules combining variables, values and situation sets, e.g., IF Insured Property State = Kansas, THEN Agent = ABC Co. AND Tax Rate = 0.15%.

3. Decision Trees

Tree representations of sequences of if/then rules, particularly useful when subject matter experts document their thinking in flowcharts and when rules have multiple, symmetrical branches.

4. Decision Tables

Multiple if/then rules following the same pattern; can also be created and updated in Microsoft Excel and imported into Studio.

5. Multi-Value Variables

NLS has specialized tools for reasoning on variables that may have multiple values, e.g., Required Compliance Steps, each of which is determined by different logic paths. NLS will automatically traverse all relevant logic paths to ensure that all possible values are determined.

6. Instances

Tabular data structures, which may be nested, of the sort commonly defined in a relational database, e.g., an insurance policy (number, date, issuer, insured) may cover multiple properties (location, value, date acquired). NLS has specialized tools for gathering, reasoning on, persisting, and reporting on such data.

7. Weighted Scorings

Combines multiple factors to reach a single conclusion, designed specifically to model common legal constructs such as the IRS 20-factor test, summary judgment balancing tests, and experts’ judgment about transaction risk levels. Factors to be included, their weights and scorings, and the combining algorithm are all within the authors’ control and can be set dynamically by other reasoning, just as results of a weighted scoring can be an input to rules and other reasoning.

8. Value Optimization

NLS can automatically traverse multiple reasoning paths to determine the highest or lowest possible value for a variable, e.g., the highest possible valuation of a property when multiple factors affect valuation. Optimization is one of several unique NLS reasoning accelerators that radically simplify the construction and maintenance of complex logic.