Introduction to ‘ZEN’ Document Review

Zero Error Numerics – ZEN. Expanding the art of quality control in large-scale document review. ZEN improves legal search and review using sampling, metric analysis, tested procedures, artificial intelligence, human-computer interface and flow-state performance.

ZEN document review is designed to attain the highest possible level of efficiency and quality in computer assisted review. The goal is zero error. The methods to attain that goal include active machine learning, random sampling, objective measurements, and comparative analysis using simple, repeatable systems. The ZEN methods were developed by Ralph Losey’s e-Discovery Team. They rely on focused attention and full clear communication between review team members.

Using Zero Error Numerics skilled reviewers can attain very high levels of efficiency and quality. ZEN methods include:

  1. UpSide_down_champagne_glasspredictive coding analytics, a type of artificial intelligence, actively managed by skilled human analysts in a hybrid approach;
  2. data visualizations with metrics to monitor progress;
  3. flow-state of human reviewer concentration and interaction with AI processes;
  4. quiet, uninterrupted, single-minded focus (dual tasking during review is prohibited);
  5. disciplined adherence to a scientifically proven set of search and review methods including linear, keyword, similarity, concept, and predictive coding;
  6. repeated tests for errors, especially retrieval omissions;
  7. objective measurements of recall, precision and accuracy ranges;
  8. judgmental and random sampling and analysis such as ei-Recall;
  9. active project management and review-lawyer supervision;
  10. small team approach with AI leverage, instead of large numbers of reviewers;
  11. quality_trianglerecognition that mere relevant is irrelevant;
  12. recognition of the importance of simplicity under the 7±2 rule;
  13. multiple fail-safe systems for error detection of all kinds, including reviewer inconsistencies;
  14. use of only the highest quality, tested e-discovery software and vendor teams under close supervision and teamwork;
  15. use of only experienced, knowledgeable Subject Matter Experts for relevancy guidance, either directly or by close consultation;
  16. extreme care taken to protect client confidentiality; and,
  17. high ethics – our goal is to find and disclose the truth in compliance with local laws, not win a particular case.


Master practitioners of ZEN attain a flow-state of creative software interaction that harnesses the power of active machine learning. ZEN projects are front-loaded with beginner’s mind and clear discussions. Search and production are phased and unhurried. A calm, deliberate approach is attained by strict time management. The ZEN approach relies on small teams of skilled reviewers and adherence to proven procedures, standards, measures and tests. The net result of this practice is a satori break-through in document review quality, consistency, recall and precision.

ZenA_trandparentSignificant cost savings can also be attained by following Zero Error Numerics methods, especially when compared to more traditional review methods.



zen_koanThe ZEN approach encourages an open, empty mind — a beginner’s mind. That is an ideal way to take on information retrieval challenges arising from new technologies and new writings. Old expert systems provide a solid foundation to begin a project, but in most matters the standard procedures are customized to fit new challenges. We thrive on large, complex projects that require creative solutions. In this field we see new challenges every day and learn how to devise simple answers. Some new challenges are difficult and expensive to solve. Some are not. Most ZEN methods can scale in cost according to project proportionality.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s