deeprank

Selection Scenarios

Real-world examples demonstrating how AI selection works in practice. Each scenario shows the query structure, decision logic, common failure modes, and how a properly structured Deeprank Profile resolves the issue.

Each scenario follows a consistent structure:

1.Intent + Constraints - What the user needs
2.Decision Logic - How AI evaluates fit
3.Common Failure - What goes wrong without structure
4.Deeprank Resolution - How proper profiles fix it

Intent

Find a lawyer to help sponsor a foreign employee

Constraints

  • 1.Must handle H-1B visas
  • 2.Licensed to practice immigration law in the US
  • 3.Works with technology companies
  • 4.Can handle the full petition process

Decision Logic

AI must match: problem_class = "legal-immigration-employment", capability.labels includes "h1b-visa", fit_conditions.customer_type includes "technology-company" or "employer-sponsor".

Common AI Failure

AI selects a general immigration attorney who primarily handles family immigration. The attorney is licensed and technically can file H-1B petitions but lacks specialized expertise in employment-based cases. Result: suboptimal representation, potential RFE, client dissatisfaction.

Deeprank Resolution

A properly structured Deeprank Profile declares problem_class = "legal-immigration-employment" (not just "legal-immigration"), includes "h1b-visa" in capability.labels, and explicitly excludes "family-immigration" in non_fit.exclusions. This allows AI to select firms with actual specialization.