Candidate relevance scoring

Step 01

Define and Align

Upload sample data, define your output schema, and provide feedback on the hardest cases.

Output schema

RelevanceChoose one: Fit against the documented role requirements.
meets_requirements
partially_meets
missing_required_evidence
Matched requirementsList of values: Requirements supported by job-related evidence.
Missing requirementsList of values: Required capabilities not demonstrated in the supplied profile.

app.sutro.sh/functions/candidate-relevance-scoring

Collecting feedback · 1/3

Compare documented job-related experience with explicit role requirements.

Example 1 of 3

Required skill missing

Model input

Requirements: Production Rust experience.
Profile: Production Go experience; interested in learning Rust.

Model output

Relevance

Matched requirementsMultiple values

Missing requirementsMultiple values

Why? Optional guidance

Step 02

Model Sweep

Compare quality and cost on your examples, then choose a model or use Sutro’s default.

Compare models on expert agreement and cost. The interactive chart uses illustrative measurements.

Illustrative sweep · select Value or Best to use that model in your function.

Step 03

Deployment

Call Sutro Functions like any other software. Swap the model as soon as something more performant is released.

Selected modelWaiting for sweep results.

Real-time

import sutro as so

input_data = {
    "requirements": "Production Rust experience.",
    "profile": "Production Go experience; interested in learning Rust."
}

result = so.run_function(
    "candidate-relevance-scoring",
    input_data,
)

curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/candidate-relevance-scoring/run" \
  -H "Authorization: Key $SUTRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "requirements": "Production Rust experience.",
    "profile": "Production Go experience; interested in learning Rust."
  }
}'

Batch

import sutro as so

job_id = so.batch_run_function(
    name="candidate-relevance-scoring",
    data="candidate_relevance_scoring.csv",
)
results = so.await_job_completion(job_id)

curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/batch-inference" \
  -H "Authorization: Key $SUTRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "candidate-relevance-scoring",
  "inputs": [
    {
      "requirements": "Production Rust experience.",
      "profile": "Production Go experience; interested in learning Rust."
    }
  ]
}'