Buying-signal detection

Step 01

Define and Align

Review representative examples and annotate the fields that need to change. Explain the edge cases to teach your team’s policy.

Output schema

Signal typeChoose one: The current signal explicitly supported by the source.
hiring
tool_evaluation
funding
none
Signal strengthChoose one: Evidence of active buying intent, distinct from general company activity.
strong
weak
none
Observed dateDate · optional: Date of the source event in YYYY-MM-DD; unknown when unstated.
EvidenceText: The source statement and its relevance to the offered product.

app.sutro.sh/functions/buying-signal-detection

Collecting feedback · 1/3

Identify current buying signals using the supplied offering, strength criteria, and recency window.

Example 1 of 3

Keyword mention is not purchase intent

Model input

Signal policy: Offering: automated API-testing software. Strong intent requires explicit evaluation or a purchase-related request for this category. Generic hiring is weak evidence. Only events within 30 days of 2026-11-09 count as current signals.
Account: Cedar Analytics
Source: 2026-11-05 job posting: “Hiring a platform engineer. Familiarity with API testing is helpful.” No tool evaluation or purchase request is mentioned.

Model output

Signal type

Signal strength

Observed date

Evidence

Why? Optional guidance

Step 02

Model Sweep

Compare models on the same expert annotations, then choose a quality–cost tradeoff.

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 = {
    "signal_policy": "Offering: automated API-testing software. Strong intent requires explicit evaluation or a purchase-related request for this category. Generic hiring is weak evidence. Only events within 30 days of 2026-11-09 count as current signals.",
    "account": "Cedar Analytics",
    "source": "2026-11-05 job posting: “Hiring a platform engineer. Familiarity with API testing is helpful.” No tool evaluation or purchase request is mentioned."
}

result = so.run_function(
    "buying-signal-detection",
    input_data,
)

curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/buying-signal-detection/run" \
  -H "Authorization: Key $SUTRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "signal_policy": "Offering: automated API-testing software. Strong intent requires explicit evaluation or a purchase-related request for this category. Generic hiring is weak evidence. Only events within 30 days of 2026-11-09 count as current signals.",
    "account": "Cedar Analytics",
    "source": "2026-11-05 job posting: “Hiring a platform engineer. Familiarity with API testing is helpful.” No tool evaluation or purchase request is mentioned."
  }
}'

Batch

import sutro as so

job_id = so.batch_run_function(
    name="buying-signal-detection",
    data="buying_signal_detection.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": "buying-signal-detection",
  "inputs": [
    {
      "signal_policy": "Offering: automated API-testing software. Strong intent requires explicit evaluation or a purchase-related request for this category. Generic hiring is weak evidence. Only events within 30 days of 2026-11-09 count as current signals.",
      "account": "Cedar Analytics",
      "source": "2026-11-05 job posting: “Hiring a platform engineer. Familiarity with API testing is helpful.” No tool evaluation or purchase request is mentioned."
    }
  ]
}'