Brand & messaging review

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

ApprovedYes / No: Whether the copy follows the supplied brand and claim-substantiation rules.
true
false
IssuesChoose any: Specific messaging issues found; empty when the copy is supported.
unsupported_claim
off_brand
missing_context
ExplanationText: Why the copy is approved or which evidence and context need to change.

app.sutro.sh/functions/brand-messaging-review

Collecting feedback · 1/3

Review the copy using the supplied brand guidelines and claim evidence.

Example 1 of 3

Unsupported accuracy guarantee

Model input

Brand guidelines: Voice: calm, concrete, and precise. Claims must be supported by the supplied product evidence. Preserve limitations and the scope of any pilot result; do not turn one example into a universal guarantee.
Product evidence: The product applies expert-defined labels and supports batch API processing. No universal accuracy rate or guarantee is supplied.
Copy: 100% accurate decisions, every time. You will never need human review again.

Model output

Approved

IssuesMultiple values

Explanation

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 = {
    "brand_guidelines": "Voice: calm, concrete, and precise. Claims must be supported by the supplied product evidence. Preserve limitations and the scope of any pilot result; do not turn one example into a universal guarantee.",
    "product_evidence": "The product applies expert-defined labels and supports batch API processing. No universal accuracy rate or guarantee is supplied.",
    "copy": "100% accurate decisions, every time. You will never need human review again."
}

result = so.run_function(
    "brand-messaging-review",
    input_data,
)

curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/brand-messaging-review/run" \
  -H "Authorization: Key $SUTRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "brand_guidelines": "Voice: calm, concrete, and precise. Claims must be supported by the supplied product evidence. Preserve limitations and the scope of any pilot result; do not turn one example into a universal guarantee.",
    "product_evidence": "The product applies expert-defined labels and supports batch API processing. No universal accuracy rate or guarantee is supplied.",
    "copy": "100% accurate decisions, every time. You will never need human review again."
  }
}'

Batch

import sutro as so

job_id = so.batch_run_function(
    name="brand-messaging-review",
    data="brand_messaging_review.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": "brand-messaging-review",
  "inputs": [
    {
      "brand_guidelines": "Voice: calm, concrete, and precise. Claims must be supported by the supplied product evidence. Preserve limitations and the scope of any pilot result; do not turn one example into a universal guarantee.",
      "product_evidence": "The product applies expert-defined labels and supports batch API processing. No universal accuracy rate or guarantee is supplied.",
      "copy": "100% accurate decisions, every time. You will never need human review again."
    }
  ]
}'