Skip to main content
POST
/
v1
/
intelligence
/
predict
Predict Content Performance
curl --request POST \
  --url https://app.uselamina.ai/v1/intelligence/predict \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "concept": "A lifestyle photo of our new sneakers in an urban setting with warm golden-hour lighting",
  "platform": "instagram",
  "modality": "image",
  "brandProfileId": null,
  "campaignId": null
}
'
{
  "data": {
    "predictedScore": 78.5,
    "confidence": "medium",
    "strengths": [
      "Strong alignment with brand visual identity",
      "Lifestyle format historically performs well"
    ],
    "risks": [
      "Golden-hour lighting may not differentiate from competitors",
      "Urban setting is overused in category"
    ],
    "suggestions": [
      "Add a human subject for +15% predicted engagement",
      "Consider a close-up crop variant"
    ]
  }
}
Predict how a content concept will perform on a given platform before you create or publish it. Send a text concept describing the content idea along with the target platform and modality. Returns a performance prediction grounded in your workspace’s historical data and brand context. Use this in pre-creation decision flows, A/B content selection, or automated quality gates to prioritize high-performing concepts.

Authorizations

​
x-api-key
string
header
required

Workspace API key. Prefix: lma_. Example: lma_abc123...

Body

application/json
​
concept
string
required

Natural-language content concept or brief to evaluate.

​
platform
string
required

Target platform (e.g. instagram, tiktok, facebook, linkedin).

​
modality
enum<string>
required

Content modality of the concept.

Available options:
image,
video,
text,
audio,
mixed
​
brandProfileId
string<uuid> | null

Optional brand profile to evaluate against.

​
campaignId
string<uuid> | null

Optional campaign context for more targeted prediction.

Response

Performance prediction with scores and reasoning

​
data
object

Prediction results. Structure varies based on the workspace's intelligence model.