Sync preview of a personalized email for a single lead

Blocking endpoint. Runs find_commonalities + generate_email inline against the provided lead + sender profile. Returns subject, body, commonality, and the prompt source used. Does not create a campaign, does not queue a job.

POST /api/v1/personalize/preview

Sync preview of a personalized email for a single lead

cURL

curl --request POST \
  --url https://api.example.com/api/v1/personalize/preview \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "lead_data": {},
  "sender_profile_id": "<string>",
  "sender_data": {},
  "custom_prompt": "<string>",
  "research_context": "<string>",
  "dataset_id": "<string>",
  "row_index": 1,
  "force_refresh_research": false
}
'

200

{
  "subject": "<string>",
  "email_body": "<string>",
  "commonality": {
    "text": "<string>",
    "confidence_score": 123,
    "rarity_score": 123,
    "relevance_score": 123,
    "supporting_evidence": [
      "<string>"
    ]
  },
  "prompt_source": "<string>",
  "model_used": "<string>",
  "latency_ms": 123,
  "research_sources": [
    {
      "name": "<string>",
      "status": "<string>",
      "summary": "",
      "meta": {},
      "from_cache": false
    }
  ],
  "research_chars": 0,
  "research_latency_ms": 0,
  "research_from_cache": false,
  "research_cached_at": "<string>",
  "research_meta": {}
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Input for the sync personalization preview.

lead_data · Lead Data · object · required

The lead fields to personalize against (company, role, linkedin_url, etc.)

sender_profile_id · string | null

ID of a saved sender profile. If omitted, sender_data must be provided.

sender_data · Sender Data · object

Inline sender profile data. Ignored if sender_profile_id is provided.

custom_prompt · string | null

Optional prompt override. Must be 100-5000 characters if provided.

research_context · string | null

Optional pre-fetched research context (overrides enrichment). Max 20000 chars.

Maximum string length: 20000

dataset_id · string | null

Optional dataset id for research cache persistence. Paired with row_index.

row_index · integer | null

Row index within the dataset. Required when dataset_id is set.

Required range: x >= 0

force_refresh_research · boolean · default: false

Bypass the research cache and fetch fresh (e.g. user hit 'Refresh research').

Response

200

application/json

Successful Response

subject · string · required

email_body · string · required

commonality · PersonalizationPreviewCommonality · object · required

Show child attributes

prompt_source · string · required

Which prompt was used: 'default', 'sender_profile_custom', or 'custom_override'.

model_used · string · required

latency_ms · integer · required

research_sources · PersonalizationPreviewResearchSource · object[]

Which enrichment sources ran and whether they succeeded.

Show child attributes

research_chars · integer · default: 0

research_latency_ms · integer · default: 0

research_from_cache · boolean · default: false

research_cached_at · string | null

research_meta · Research Meta · object

Aggregate research metadata. Currently exposes zero_research_reason (one of the ZERO_RESEARCH_REASON_* enum values) when the joined research_chars was below the useful threshold. Used by ops sweep scripts to derive a per-cohort distribution of why some leads return empty research.