Registered Nurse with 6 years on a 32-bed telemetry unit, holding a compact TN license and BLS certification
Review low scoresResume parsing that scores every field it returns.
Blue-IQ Capture reads resumes, nursing licenses and certifications, and returns structured JSON with a confidence score on each field. Your team stops re-typing records and only checks the values that are actually in doubt.
- Formats
- PDF, DOCX, RTF, PNG, JPG, TIFF
- File size
- Up to 10 MB
- Batch
- 200 files per request
Three things most resume parsers skip
A score on every field, a documented API, and a searchable history of every parse.
REST API and signed webhooks
Parsed record library
How a resume becomes a structured record
Three calls, no templates to train and no fields to map by hand. A clean export and a crooked phone photo go through the same flow.
1 Send the file
A PDF, a Word file or a phone photo of a page, to one endpoint. Up to 200 in a batch.
2 Sonar reads and scores it
Every field gets a score from 0 to 1. Nothing on the page means null, never a guess.
3 The record lands where you work
Poll or take a signed webhook, then write validated JSON into your ATS, CRM or warehouse.
A wrong value costs more than an empty one
Generic parsers fill gaps with something plausible, and nobody notices until a credential check fails. Here is the same license as a typical parser returns it, and as Capture does.
- license_type
- RN
- state
- TN
- license_number
- RN-2201847invented
- expires
- 2026-03-31invented
A typical parser
Two values invented to fill the gaps. Both look real, and nobody finds out until a credential check fails.
- license_type
- RN0.98
- state
- TN0.97
- license_number
- nullreview
- expires
- nullreview
Blue-IQ Capture
The two fields that are not on the page come back null, flagged, so they are chased rather than trusted.
A resume parser API you can wire in in an afternoon
Submit a file, then poll for the result or take a webhook. Nothing parses on the request path, so a call never blocks and never trips a gateway timeout.
- Signed webhooks
- HMAC-SHA256 over the timestamp and the raw body, so a captured delivery cannot be replayed.
- One error shape
- A stable error code on every failure, and a hint that is safe to show your users.
- Large files and batches
- Presigned uploads for big scans, and up to 200 files in one request.
curl -X POST "https://api.parsinglab.blue-iq.ai/api/v1/resume/parse" \
-H "X-API-Key: rp_live_your_key" \
-F "file=@resume.pdf"
# { "job_id": "01J3K...", "status": "processing",
# "poll_url": "/api/v1/resume/job/01J3K..." }Poll response, 200 OK
{
"status": "completed",
"data": {
"personal_info": { "full_name": "Jane Smith", "credentials": ["RN", "BSN"] },
"licenses": [{ "license_type": "RN", "state": "TN", "is_compact": true }]
},
"confidence": { "overall": 0.9, "catalog_mapping": 0.8 },
"partial": false,
"warnings": []
}How we handle the records you send
Clinical histories, signed agreements, salary lines. None of it is test data, so it is encrypted, isolated per workspace, and never written to our logs.
TLS 1.3
api.parsinglab.blue-iq.ai
X-API-Key: rp_live_••••••••
Encryption in transit
TLS on every request, with a per-workspace key you can rotate whenever you like.
acme
globex
no shared access
Workspace isolation
Documents and keys never leave their workspace. Role-based access and SSO on top.
zero_retention
parsed in memory
returned to caller
discarded
Zero-retention option
Parsed in memory, returned, discarded. Nothing stored is nothing to leak.
duration22.7s
file_typepdf
tokens38,905
content
Content-free audit trail
We log that a parse happened, how long it took and what it cost. Never a word of what it said.
Send us your worst document.
The messy scan. The seven-page contract. The resume with three job titles crammed into one line. We will run it live and show you exactly what comes back.
full_name0.97
Jane A. Smith
start_date0.83
01/2022
bls_expires0.00
null
1 field flagged, nothing invented