Build healthcare agents with open source models
Superlinked gives your agent one API to read submitted records, retrieve current rules, extract evidence and return cited findings for human review.
Your documentation review agent
Read the submitted record, check current criteria and cite the mismatch.
Your review context
Submitted records, current rules and prior review decisions.
from sie_sdk import SIEClientclient = SIEClient( api_key="sk-sie-…", base_url="https://api.superlinked.com",)# Parse a document → clean markdown, tables and layout kept.result = client.extract( "modeldocling", {"document": fileHTMLcms-lower-limb-orthoses.htmlbrowse},)print(result["data"]["markdown"])document_bytes=$(base64 < 'cms-lower-limb-orthoses.html' | tr -d '\n')
curl https://api.superlinked.com/v1/extract/docling \
-H "Authorization: Bearer sk-sie-…" \
-H "Content-Type: application/json" \
-d "{\"items\":[{\"document\":{\"data\":\"$document_bytes\",\"format\":\"html\"}}]}"Build the "Doc to Markdown" capability into my app using the Superlinked Inference Engine (SIE).
Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: docling (SIE primitive: /extract). Keep the model id configurable.
Task
- Input: an uploaded document (PDF / Office / scan).
- Behaviour: return clean markdown for the document, preserving tables and reading order
- Call the selected SIE primitive once per request and map the response into your domain type.
Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.

import numpy as npfrom sie_sdk import SIEClientclient = SIEClient( api_key="sk-sie-…", base_url="https://api.superlinked.com",)query = "queryFor CMS's published L1851 example, what was required, what was submitted, what timing gap caused insufficient documentation, and what payment action followed?"documents = [ "document 1https://www.cms.gov/training-education/medicare-learning-networkr-mln/compliance/medicare-provider-compliance-tips/lower-limb-orthoses Page Last Modified: 02/11/2026 04:18 PM", "document 2## Billing & Coding Criteria", "document 3We require prior authorization, a face-to-face encounter, and written order prior to delivery for HCPCS codes L1832 and L1851. Conduct the face-to-face encounter within the 6 months before prescribing the item.", "document 4## Example of Improper Payments Due to Insufficient Documentation for Lower Limb Orthoses", "document 5A supplier bills the claim for L1851 (Knee orthosis (KO), single upright, thigh and calf, with adjustable flexion and extension joint (unicentric or polycentric), medial-lateral and rotation control, with or without varus/valgus adjustment, prefabricated, off-the-shelf) and submits the following documentation per the review contractor's request:", "document 6- Standard written order with correct HCPCS coding", "document 7- Treating practitioner's medical record that has adequate medical necessity information", "document 8- Proof of delivery with face-to-face encounter 7 months ago", "document 9### What Documentation Was Missing?", "document 10The doctor didn't document the face-to-face encounter within 6 months of proof of delivery.", "document 11The review contractor completes the claim as an insufficient documentation error, and the MAC recoups payment.",]items = [{"text": query}, *({"text": d} for d in documents)]vecs = client.encode("modelQwen/Qwen3-Embedding-4B", items)mat = np.array([v["dense"] for v in vecs])mat = mat / np.linalg.norm(mat, axis=1, keepdims=True)scores = mat[1:] @ mat[0] # cosine similarity to the queryfor i in np.argsort(scores)[::-1]: print(f"{scores[i]:.3f} {documents[i]}")import { SIEClient } from '@superlinked/sie-sdk';
const client = new SIEClient('https://api.superlinked.com', {
apiKey: 'sk-sie-…',
});
const query = "For CMS's published L1851 example, what was required, what was submitted, what timing gap caused insufficient documentation, and what payment action followed?";
const documents = [
"https://www.cms.gov/training-education/medicare-learning-networkr-mln/compliance/medicare-provider-compliance-tips/lower-limb-orthoses Page Last Modified: 02/11/2026 04:18 PM",
"## Billing & Coding Criteria",
"We require prior authorization, a face-to-face encounter, and written order prior to delivery for HCPCS codes L1832 and L1851. Conduct the face-to-face encounter within the 6 months before prescribing the item.",
"## Example of Improper Payments Due to Insufficient Documentation for Lower Limb Orthoses",
"A supplier bills the claim for L1851 (Knee orthosis (KO), single upright, thigh and calf, with adjustable flexion and extension joint (unicentric or polycentric), medial-lateral and rotation control, with or without varus/valgus adjustment, prefabricated, off-the-shelf) and submits the following documentation per the review contractor's request:",
"- Standard written order with correct HCPCS coding",
"- Treating practitioner's medical record that has adequate medical necessity information",
"- Proof of delivery with face-to-face encounter 7 months ago",
"### What Documentation Was Missing?",
"The doctor didn't document the face-to-face encounter within 6 months of proof of delivery.",
"The review contractor completes the claim as an insufficient documentation error, and the MAC recoups payment.",
];
const items = [{ text: query }, ...documents.map((text) => ({ text }))];
const vecs = await client.encode('Qwen/Qwen3-Embedding-4B', items);
const [q, ...d] = vecs.map((v) => v.dense);
const cosine = (a: Float32Array, b: Float32Array) => {
const dot = a.reduce((s, x, i) => s + x * b[i], 0);
return dot / (Math.hypot(...a) * Math.hypot(...b));
};
const ranked = documents
.map((doc, i) => ({ doc, score: cosine(q!, d[i]!) }))
.sort((a, b) => b.score - a.score);
console.log(ranked);# Encode the query + candidates in one batch, then rank by cosine.
curl https://api.superlinked.com/v1/encode/Qwen%2FQwen3-Embedding-4B \
-H "Authorization: Bearer sk-sie-…" \
-H "Content-Type: application/json" \
-d "{\"items\":[{\"text\":\"For CMS's published L1851 example, what was required, what was submitted, what timing gap caused insufficient documentation, and what payment action followed?\"},{\"text\":\"https://www.cms.gov/training-education/medicare-learning-networkr-mln/compliance/medicare-provider-compliance-tips/lower-limb-orthoses Page Last Modified: 02/11/2026 04:18 PM\"},{\"text\":\"## Billing & Coding Criteria\"},{\"text\":\"We require prior authorization, a face-to-face encounter, and written order prior to delivery for HCPCS codes L1832 and L1851. Conduct the face-to-face encounter within the 6 months before prescribing the item.\"},{\"text\":\"## Example of Improper Payments Due to Insufficient Documentation for Lower Limb Orthoses\"},{\"text\":\"A supplier bills the claim for L1851 (Knee orthosis (KO), single upright, thigh and calf, with adjustable flexion and extension joint (unicentric or polycentric), medial-lateral and rotation control, with or without varus/valgus adjustment, prefabricated, off-the-shelf) and submits the following documentation per the review contractor's request:\"},{\"text\":\"- Standard written order with correct HCPCS coding\"},{\"text\":\"- Treating practitioner's medical record that has adequate medical necessity information\"},{\"text\":\"- Proof of delivery with face-to-face encounter 7 months ago\"},{\"text\":\"### What Documentation Was Missing?\"},{\"text\":\"The doctor didn't document the face-to-face encounter within 6 months of proof of delivery.\"},{\"text\":\"The review contractor completes the claim as an insufficient documentation error, and the MAC recoups payment.\"}],\"params\":{\"output_types\":[\"dense\"]}}"Build the "Search" capability into my app using the Superlinked Inference Engine (SIE).
Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: Qwen/Qwen3-Embedding-4B (SIE primitive: /encode). Keep the model id configurable.
Task
- Input: a query string plus a list of candidate documents.
- Behaviour: return the candidates ranked by semantic similarity to the query, with a score per candidate
- Encode the query and candidates in one batched /encode call, then rank by cosine similarity in the client. Do not call the API per candidate.
Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.from sie_sdk import SIEClientclient = SIEClient( api_key="sk-sie-…", base_url="https://api.superlinked.com",)query = "queryFor CMS's published L1851 example, what was required, what was submitted, what timing gap caused insufficient documentation, and what payment action followed?"documents = [ "document 1https://www.cms.gov/training-education/medicare-learning-networkr-mln/compliance/medicare-provider-compliance-tips/lower-limb-orthoses Page Last Modified: 02/11/2026 04:18 PM", "document 2## Billing & Coding Criteria", "document 3We require prior authorization, a face-to-face encounter, and written order prior to delivery for HCPCS codes L1832 and L1851. Conduct the face-to-face encounter within the 6 months before prescribing the item.", "document 4## Example of Improper Payments Due to Insufficient Documentation for Lower Limb Orthoses", "document 5A supplier bills the claim for L1851 (Knee orthosis (KO), single upright, thigh and calf, with adjustable flexion and extension joint (unicentric or polycentric), medial-lateral and rotation control, with or without varus/valgus adjustment, prefabricated, off-the-shelf) and submits the following documentation per the review contractor's request:", "document 6- Standard written order with correct HCPCS coding", "document 7- Treating practitioner's medical record that has adequate medical necessity information", "document 8- Proof of delivery with face-to-face encounter 7 months ago", "document 9### What Documentation Was Missing?", "document 10The doctor didn't document the face-to-face encounter within 6 months of proof of delivery.", "document 11The review contractor completes the claim as an insufficient documentation error, and the MAC recoups payment.",]items = [{"id": str(i), "text": d} for i, d in enumerate(documents)]ranked = client.score("modelQwen/Qwen3-Reranker-4B", {"text": query}, items)for r in ranked["scores"]: print(r["score"], documents[int(r["item_id"])])import { SIEClient } from '@superlinked/sie-sdk';
const client = new SIEClient('https://api.superlinked.com', {
apiKey: 'sk-sie-…',
});
const query = "For CMS's published L1851 example, what was required, what was submitted, what timing gap caused insufficient documentation, and what payment action followed?";
const documents = [
"https://www.cms.gov/training-education/medicare-learning-networkr-mln/compliance/medicare-provider-compliance-tips/lower-limb-orthoses Page Last Modified: 02/11/2026 04:18 PM",
"## Billing & Coding Criteria",
"We require prior authorization, a face-to-face encounter, and written order prior to delivery for HCPCS codes L1832 and L1851. Conduct the face-to-face encounter within the 6 months before prescribing the item.",
"## Example of Improper Payments Due to Insufficient Documentation for Lower Limb Orthoses",
"A supplier bills the claim for L1851 (Knee orthosis (KO), single upright, thigh and calf, with adjustable flexion and extension joint (unicentric or polycentric), medial-lateral and rotation control, with or without varus/valgus adjustment, prefabricated, off-the-shelf) and submits the following documentation per the review contractor's request:",
"- Standard written order with correct HCPCS coding",
"- Treating practitioner's medical record that has adequate medical necessity information",
"- Proof of delivery with face-to-face encounter 7 months ago",
"### What Documentation Was Missing?",
"The doctor didn't document the face-to-face encounter within 6 months of proof of delivery.",
"The review contractor completes the claim as an insufficient documentation error, and the MAC recoups payment.",
];
const items = documents.map((text, i) => ({ id: String(i), text }));
const ranked = await client.score('Qwen/Qwen3-Reranker-4B', { text: query }, items);
console.log(ranked.scores.map(({ itemId, score }) => ({ document: documents[Number(itemId)], score })));curl https://api.superlinked.com/v1/score/Qwen%2FQwen3-Reranker-4B \
-H "Authorization: Bearer sk-sie-…" \
-H "Content-Type: application/json" \
-d "{\"query\":{\"text\":\"For CMS's published L1851 example, what was required, what was submitted, what timing gap caused insufficient documentation, and what payment action followed?\"},\"items\":[{\"id\":\"0\",\"text\":\"https://www.cms.gov/training-education/medicare-learning-networkr-mln/compliance/medicare-provider-compliance-tips/lower-limb-orthoses Page Last Modified: 02/11/2026 04:18 PM\"},{\"id\":\"1\",\"text\":\"## Billing & Coding Criteria\"},{\"id\":\"2\",\"text\":\"We require prior authorization, a face-to-face encounter, and written order prior to delivery for HCPCS codes L1832 and L1851. Conduct the face-to-face encounter within the 6 months before prescribing the item.\"},{\"id\":\"3\",\"text\":\"## Example of Improper Payments Due to Insufficient Documentation for Lower Limb Orthoses\"},{\"id\":\"4\",\"text\":\"A supplier bills the claim for L1851 (Knee orthosis (KO), single upright, thigh and calf, with adjustable flexion and extension joint (unicentric or polycentric), medial-lateral and rotation control, with or without varus/valgus adjustment, prefabricated, off-the-shelf) and submits the following documentation per the review contractor's request:\"},{\"id\":\"5\",\"text\":\"- Standard written order with correct HCPCS coding\"},{\"id\":\"6\",\"text\":\"- Treating practitioner's medical record that has adequate medical necessity information\"},{\"id\":\"7\",\"text\":\"- Proof of delivery with face-to-face encounter 7 months ago\"},{\"id\":\"8\",\"text\":\"### What Documentation Was Missing?\"},{\"id\":\"9\",\"text\":\"The doctor didn't document the face-to-face encounter within 6 months of proof of delivery.\"},{\"id\":\"10\",\"text\":\"The review contractor completes the claim as an insufficient documentation error, and the MAC recoups payment.\"}]}"Build the "Rerank" capability into my app using the Superlinked Inference Engine (SIE).
Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: Qwen/Qwen3-Reranker-4B (SIE primitive: /score). Keep the model id configurable.
Task
- Input: a query string plus a list of candidate documents.
- Behaviour: reorder the candidates by true relevance to the query using the cross-encoder
- Call the selected SIE primitive once per request and map the response into your domain type.
Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.from sie_sdk import SIEClientclient = SIEClient( api_key="sk-sie-…", base_url="https://api.superlinked.com",)result = client.extract( "modelfastino/gliner2-large-v1", {"text": "textThe doctor didn't document the face-to-face encounter within 6 months of proof of delivery. The review contractor completes the claim as an insufficient documentation error, and the MAC recoups payment."}, labels=[ "entity typemissing documentation", "entity typeclaim result", "entity typepayment action", "entity typeorganization", "entity typetime period", ],)for span in result["entities"]: print(span["label"], span["text"])import { SIEClient } from '@superlinked/sie-sdk';
const client = new SIEClient('https://api.superlinked.com', {
apiKey: 'sk-sie-…',
});
const result = await client.extract(
'fastino/gliner2-large-v1',
{ text: "The doctor didn't document the face-to-face encounter within 6 months of proof of delivery. The review contractor completes the claim as an insufficient documentation error, and the MAC recoups payment." },
{ labels: ["missing documentation","claim result","payment action","organization","time period"] },
);
console.log(result.entities);curl https://api.superlinked.com/v1/extract/fastino%2Fgliner2-large-v1 \
-H "Authorization: Bearer sk-sie-…" \
-H "Content-Type: application/json" \
-d "{\"items\":[{\"text\":\"The doctor didn't document the face-to-face encounter within 6 months of proof of delivery. The review contractor completes the claim as an insufficient documentation error, and the MAC recoups payment.\"}],\"params\":{\"labels\":[\"missing documentation\",\"claim result\",\"payment action\",\"organization\",\"time period\"]}}"Build the "Named entities" capability into my app using the Superlinked Inference Engine (SIE).
Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: fastino/gliner2-large-v1 (SIE primitive: /extract). Keep the model id configurable.
Task
- Input: a block of text.
- Behaviour: return the named entities found in the text with their types
- Call the selected SIE primitive once per request and map the response into your domain type.
Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.Lower Limb Orthoses
Billing & Coding Criteria
Conduct the face-to-face encounter within the 6 months before prescribing the item.
Published L1851 example
- Standard written order with correct HCPCS coding
- Treating practitioner's medical record
- Proof of delivery with face-to-face encounter 7 months ago
Missing documentation
The doctor didn't document the face-to-face encounter within 6 months of proof of delivery.
- Extracts clean, agent-ready markdown
- Keeps tables and layout intact
- Ranks by meaning, not keyword overlap
- Scores every candidate against your query
- Reorders by true relevance
- Scored by meaning, keyword-free
The doctororganization didn't document the face-to-face encountermissing documentation within 6 monthstime period of proof of delivery. The review contractororganization completes the claim as an insufficient documentation errorclaim result, and the MACorganization recoups paymentpayment action.
- Pulls typed entities straight from raw text
Compare models for this task
Our example agent catches the timing error in CMS’s published case
View on GitHubFive model stages assemble and check the record
7 months 6-month limit
Insufficient documentationDeploy your way
Managed Cloud
Full compute toolkit for your agents with zero ops.
- No idle GPUs, pay for what you use
- Fits your stack: SDK, API, CLI, MCP
- Zero lock-in, self-host the same stack
- SOC 2 Type 2, US or EU data residency
no credit card required
Self-host with K8s
Easy & scalable deployment in your own cloud.
- Terraform to your cloud in minutes
- Apache-2.0, same engine as Cloud
- Scales to zero, no bill between jobs
- Per-tenant pools, no noisy neighbors
Deploy SIE to our AWS account with the superlinked/sie/aws Terraform module. Docs: superlinked.com/docs/deploymentDeploy SIE to our GCP project with the superlinked/sie/google Terraform module. Docs: superlinked.com/docs/deploymentDeploy SIE to our Azure AKS cluster via helm install. Requirements: superlinked.com/docs/deployment Run locally
Run the same models on your own machine.
- Runs on NVIDIA GPU or Apple Silicon
- One command, no Docker or cluster
- All 100+ Cloud models, fully offline
- Same SDK and IDs, no code changes
pip install "sie-server[local]" && sie-server servepip install "sie-server[local]" && sie-server serve --device cuda