> ## Documentation Index
> Fetch the complete documentation index at: https://claritylabs.inc/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Clarity Labs SDK: Provider-Agnostic LLM Insurance Toolkit

> Build LLM-powered insurance workflows with source-grounded extraction, citation-backed queries, application pipelines, and PCE processing—no framework lock-in.

The Clarity Labs SDK (`@claritylabs/cl-sdk`) v4.5.0 gives you a complete toolkit for building LLM-powered insurance workflows entirely in TypeScript. Because it communicates with language models through plain callback functions—`GenerateText` and `GenerateObject`—you choose your own AI provider and model without any framework lock-in.

## Install

Install the SDK along with its peer dependencies:

```bash theme={"system"}
npm install @claritylabs/cl-sdk pdf-lib zod
```

## Quick example

The snippet below shows the core pattern: build source spans from your parsed PDF pages, create an extractor with your provider callback, and get a fully structured insurance document back in one call.

```typescript theme={"system"}
import { buildPageSourceSpans, createExtractor } from "@claritylabs/cl-sdk";

const extractor = createExtractor({ generateObject });
const sourceSpans = buildPageSourceSpans([
  { documentId: "policy-123", sourceKind: "policy_pdf", pageNumber: 1, text: pageOneText },
]);

const result = await extractor.extract(pdfBase64, "policy-123", { sourceSpans });
console.log(result.document.carrier);      // "Hartford"
console.log(result.operationalProfile);    // source-backed policy facts
```

## Key features

<CardGroup cols={2}>
  <Card title="Provider-agnostic LLM" icon="plug">
    Pass any `generateText` or `generateObject` callback—Anthropic, OpenAI, Vercel AI SDK, or your own—without changing SDK code.
  </Card>

  <Card title="Source-tree extraction" icon="file-search">
    Parser-provided PDF spans become a canonical source hierarchy, grounding every extracted fact in traceable evidence.
  </Card>

  <Card title="Citation-backed query agent" icon="message-circle-question-mark">
    A five-phase query pipeline (classify → plan → retrieve → reason → respond) returns answers with source citations.
  </Card>

  <Card title="Application processing" icon="file-pen-line">
    A full pipeline classifies, extracts, auto-fills, and batches questions from ACORD applications using a question graph.
  </Card>

  <Card title="PCE workflows" icon="file-check">
    Policy Change Endorsement processing handles intake, evidence collection, validation, and submission packet generation.
  </Card>

  <Card title="Case workflow primitives" icon="briefcase">
    Shared building blocks for proposals, evidence tracking, validation, and stable IDs across case-based workflows.
  </Card>

  <Card title="Agent system prompts" icon="bot">
    `buildAgentSystemPrompt` composes channel-aware prompts for email, chat, SMS, Slack, and Discord agents.
  </Card>

  <Card title="Storage interfaces" icon="database">
    `DocumentStore`, `MemoryStore`, and `SourceStore` abstractions ship with a SQLite reference implementation.
  </Card>
</CardGroup>

## Design principles

CL SDK is built around four principles that keep your codebase clean and your workflows auditable:

* **Provider-agnostic** — plain `GenerateText` and `GenerateObject` callbacks mean zero vendor coupling.
* **Pure TypeScript** — no framework dependencies; works in Node.js, Bun, Deno, and edge runtimes.
* **Deterministic scaffold with bounded agentic steps** — pipelines follow predictable phases; LLM decisions are confined to clearly marked decision points.
* **Source-grounded** — every extracted fact, query answer, and workflow output cites `sourceNodeIds` or `sourceSpanIds`, giving you a full evidence trail.

## What's included

| Module                      | What it does                                                                    |
| --------------------------- | ------------------------------------------------------------------------------- |
| `createExtractor`           | Source-tree extraction from PDF or Docling input                                |
| `createQueryAgent`          | Citation-backed question answering over stored documents                        |
| `createApplicationPipeline` | ACORD application processing with question batching                             |
| `createPceAgent`            | Policy Change Endorsement intake through submission packet                      |
| `buildAgentSystemPrompt`    | Channel-aware agent prompt composition                                          |
| Storage interfaces          | `DocumentStore`, `MemoryStore`, `SourceStore`, `ApplicationStore` + SQLite impl |
| ACORD LOB taxonomy          | 107 line-of-business codes                                                      |
| MCP server                  | Companion package for Model Context Protocol integration                        |

<Tip>
  If you're new to the SDK, head to the [Quickstart](/docs/cl-sdk/quickstart) to have your first extraction running in minutes. For a deeper understanding of how the eight systems interact, see the [Architecture](/docs/cl-sdk/architecture) page.
</Tip>