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

# What is Precipiq? AI decisions meet dollar outcomes

> Precipiq links every AI decision to its dollar outcome on an immutable, hash-chained ledger — built for teams shipping autonomous AI into production.

When AI agents take actions that cost or earn money, two questions become unavoidable: which decision caused which outcome, and can you prove it? Precipiq answers both. Every agent decision is written to an append-only, hash-chained ledger, then linked to the downstream financial event it caused — revenue earned, cost incurred, or liability opened. The result is a forensically auditable record from "the model said X" to "the customer was charged Y," queryable years after the fact.

## Why teams use it

<CardGroup cols={2}>
  <Card title="Forensic traceability" icon="shield-check">
    Every decision is chain-linked and signable. Export a cryptographically
    sealed bundle for auditors, regulators, or post-incident review.
  </Card>

  <Card title="AI P&L" icon="chart-line">
    A live dashboard that attributes revenue, cost, and open liability to
    specific agents — so you can answer "is this AI making or losing money?".
  </Card>

  <Card title="Compliance-ready" icon="scale-balanced">
    Designed to align with EU AI Act Article 12 record-keeping and the kinds
    of evidence U.S. class-action discovery tends to demand.
  </Card>

  <Card title="Drop-in SDKs" icon="plug">
    Python and TypeScript SDKs with LangChain, CrewAI, OpenAI, and Vercel AI
    adapters. Wrap a function; never touch transport code.
  </Card>
</CardGroup>

## The 60-second mental model

Precipiq is built around four concepts that compose into a complete audit trail.

<Steps>
  <Step title="Decision">
    Your AI picks an action. The SDK writes a **Decision Record**: inputs,
    outputs, confidence, human-in-loop flag, and timestamp.
  </Step>

  <Step title="Chain">
    Each record hashes its predecessor's hash into its own `prev_hash` field —
    tamper-evident and verifiable in constant time.
  </Step>

  <Step title="Financial event">
    A payment clears, a refund fires, an invoice books. Stripe and QuickBooks
    webhooks feed these in automatically; you can also POST events directly.
  </Step>

  <Step title="Consequence link">
    The attribution engine (or you) connects decisions to events. Live AI P\&L
    updates. Threshold-exceeded liabilities fire dashboard alerts.
  </Step>
</Steps>

## Where to go next

<CardGroup cols={2}>
  <Card title="Quick start" icon="rocket" href="/quickstart">
    Install the SDK, log your first decision, and see it on the dashboard in
    five minutes.
  </Card>

  <Card title="Core concepts" icon="book-open" href="/concepts/decision-records">
    Understand Decision Records, Financial Events, Consequence Links, and the
    Hash Chain.
  </Card>

  <Card title="API reference" icon="code" href="/api-reference">
    Full endpoint reference with interactive try-it forms and multi-language
    code samples.
  </Card>

  <Card title="Stripe integration" icon="plug" href="/integrations/stripe">
    Auto-create Financial Events from Stripe webhooks and let the attribution
    engine propose consequence links.
  </Card>
</CardGroup>

## Not a fit (yet)

Precipiq is built for product-side AI where an action costs money. It is not a model-observability replacement — tools like LangSmith and Arize are better suited for tracing prompts, inspecting activations, and profiling latency. Precipiq records decisions so the downstream consequences can be measured and defended, not to prevent bad decisions from happening.