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

# Build → Run Sequence

> The six-step path from an empty platform to a working agent your team runs against a real client.

The building blocks are easier to act on when you know the order to tackle them in. This is the canonical sequence — from registering your first system to a team member running an agent against a live client. Each step builds on the one before it, so following the order saves you backtracking.

## The Six-Step Build Sequence

<Steps>
  <Step title="Configure Connectors">
    Register the external systems you'll need — from the catalogue or as custom MCP connectors. This is done once and reused broadly, so start here.

    See [Connectors](/accounting/connectors).
  </Step>

  <Step title="Build Skills">
    Compose connectors into single-purpose skills, each with a clear instruction and a defined input/output contract. Keep each skill focused on one job.

    See [Skills](/accounting/skills).
  </Step>

  <Step title="Add Pipelines to skills that need data">
    Within a skill, define its pipeline — the source connectors, the transformation, the schedule, and the workstream binding. The data lands in the Data Store, ready for agents to read.

    See [Pipelines](/accounting/pipelines).
  </Step>

  <Step title="Build Agents">
    Chain skills together with glue logic, wire in the Data Store and File Explorer reads through those skills, place human-in-the-loop gates at the review moments, and bind the agent to its workstreams.

    See [Agents & Human-in-the-Loop](/accounting/agents).
  </Step>

  <Step title="Set up Workstreams">
    Create a workstream per client and add the people who should have access. Point pipelines and files at the right client systems.

    See [Workstreams](/accounting/workstreams).
  </Step>

  <Step title="Run it in the App">
    End-users open the agent, pick the workstream, converse, and resolve any human-in-the-loop steps. Every run is logged under the workstream.

    See [The End-User App](/accounting/end-user-app).
  </Step>
</Steps>

<Tip>
  The first three steps are foundation you build once and reuse across every client. The real per-client work is small: create a workstream, point it at the client's systems, and run. That's what makes onboarding a new client fast.
</Tip>

## Why the Sequence Matters

The order isn't arbitrary — it follows the dependency chain. You can't build a useful skill without a connector to give it access, can't build an agent without skills to compose, and can't run anything meaningful without a workstream to scope it. Work the sequence in order and each step has everything it needs from the steps before it.

## Next Steps

1. [Review the design principles behind the platform](/accounting/design-principles)
2. [See how everything connects](/accounting/how-it-connects)
3. [Start at step one with Connectors](/accounting/connectors)