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

# Implementation Guide

> How to take a new client from kickoff to a trusted knowledge graph, and who does what along the way

## What this guide is for

Experio answers questions from a client's own data. It does that by building a **knowledge graph**: a connected model of the client's clients, projects, people, contracts and everything else that matters to them. It builds the graph from their documents and their business systems.

The software reads files and tables. It can't guess the business rules behind them: which things matter, how they connect, which lists the firm already uses, when two names mean the same thing. An implementation captures those rules in a series of workshops and then enters them in Experio. That work is what makes the answers accurate.

This guide is the playbook for that work. It explains how Experio works, defines the building blocks, and lays out an 8–10 week plan with a workshop for each decision. Every workshop page includes an agenda, the questions to ask, and a worked example.

## Who it is for

| Reader | Role in the implementation | Start with |
| - | - | - |
| **Forward Facing Engineer (FFE)** | Leads the implementation and is Experio's project lead. Runs the workshops, enters the configuration, tunes accuracy, and brings in other Experio SMEs as needed. | Everything, in order |
| **Client Project Manager (PM)** | Owns the client-side plan, the calendar, the decision log and status reporting. | [Roadmap](/implementation/roadmap), [Running the Workshops](/implementation/running-workshops) |
| **Client super user** | A business power user at the client. Follows along, owns the decisions with the subject-matter experts, and takes over the configuration after go-live. | [How Experio Works](/implementation/how-experio-works), [Key Concepts](/implementation/key-concepts) |
| **Client sponsor** | Sets the goals and the success criteria and removes blockers. | This page, [Roadmap](/implementation/roadmap) |

<Tip>
  Super users: you don't need to be technical. Each workshop page says what you'll be asked to decide and what to prepare. After handover, you'll use the same pages to maintain the configuration.
</Tip>

## The approach in one picture

The method starts from the **questions the business wants answered** and the **agents it wants to run**. It works backwards to the data model, then builds forwards to a tested graph.

```mermaid theme={null}
flowchart LR
    Q["Questions and agents<br/>(what value looks like)"] --> D["Data inventory<br/>(where the truth lives)"]
    D --> M["Model<br/>ontology, taxonomies,<br/>artifact types, mappings,<br/>matching"]
    M --> P["Pilot ingestion<br/>(small sample)"]
    P --> V["Validate<br/>golden questions +<br/>graph evaluation"]
    V -->|"fix and repeat"| M
    V --> C["Consume<br/>assistants, templates,<br/>agent flows"]
    C --> L["Go-live and<br/>handover"]
```

Three ideas run through the whole guide:

1. **Questions drive the model.** Every entity type, relationship and attribute should trace back to a question someone actually asks. If no question needs it, leave it out of the pilot.
2. **Tables first, then documents.** Business systems (HR, CRM, finance) supply the reliable master list of clients, people and projects. Documents then add detail to those records instead of creating near-duplicates. See [How Data Gets to the Graph](/implementation/data-to-graph).
3. **Measure, then tune.** Accuracy is checked against a list of **golden questions** with known answers, agreed in the first workshop. Tuning continues until the must-have questions pass.

## How the guide is organised

<CardGroup cols={2}>
  <Card title="Start Here" icon="compass" href="/implementation/how-experio-works">
    How Experio works, how data reaches the graph, and definitions of every building block.
  </Card>

  <Card title="Plan" icon="calendar" href="/implementation/roadmap">
    The 8–10 week roadmap, phases, deliverables, roles and permissions.
  </Card>

  <Card title="Workshops" icon="users" href="/implementation/running-workshops">
    Ten workshops, from questions and agents to access control, each with agenda, script and example.
  </Card>

  <Card title="Validate & Launch" icon="rocket" href="/implementation/pilot-ingestion">
    Pilot ingestion, accuracy validation, go-live and handover.
  </Card>

  <Card title="Worked Example" icon="building" href="/implementation/worked-example">
    Northbridge Consulting, a fictional professional-services firm, followed from start to finish.
  </Card>

  <Card title="Templates" icon="clipboard-list" href="/implementation/templates">
    Copy-ready worksheets, agendas and checklists for every step.
  </Card>
</CardGroup>

## What "done" looks like

An implementation is complete when:

* The must-have golden questions for each use case pass (a common target is 80% or more), and every answer cites its sources.
* The agreed agents (agent flows) produce usable output for pilot users.
* The full agreed corpus is ingested, and **Model & Define > Compatibility** shows no invalid configuration.
* The client super user can run the routine work alone: the conflict review queue, taxonomy refreshes, new data sources and small model changes.
* The decision log, the ontology rationale and the golden-question scores are handed over.

## Related guides

* [Admin Guide](/admin-guide/overview): reference for every admin page. This guide links to it for the click-by-click detail.
* [User Guide](/user-guide/getting-started): what end users see. Use it for training at go-live.
* [Implementation Playbook](/admin-guide/implementation-playbook): a one-page summary of each decision and the admin page it belongs on.