> ## 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.

# Running the Workshops

> How the ten implementation workshops fit together, who is in the room, and how each one ends with signed-off decisions

Experio can read files, but it cannot read your firm's decisions. Which questions matter, which systems hold the truth, what a "client" is, when two names mean the same person: none of that is written down anywhere Experio can find it. The workshops are where those decisions get made and recorded. Each one produces an output the Forward Facing Engineer (FFE) enters into Experio, and each output makes answers more accurate.

This page explains how the workshop program works as a whole. The individual workshop pages cover what happens inside each session.

## The ten workshops

| # | Workshop | Purpose | Attendees (client side) | Duration | Outputs |
| - | - | - | - | - | - |
| 1 | [Questions & Agents](/implementation/ws-questions-and-agents) | Capture the real questions and repeatable jobs for one use case | Super user, use-case SMEs, a few end users | 2–3 h, **once per use case** | `questions.md` (golden questions), agent candidates, success criteria |
| 2 | [Data Inventory](/implementation/ws-data-inventory) | Find where the truth for each question lives | Super user, system owners, IT admin | 2–3 h | Source inventory, key crosswalk, pilot sample, access requests |
| 3 | [Ontology](/implementation/ws-ontology) | Agree the entity types, attributes and relationships | Super user, SMEs | 3 h (often 2 sessions) | Draft ontology |
| 4 | [Taxonomies](/implementation/ws-taxonomies) | Agree controlled vocabularies and who owns them | Super user, list owners | 1.5–2 h | Taxonomy CSVs, owners |
| 5 | [Artifact Types](/implementation/ws-artifact-types) | Define document families and what to extract from each | Super user, SMEs, document owners | 3 h | Artifact types, folder filters, extraction policies |
| 6 | [Data Mapping](/implementation/ws-data-mapping) | Map structured columns to the ontology | Super user, system owners | 2 h | One mapping per export, load order |
| 7 | [Identity & Matching](/implementation/ws-identity-and-matching) | Decide when two records are the same thing | Super user, SMEs, data owners | 2 h | Matching strategies, processing types |
| 8 | [Enrichment Rules](/implementation/ws-enrichment-rules) | Capture rules the documents do not state | Super user, SMEs | 1.5–2 h | Enrichment rules |
| 9 | [Access Control](/implementation/ws-access-control) (optional) | Decide who may see which records | Super user, Legal/Compliance, IT | 2 h | Access policy, test users |
| 10 | [Assistants & Agent Flows](/implementation/ws-assistants-and-flows) | Configure how people consume the graph | Super user, SMEs, pilot users | 3 h | Assistants, AI instructions, templates, agent flows |

<Note>
  Workshop 1 is run **once per use case**, with the SMEs for that use case. Northbridge Consulting runs it three times: proposals (Dana Ortiz), staffing (Sam Whitfield) and contracts (Helen Park). Plan the calendar with that in mind.
</Note>

## Dependency order

Each workshop depends on decisions made in earlier ones. A data mapping written before the ontology exists has to be rebuilt. Matching rules cannot be written until you know which entity types exist and which keys each source carries.

```mermaid theme={null}
flowchart LR
  WS1["WS1 Questions & Agents<br/>(once per use case)"] --> WS2["WS2 Data Inventory"]
  WS1 --> WS3["WS3 Ontology"]
  WS2 --> WS3
  WS3 --> WS4["WS4 Taxonomies"]
  WS3 --> WS5["WS5 Artifact Types"]
  WS4 --> WS5
  WS3 --> WS6["WS6 Data Mapping"]
  WS2 --> WS6
  WS5 --> WS7["WS7 Identity & Matching"]
  WS6 --> WS7
  WS7 --> P["Pilot ingestion"]
  P --> WS8["WS8 Enrichment Rules"]
  P --> WS9["WS9 Access Control<br/>(optional)"]
  WS8 --> V["Accuracy validation"]
  WS9 --> V
  V --> WS10["WS10 Assistants & Agent Flows"]
  P -. "second modeling pass" .-> WS3
```

Read the diagram left to right:

* **Discover (WS1, WS2)** comes first. Nothing else can be designed until you know the questions and where their answers live.
* **Model (WS3 to WS7)** turns those findings into configuration. WS4 and WS6 can run in parallel once the ontology draft exists.
* **Pilot ingestion** loads real data. WS8 and WS9 need a populated graph to be useful.
* **WS10** comes last, because assistants and agent flows are only as good as the graph beneath them.

### Which workshops are optional

* **WS9 Access Control** is optional. Run it only when the firm has ethical walls, confidential contracts or other record-level visibility rules. See [access control](/implementation/key-concepts#access-control).
* **WS8 Enrichment Rules** can be very short if the pilot shows the documents already carry the attributes you need. Do not skip the conversation; confirm there is nothing to infer.
* **Agent flows** in WS10 are optional for a first launch. Most firms start with a chat assistant and add agent flows once the golden questions pass.

## Cadence

Map the workshops onto the [roadmap](/implementation/roadmap):

| Phase | Weeks | Workshops | Typical pace |
| - | - | - | - |
| Discover | 1–2 | Kickoff, WS1 (per use case), WS2 | 2–4 sessions per week |
| Model | 2–4 | WS3, WS4, WS5, WS6, WS7 | 2–3 sessions per week |
| Pilot ingest | 4–6 | WS8 | 1 session, plus modeling revisits |
| Validate | 6–7 | WS9 if needed | 1 session |
| Consume | 7–8 | WS10 | 1–2 sessions |

Leave at least one working day between modeling workshops. The FFE needs that time to enter the configuration, and the super user needs it to review what was entered before the next session builds on it.

<Warning>
  Do not stack more than three workshops in a week. SMEs have day jobs, and a tired room agrees to things it has not thought through. Those decisions come back as rework during validation.
</Warning>

### Expect a second pass

Modeling workshops iterate. The first pass of WS3, WS5 and WS7 is based on what people *say* the data looks like. Pilot ingestion shows what it *actually* looks like: resumes that name people differently from HR, SOWs without project codes, a document family nobody mentioned. Book a 90-minute "model revisit" session after the first pilot ingestion, and tell the client at kickoff that it is planned, not a sign of failure.

## Roles in the room

| Role | Who | What they do |
| - | - | - |
| Facilitator | Experio FFE | Runs the agenda, asks the questions, proposes options, translates business answers into configuration |
| Scribe and timekeeper | Client PM | Keeps the decision log and parking lot, watches the clock, sends the follow-up |
| Specialists | Experio SMEs, as needed | Join sessions in their area (for example data modeling, integrations, agents, access control) and answer product questions |
| Decision owner | Client super user | Makes the call when the room disagrees; owns the configuration after handover |
| Subject-matter experts | Client SMEs | Supply the real questions, examples and rules for their area |
| System owners | Client HR, Sales ops, Finance, IT | Answer "what does this field mean" and "can we export that" |

The super user and the SME for the use case together own each decision. The FFE should propose, not decide. If the FFE makes business decisions, the client cannot maintain the configuration after handover. See [Roles and Permissions](/implementation/roles-and-permissions) for the Experio access each person needs.

## Preparation rhythm

Every workshop follows the same rhythm.

<Steps>
  <Step title="Five working days before: book and brief">
    The PM sends the invite with the purpose, agenda and attendee list. Name the decisions the session must make, not just the topic.
  </Step>

  <Step title="Three working days before: send pre-reads and homework">
    The FFE sends the pre-read: the previous workshop's outputs, a draft of what this session will produce, and specific homework (for example, "bring five real questions you answered last week" or "export 20 sample rows from Deltek").
  </Step>

  <Step title="One working day before: prepare the draft">
    The FFE drafts the likely answer from the homework: a draft ontology, a draft mapping, a draft taxonomy. Reacting to a draft is much faster than designing on a blank whiteboard.
  </Step>

  <Step title="Day of: run the session">
    Follow the workshop page's agenda. Close with a read-back of every decision.
  </Step>

  <Step title="Within one working day: send the follow-up">
    The PM sends the decision log, parking lot and action owners. The super user replies to confirm sign-off.
  </Step>
</Steps>

### Good pre-reads

* Short: two pages or less, plus attachments.
* Concrete: real file names, real column headers, real questions.
* Marked with what the reader should do: "Check that these 12 entity types cover your questions" beats "please review".

## Capturing decisions

Keep two living documents for the whole implementation. The PM owns both; the templates are on the [Templates](/implementation/templates) page.

### Decision log

One row per decision. Record the decision, not the discussion.

| # | Date | Workshop | Decision | Decided by | Reason | Entered in Experio |
| - | - | - | - | - | - | - |
| D-014 | 2026-10-08 | WS3 | Projects are identified by Deltek `project_code`; documents may not create projects | Marcus Lee, Sam Whitfield | Finance is the system of record for projects | Yes: Project set to Match Only on all artifact types |
| D-015 | 2026-10-08 | WS3 | Proposal outcome is an enum: won / lost / pending | Marcus Lee, Dana Ortiz | Matches Salesforce stage values | Yes: Ontology revision 7 |

The last column matters. A decision is not done until it is configured and the super user has seen it in Experio.

### Parking lot

Anything that is important but not for this session goes here, with an owner and the workshop where it will be resolved. Review the parking lot at the start of every session. Items that stay in the lot for three sessions either get a decision or get dropped.

## Remote, in person, or hybrid

| Format | Works well for | Tips |
| - | - | - |
| In person | Kickoff, WS1, WS3 | Whiteboard the ontology; people argue more productively face to face |
| Remote | WS2, WS4, WS6, WS7, WS8 | Share the Experio admin screen; enter simple decisions live |
| Hybrid | Anything, if needed | Put the remote attendees' faces on the main screen and ask them first |

For remote sessions, keep to two hours with a break, share one screen only, and have the PM post each decision in the meeting chat as it is made. Ask people to keep cameras on for decision points.

## Handling disagreement

Disagreement is useful. It usually means two teams use the same word for different things, which is exactly what the ontology must resolve.

1. **Name the disagreement.** "Sales calls it an account; Finance calls it a client. Are they the same thing?"
2. **Go to an example.** Ask for a real record. Arguments about definitions end quickly when you look at the Lakeshore Health row in both systems.
3. **Go back to the questions.** Which option lets the golden questions be answered? The questions are the tie-breaker.
4. **Decide reversibly.** Most modeling choices can be changed after the pilot. Say so, pick one, and log it.
5. **Escalate if needed.** If the super user and SME still cannot agree, park it with the sponsor (at Northbridge, Priya Shah) as the owner and a date.

## Closing each workshop

Save the last 15 minutes of every session for closing. Do not let it get squeezed.

1. The PM reads back every decision in the log.
2. The decision owner confirms each one aloud, or it goes to the parking lot.
3. Review the workshop's exit criteria (on each workshop page) and tick what is done.
4. Agree the actions, owners and due dates, including client homework for the next session.
5. The super user confirms sign-off by replying to the follow-up email. That reply is the record.

## Between workshops

The time between sessions is when configuration actually happens.

| Who | What |
| - | - |
| FFE | Enters the decisions into Experio (for example **Model & Define > Ontology**), updates the decision log's last column, and notes anything that did not fit |
| Super user | Opens Experio and reviews what was entered; flags anything that does not match the decision |
| SMEs | Complete homework: sample documents, real questions, list exports |
| System owners | Produce exports and approve access requests raised in WS2 |
| PM | Chases actions, updates the plan, books the next session |

<Tip>
  Have the super user make at least one change themselves between each pair of workshops, with the FFE watching. By WS10 they should be comfortable in the admin pages, which makes handover a formality instead of a crash course.
</Tip>

## Next

Start with [Workshop 1: Questions & Agents](/implementation/ws-questions-and-agents).