> ## 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 Roadmap > An 8–10 week plan from kickoff to go-live: phases, workshops, deliverables and exit criteria ## Overview A typical implementation runs **8–10 weeks** from kickoff to go-live. It has one preparation phase and six working phases. Each phase ends with an exit review: the FFE, the client PM and the super user confirm the exit criteria are met before moving on. Adjust the length to the number of use cases, the number of data sources and how available the client's experts are. ```mermaid theme={null} gantt dateFormat YYYY-MM-DD axisFormat W%W section Discover Kickoff and WS1 per use case :d1, 2026-01-05, 8d WS2 Data Inventory :d2, after d1, 3d section Model WS3 Ontology :m1, 2026-01-14, 5d WS4 Taxonomies :m2, after m1, 3d WS5 Artifact Types :m3, after m2, 5d WS6 Data Mapping :m4, after m2, 5d WS7 Identity and Matching :m5, after m3, 3d section Pilot ingest Structured loads :p1, 2026-01-28, 4d Document sample and tuning :p2, after p1, 8d WS8 Enrichment Rules :p3, after p1, 5d section Validate Golden-question scoring round 1 :v1, 2026-02-11, 4d Fixes and round 2 :v2, after v1, 5d WS9 Access Control (optional) :v3, 2026-02-11, 5d section Consume WS10 Assistants and Agent Flows :c1, 2026-02-18, 5d User acceptance :c2, after c1, 5d section Launch Full ingestion and rollout :l1, 2026-03-02, 7d Hypercare and handover :l2, after l1, 7d ``` The dates in the chart are illustrative. The plan is a sequence with dependencies, not a fixed calendar. Workshops in the same phase can overlap when different experts own them. For example, data mapping with Finance can run alongside artifact types with Legal. ## Phase summary | Phase | Weeks | Goal | Workshops and work | Key deliverables | | - | - | - | - | - | | **0. Prepare** | Before week 1 | Everything needed to start is in place | Environment, accounts, access requests, team, kickoff pack | Environment URL; admin accounts; connector access requested; project plan | | **1. Discover** | 1–2 | Agree what value looks like and where the data is | Kickoff; [WS1 Questions & Agents](/implementation/ws-questions-and-agents), **once per use case**; [WS2 Data Inventory](/implementation/ws-data-inventory) | `questions.md`; agent candidates; success criteria; data inventory; key crosswalk; pilot sample | | **2. Model** | 2–4 | Capture the business rules | [WS3 Ontology](/implementation/ws-ontology), [WS4 Taxonomies](/implementation/ws-taxonomies), [WS5 Artifact Types](/implementation/ws-artifact-types), [WS6 Data Mapping](/implementation/ws-data-mapping), [WS7 Identity & Matching](/implementation/ws-identity-and-matching) | Ontology v1; taxonomies imported; artifact types tested on samples; mappings; matching strategies; Compatibility all valid | | **3. Pilot ingest** | 4–6 | Real data in the graph, tuned on a sample | [Pilot Ingestion](/implementation/pilot-ingestion); [WS8 Enrichment Rules](/implementation/ws-enrichment-rules) | Structured master data loaded; document sample ingested; review queues worked; enrichment rules run | | **4. Validate** | 6–7 | Prove accuracy against the golden questions | [Accuracy Validation](/implementation/accuracy-validation); [WS9 Access Control](/implementation/ws-access-control) (optional) | Scoring rounds; Graph Evaluation results; fix log; access policy in shadow mode | | **5. Consume** | 7–8 | Put the graph to work for users | [WS10 Assistants & Agent Flows](/implementation/ws-assistants-and-flows); user acceptance | Assistants; AI instructions; document templates; agent flows; pilot user sign-off | | **6. Launch & hand over** | 9–10 | Full corpus, all users, client ownership | [Go-Live & Handover](/implementation/go-live) | Full ingestion; rollout waves; training; hypercare; handover pack | ## Phase 0: Prepare **Goal.** Nobody waits on access in week 1. | Task | Owner | Notes | | - | - | - | | Provision the Experio environment and confirm **Observe > Startup Health** is green | Experio | Includes model configuration for chat, ingestion tiers, classification and embeddings | | Create admin accounts and set up SSO if needed | FFE + client IT | See [Roles & Permissions](/implementation/roles-and-permissions) | | Request connector access: OAuth app for SharePoint, Box or Google Drive; service account; folders in scope | Client IT (Raj at Northbridge) | This is often the longest lead-time item. Start it at contract signature. | | Request structured exports or API credentials for HR, CRM and finance | Client super user | Sample files are enough for the Model phase. Full exports come in Phase 3. | | Name the use cases (2–4) and their subject-matter experts | Sponsor + super user | Each use case gets its own WS1 session | | Book the workshop calendar for weeks 1–4 | PM | See [Running the Workshops](/implementation/running-workshops) | | Send the kickoff pack: this guide, the agenda and the WS1 homework | PM | The WS1 homework is to bring questions asked last week and reports built by hand | **Exit criteria.** The environment is healthy. Admin accounts work. Access requests are filed with named owners. Use cases and experts are named. Workshops are booked. ## Phase 1: Discover (weeks 1–2) **Goal.** Agree what success looks like, in the client's own words, and where the data to support it lives. * **Kickoff (90 minutes).** Goals, scope, roles, the roadmap, how Experio works ([How Experio Works](/implementation/how-experio-works)), and how decisions are made and logged. * **WS1 Questions & Agents, once per use case.** Each session produces golden questions with expected answers and agent candidates. The FFE and super user merge the sessions into one de-duplicated `questions.md`. * **WS2 Data Inventory.** For every must-have question, identify the system or library where its answer lives. The output is a data inventory, a **key crosswalk** (how the same client, person or project is identified in each source) and the pilot sample. **Exit criteria.** * `questions.md` has at least 15–30 must-have questions across the use cases, each with an expected answer and a source of truth. * Success criteria are signed off by the sponsor. For example: "80% of must-have golden questions pass, with correct citations, by the end of week 7." * Every must-have question maps to at least one source in the inventory. Questions with no source are dropped or marked "needs new data". * Pilot sample chosen: full structured exports, plus the document folders for 2–3 representative clients or projects. ## Phase 2: Model (weeks 2–4) **Goal.** Capture the business rules and enter them in Experio. | Workshop | Depends on | Typical length | Output entered on | | - | - | - | - | | WS3 Ontology | WS1, WS2 | 2 × 2 hours | **Model & Define > Ontology** | | WS4 Taxonomies | WS3 (draft) | 1–2 hours | **Model & Define > Taxonomies** (CSV import) | | WS5 Artifact Types | WS3, WS4 | 2 × 2 hours | **Model & Define > Artifact Types** | | WS6 Data Mapping | WS3, WS2 | 1–2 hours per source | **Model & Define > Data Mapping** | | WS7 Identity & Matching | WS3, WS6 | 90 minutes | **Administer > Client Configuration**, **Process > Matching Strategies** | Between sessions the FFE enters the configuration. The super user reviews it in Experio before the next session. Test Ingestion on the artifact types, run on real samples, should happen in this phase, not after. **Exit criteria.** * Ontology v1 is saved, and every entity type and relationship traces to at least one golden question. * Taxonomies are imported, with owners and a refresh process agreed. * Each artifact type has passed Test Ingestion on 3–5 real samples: correct classification, and the expected entities extracted. * Mappings are defined for each structured source, with the load order agreed. * Matching strategies are set for the key entity types, and someone is named to staff the review queue. * **Model & Define > Compatibility** shows no invalid configuration. ## Phase 3: Pilot ingest (weeks 4–6) **Goal.** Real data in the graph, and the configuration tuned on a sample. 1. Load structured master data in dependency order, and check the counts against the source. 2. Ingest the document sample (a few hundred files). Watch **Process > Jobs**. 3. Work the **Conflict Resolution** queues daily, and feed repeated patterns back into classification instructions and matching strategies. 4. Run **Graph Evaluation** per artifact type and fix the extraction instructions it points to. 5. Hold **WS8 Enrichment Rules** once there's real data to look at. Run the rules and spot-check the results. 6. Expect a **second modeling pass**. Pilot data always reveals a missing attribute or a relationship nobody mentioned. **Exit criteria.** Structured counts reconcile with the sources. The document sample is processed, with under 5% failed and the review queues cleared. Graph Evaluation is "good" or "acceptable" for each artifact type. Enrichment rules are run and spot-checked. ## Phase 4: Validate (weeks 6–7) **Goal.** Prove answer accuracy against the golden questions. * **Scoring round 1.** Run every must-have question in chat. Record the answer, check the citations, score pass, partial or fail, and assign a root cause. See [Accuracy Validation](/implementation/accuracy-validation). * **Fix** by root cause: classification, extraction, matching, mapping, missing data, or retrieval and assistant instructions. * **Scoring round 2.** Re-run the full list, not just the failures, to catch regressions. * **WS9 Access Control** (optional). Design the policy, run it in shadow mode, and preview it as real users. **Exit criteria.** The success criteria from Phase 1 are met, or the gap is understood and accepted by the sponsor. The fix log is up to date. If access control is used, it is validated in shadow mode. ## Phase 5: Consume (weeks 7–8) **Goal.** Put the graph to work in the tools users will actually use. * **WS10 Assistants & Agent Flows.** Configure the assistant(s), AI instructions and document templates. Build the agent candidates from WS1 as agent flows. * **User acceptance testing.** 5–10 pilot users per use case work through real tasks for a week and log issues. **Exit criteria.** Pilot users sign off each use case. Every agent flow produces usable output for its sample inputs. Blocking issues are fixed. ## Phase 6: Launch & hand over (weeks 9–10) **Goal.** Full corpus, all users, and client ownership. * Ingest the full corpus in batches, library by library, and watch jobs and cost. * Turn on access control enforcement, if used. * Roll out in waves, with training by persona. * Two weeks of hypercare, with daily triage. * Handover: the decision log, the ontology rationale, `questions.md` with the final scores, the runbook for routine tasks, and the operating cadence. **Exit criteria.** See the go-live readiness checklist in [Go-Live & Handover](/implementation/go-live). ## Status reporting The PM sends a weekly status report with the phase, completed and upcoming workshops, decisions made, open decisions, risks, and the latest golden-question pass rate once scoring has started. A template is in [Templates](/implementation/templates). ## Common risks | Risk | Early sign | Mitigation | | - | - | - | | Connector access is late | No OAuth app by week 2 | Start in Phase 0. Use uploaded sample files for Test Ingestion meanwhile. | | Experts aren't available | Workshops rescheduled | Book the whole Model phase at kickoff. Send pre-reads so each session is only for decisions. | | Scope creep in the ontology | 25+ entity types in v1 | Every type must trace to a must-have golden question. Park the rest for phase 2. | | Keys don't line up across sources | Duplicate clients or people after the pilot | Build the key crosswalk in WS2. Standardise keys before the structured loads. | | Unclear success criteria | "It should just know everything" | Golden questions with expected answers, signed off in Phase 1 | | Documents don't contain the answer | Questions fail with "no data" | Mark them in `questions.md` as needing a new source, or drop them |