ms-ai-architect/skills/ms-ai-advisor/references/architecture/poc-template.md

# POC Template - Microsoft AI Projects

**Last updated:** 2026-01 (research via microsoft-learn MCP)

---

Dette dokumentet tilbyr en strukturert mal for å planlegge, gjennomføre og evaluere Proof of Concept (POC) prosjekter for Microsoft AI-løsninger. Malen er tilpasset Azure AI Foundry, Copilot Studio, Power Platform AI, og andre Microsoft AI-plattformer.

## Innhold

1. [POC Plan Template](#poc-plan-template)
2. [Success Criteria Framework](#success-criteria-framework)
3. [Evaluation Rubric](#evaluation-rubric)
4. [Platform-Specific Checklists](#platform-specific-checklists)
5. [Risk Assessment Template](#risk-assessment-template)
6. [Timeline Templates](#timeline-templates)
7. [Stakeholder Communication Template](#stakeholder-communication-template)
8. [Go/No-Go Decision Framework](#gono-go-decision-framework)
9. [Example POC Plan](#example-poc-plan)

---

## POC Plan Template

Bruk denne malen for å strukturere din POC-plan. Fyll ut hver seksjon basert på ditt spesifikke use case.

### 1. Executive Summary

**Hensikt med POC:**
_[1-2 setninger: Hva skal POC bevise eller validere?]_

**Forventet varighet:** _[1 uke / 2 uker / 4 uker]_

**Estimert ressursbehov:** _[Antall personer, roller, budsjett]_

**Beslutningspunkt:** _[Dato for go/no-go beslutning]_

---

### 2. Business Case

#### 2.1 Problem Statement
_[Beskriv forretningsproblemet eller ineffektiviteten som AI kan løse.]_

**Eksempel:**
> Kundestøtte bruker 40% av tiden på repetitive spørsmål om ordrestatus, produktreturer og leveringsinformasjon. Dette binder opp ressurser som kunne brukes på mer komplekse kundehenvendelser.

#### 2.2 Target Outcome
_[Hva er det ønskede resultatet? Vær konkret og målbar.]_

**Eksempel:**
> Automatisere 60% av repetitive kundehenvendelser via chatbot, redusere gjennomsnittlig responstid fra 15 minutter til 2 minutter, og frigjøre 16 timer per uke for støtteteamet.

#### 2.3 Strategic Value
Ranger strategisk verdi (1-5, hvor 5 er høyest):

- **Business Impact:** _[1-5]_ — Hvor stor påvirkning har dette på forretningen?
- **User Value:** _[1-5]_ — Hvor mye verdi gir dette til sluttbrukere?
- **Innovation Potential:** _[1-5]_ — Hvor innovativt er dette for organisasjonen?
- **Strategic Alignment:** _[1-5]_ — Hvor godt aligner dette med organisasjonens AI-strategi?

---

### 3. Technical Scope

#### 3.1 AI Maturity Assessment
Identifiser din organisasjons AI-modningsnivå (basert på Microsoft CAF):

| Level | Skills Required | Data Readiness | Feasible Use Cases |
|-------|-----------------|----------------|-------------------|
| **Level 1** | Basic AI-forståelse, data-integrasjon | Minimal data, enterprise data tilgjengelig | Azure quickstart, Copilot-løsninger |
| **Level 2** | Model selection, deployment, data cleaning | Små strukturerte datasett, domene-spesifikk data | Analytical AI (Foundry Tools), Custom gen AI chat uten RAG, Fine-tuning |
| **Level 3** | Prompt engineering, data chunking, preprocessing | Store historiske datasett, domene-spesifikk data | Gen AI med RAG, ML model training, small AI models på VMs |
| **Level 4** | Advanced AI/ML, infra management, orchestration | Store treningsdatasett | Large gen AI/ML apps på VMs, AKS, Container Apps |

**Din organisasjon er på:** _[Level 1 / 2 / 3 / 4]_

#### 3.2 Chosen AI Solution
_[Velg én eller flere:]_

- [ ] **Microsoft 365 Copilot** (extensions/agents)
- [ ] **Copilot Studio** (custom agents)
- [ ] **Azure AI Foundry** (custom gen AI apps)
- [ ] **Power Platform AI** (AI Builder, Power Automate AI)
- [ ] **Azure Machine Learning** (custom ML models)
- [ ] **Analytical AI** (Content Safety, Document Intelligence, Custom Vision)

**Rationale:**
_[Hvorfor er denne løsningen valgt? Hva gjør den til det beste valget for dette use case?]_

#### 3.3 Data Requirements

**Data Sources:**
1. _[Source 1: Type, format, quality, accessibility]_
2. _[Source 2: Type, format, quality, accessibility]_
3. _[Source 3: ...]_

**Data Preparation Needed:**
- [ ] Data cleaning/normalization
- [ ] Data labeling
- [ ] Data chunking (for RAG)
- [ ] Privacy/security review (PII removal, anonymization)
- [ ] Data governance approvals

**Estimated Data Volume:**
_[Small (<100 MB) / Medium (100 MB - 10 GB) / Large (>10 GB)]_

#### 3.4 Infrastructure Requirements

**Compute:**
- [ ] Azure OpenAI capacity (model, region, quota)
- [ ] Azure Machine Learning compute (SKU, vCPUs, GPU)
- [ ] Power Platform capacity (Copilot Studio, AI Builder credits)

**Storage:**
- [ ] Azure Storage (type, size)
- [ ] Vector database (Azure AI Search, Cosmos DB)

**Network:**
- [ ] VNet integration
- [ ] Private endpoints
- [ ] Bandwidth requirements

**Security & Compliance:**
- [ ] Azure Policy enforcement
- [ ] Content Safety filters
- [ ] Data residency requirements
- [ ] Authentication/authorization (Entra ID, RBAC)

---

### 4. Success Criteria

Definer spesifikke, målbare kriterier for POC-suksess. Se [Success Criteria Framework](#success-criteria-framework) for detaljerte KPIer.

#### 4.1 Technical Success Criteria
1. **Functional Requirements:**
   - _[Eksempel: Chatbotten skal kunne svare på 80% av testspørsmålene korrekt.]_
   - _[Eksempel: Systemet skal kunne håndtere 100 samtidige forespørsler.]_

2. **Performance Metrics:**
   - **Response Time:** _[Target: < 3 sekunder for 95% av forespørslene]_
   - **Accuracy:** _[Target: 85% nøyaktighet på validasjonsdatasett]_
   - **Availability:** _[Target: 99% uptime under testperioden]_

3. **Quality Metrics (for Gen AI):**
   - **Groundedness:** _[Target: 90% av svarene skal være faktabaserte]_
   - **Relevance:** _[Target: 85% av svarene skal være relevante for brukerens spørsmål]_
   - **Content Safety:** _[Target: 0% harmful content, 100% moderate risk filtered]_

#### 4.2 Business Success Criteria
1. **Efficiency Gains:**
   - _[Eksempel: Redusere behandlingstid med 50%]_

2. **Cost Savings:**
   - _[Eksempel: Redusere driftskostnader med 20%]_

3. **User Satisfaction:**
   - _[Eksempel: Oppnå 70% user satisfaction score]_

#### 4.3 Responsible AI Criteria
- [ ] **Fairness:** Løsningen skal ikke diskriminere basert på alder, kjønn, etnisitet, etc.
- [ ] **Transparency:** Brukere skal forstå når de interagerer med AI
- [ ] **Privacy:** Persondata skal beskyttes i henhold til GDPR/compliance-krav
- [ ] **Accountability:** Klare roller og ansvar for AI-beslutninger
- [ ] **Safety:** Content Safety filters implementert og testet
- [ ] **Inclusiveness:** Løsningen skal fungere for alle brukergrupper

---

### 5. Implementation Plan

#### 5.1 Phases & Milestones

**Phase 1: Prepare (Duration: _[X dager]_)**
- [ ] Data collection and preparation
- [ ] Environment setup (Azure, Power Platform)
- [ ] Team onboarding
- [ ] Security/compliance approvals

**Deliverable:** _[Data ready for use, infrastructure provisioned]_

---

**Phase 2: Build (Duration: _[X dager]_)**
- [ ] Develop initial prototype/POC
- [ ] Implement core functionality
- [ ] Integrate data sources
- [ ] Configure AI model/agent

**Deliverable:** _[Working prototype in dev environment]_

---

**Phase 3: Evaluate & Iterate (Duration: _[X dager]_)**
- [ ] Functional testing
- [ ] Performance testing
- [ ] Responsible AI testing (fairness, safety, bias)
- [ ] User acceptance testing (UAT)
- [ ] Iterate based on feedback

**Deliverable:** _[Validated POC with test results]_

---

**Phase 4: Document & Decide (Duration: _[X dager]_)**
- [ ] Document lessons learned
- [ ] Compile evaluation report
- [ ] Prepare go/no-go recommendation
- [ ] Present to stakeholders

**Deliverable:** _[POC report + go/no-go decision]_

---

#### 5.2 Team Roles & Responsibilities

| Role | Responsible For | Time Commitment |
|------|-----------------|-----------------|
| **Project Lead** | Overall POC coordination, stakeholder communication | _[X hours/week]_ |
| **Solution Architect** | Technical design, platform selection | _[X hours/week]_ |
| **Data Scientist/Engineer** | Data preparation, model evaluation | _[X hours/week]_ |
| **Developer/Maker** | Building prototype (Copilot Studio, Power Platform, code) | _[X hours/week]_ |
| **Subject Matter Expert (SME)** | Domain knowledge, validation | _[X hours/week]_ |
| **Security/Compliance Officer** | Responsible AI review, compliance validation | _[X hours/week]_ |
| **End-User Representative** | User testing, feedback | _[X hours/week]_ |

---

### 6. Testing & Validation Plan

#### 6.1 Functional Testing
- [ ] Unit tests for individual components
- [ ] Integration tests for data pipelines
- [ ] End-to-end scenario testing

**Test Cases:** _[Liste av testscenarier, f.eks. "User asks about order status"]_

#### 6.2 Performance Testing
- [ ] Load testing (concurrent users/requests)
- [ ] Latency testing (response times)
- [ ] Throughput testing (requests per second)

#### 6.3 Responsible AI Testing
- [ ] **Fairness Assessment:** Test på diverse brukergrupper
- [ ] **Content Safety:** Test adversarial prompts (jailbreak, harmful content)
- [ ] **Bias Detection:** Evaluate model outputs for bias
- [ ] **Explainability:** Validate that model decisions are understandable

**Tools:**
- Azure AI Foundry evaluation tools
- Azure AI Content Safety
- Responsible AI Dashboard (Azure ML)

#### 6.4 User Acceptance Testing (UAT)
- [ ] Recruit representative users
- [ ] Define UAT scenarios
- [ ] Collect qualitative feedback (surveys, interviews)
- [ ] Measure user satisfaction (NPS, CSAT)

---

### 7. Risk Management

Se [Risk Assessment Template](#risk-assessment-template) for detaljert risikovurdering.

**High-Priority Risks:**
1. _[Risk 1: Description + Mitigation Plan]_
2. _[Risk 2: Description + Mitigation Plan]_
3. _[Risk 3: Description + Mitigation Plan]_

---

### 8. Budget & Resources

**Estimated Costs:**

| Category | Estimated Cost | Notes |
|----------|---------------|-------|
| **Azure Compute** | _[NOK/USD]_ | OpenAI quota, VM SKUs, AML compute |
| **Storage** | _[NOK/USD]_ | Blob Storage, AI Search |
| **Licensing** | _[NOK/USD]_ | Copilot Studio, Power Platform |
| **Personnel** | _[NOK/USD]_ | Team member time (internal/external) |
| **Contingency (20%)** | _[NOK/USD]_ | Buffer for unexpected costs |
| **TOTAL** | _[NOK/USD]_ | |

---

### 9. Go/No-Go Decision Criteria

Ved slutten av POC, evaluer mot disse kriteriene:

- [ ] **Technical Feasibility:** Løsningen fungerer som forventet (>80% success criteria oppfylt)
- [ ] **Business Value:** ROI er positiv, eller verdi er dokumentert
- [ ] **User Acceptance:** Brukere er fornøyde (>70% satisfaction)
- [ ] **Responsible AI:** Ingen kritiske fairness/safety issues
- [ ] **Risk Acceptable:** Identifiserte risikoer kan håndteres
- [ ] **Budget Viable:** Production deployment er innenfor budsjett

**Decision:** _[GO / NO-GO / CONDITIONAL GO (specify conditions)]_

---

## Success Criteria Framework

### Technical KPIs (Generative AI)

| Metric | Definition | Target Range | Measurement Method |
|--------|------------|--------------|-------------------|
| **Groundedness** | % of responses supported by source data | >85% | Azure AI Foundry evaluation |
| **Relevance** | % of responses relevant to user query | >80% | Azure AI Foundry evaluation |
| **Fluency** | % of responses that are coherent and grammatical | >90% | Azure AI Foundry evaluation |
| **Content Safety** | % of harmful content blocked | 100% | Azure AI Content Safety |
| **Response Time** | Average latency (seconds) | <3s (p95) | Application Insights |
| **Throughput** | Requests per second handled | >100 rps | Load testing |
| **Availability** | Uptime during test period | >99% | Azure Monitor |

### Business KPIs

| Metric | Definition | Target | Measurement Method |
|--------|------------|--------|-------------------|
| **Time Saved** | Hours saved per week | _[X hours]_ | Before/after comparison |
| **Cost Reduction** | % reduction in operational costs | _[X%]_ | Financial analysis |
| **User Satisfaction (CSAT)** | Customer satisfaction score (1-5) | >4.0 | Survey |
| **Net Promoter Score (NPS)** | Likelihood to recommend (0-10) | >7.0 | Survey |
| **Task Completion Rate** | % of user tasks successfully completed | >80% | Analytics |
| **Adoption Rate** | % of target users actively using solution | >60% | Usage analytics |

### Responsible AI KPIs

| Metric | Definition | Target | Measurement Method |
|--------|------------|--------|-------------------|
| **Fairness (Demographic Parity)** | Max difference in positive prediction rates across groups | <10% | Responsible AI Dashboard |
| **Bias Detection** | No significant bias detected in outputs | 0 critical issues | Manual review + automated tools |
| **Privacy Compliance** | % of PII correctly handled (removed/anonymized) | 100% | Data audit |
| **Content Safety Pass Rate** | % of responses passing content safety filters | 100% | Azure AI Content Safety |
| **Explainability Score** | % of users who understand AI decisions | >70% | User survey |

---

## Evaluation Rubric

Bruk denne matrisen for å score POC-resultater:

### Technical Performance

| Criterion | Score 1 (Poor) | Score 3 (Fair) | Score 5 (Good) | Score 7 (Excellent) | Score |
|-----------|---------------|----------------|----------------|---------------------|-------|
| **Accuracy/Quality** | <60% | 60-74% | 75-89% | ≥90% | _[X]_ |
| **Performance** | Frequent failures, >5s latency | Occasional failures, 3-5s latency | Stable, 2-3s latency | Highly stable, <2s latency | _[X]_ |
| **Reliability** | <95% uptime | 95-97% uptime | 97-99% uptime | >99% uptime | _[X]_ |
| **Scalability** | Cannot scale beyond POC | Limited scalability | Scales to production | Easily scales | _[X]_ |

**Technical Score:** _[Sum / 28]_ → _[%]_

---

### Business Value

| Criterion | Score 1 (Poor) | Score 3 (Fair) | Score 5 (Good) | Score 7 (Excellent) | Score |
|-----------|---------------|----------------|----------------|---------------------|-------|
| **Efficiency Gains** | <20% improvement | 20-40% | 40-60% | >60% | _[X]_ |
| **User Satisfaction** | <50% satisfied | 50-65% | 65-80% | >80% | _[X]_ |
| **Cost-Effectiveness** | ROI negative | ROI break-even | ROI 1-2x | ROI >2x | _[X]_ |
| **Strategic Fit** | Misaligned | Partially aligned | Well aligned | Critical priority | _[X]_ |

**Business Score:** _[Sum / 28]_ → _[%]_

---

### Responsible AI

| Criterion | Score 1 (Poor) | Score 3 (Fair) | Score 5 (Good) | Score 7 (Excellent) | Score |
|-----------|---------------|----------------|----------------|---------------------|-------|
| **Fairness** | Significant bias issues | Minor bias detected | Fair across groups | Highly fair | _[X]_ |
| **Safety** | Harmful content generated | Moderate safety issues | Safe with minor exceptions | 100% safe | _[X]_ |
| **Privacy** | PII leaks detected | Minor privacy concerns | Privacy compliant | Exceeds compliance | _[X]_ |
| **Transparency** | Opaque, users confused | Somewhat transparent | Transparent | Highly transparent | _[X]_ |

**Responsible AI Score:** _[Sum / 28]_ → _[%]_

---

### Overall POC Score

| Dimension | Weight | Score (%) | Weighted Score |
|-----------|--------|-----------|----------------|
| Technical Performance | 40% | _[X%]_ | _[X]_ |
| Business Value | 40% | _[X%]_ | _[X]_ |
| Responsible AI | 20% | _[X%]_ | _[X]_ |
| **TOTAL** | **100%** | | **_[X%]_** |

**Recommendation:**
- **>80%:** Strong GO — Proceed to production
- **60-80%:** Conditional GO — Address gaps before production
- **<60%:** NO-GO — Re-evaluate or pivot

---

## Platform-Specific Checklists

### Copilot Studio POC Checklist

**Pre-Development:**
- [ ] Define agent scope (which topics/intents)
- [ ] Identify data sources for grounding (SharePoint, Dataverse, APIs)
- [ ] Determine deployment channels (Teams, website, custom)
- [ ] Configure Copilot Studio environment (dev, test, prod)
- [ ] Set up authentication (if required)

**Development:**
- [ ] Build initial topics using conversational design best practices
- [ ] Configure generative orchestration (if using gen AI)
- [ ] Integrate data sources (connections, AI Search)
- [ ] Implement content moderation (Azure AI Content Safety)
- [ ] Test conversation flows with representative users

**Evaluation:**
- [ ] Test intent recognition accuracy
- [ ] Measure conversation abandonment rate
- [ ] Validate grounding accuracy (if using data sources)
- [ ] Test escalation paths (handoff to human)
- [ ] Collect user feedback via surveys

**Governance:**
- [ ] Apply content filters (Azure Policy)
- [ ] Configure security groups (Entra ID)
- [ ] Review compliance (data residency, privacy)
- [ ] Document agent behavior and limitations

---

### Azure AI Foundry POC Checklist

**Pre-Development:**
- [ ] Select foundation model (GPT-4o, GPT-4, custom)
- [ ] Provision Azure OpenAI capacity (region, quota)
- [ ] Define prompt engineering strategy
- [ ] Identify grounding data (if RAG)
- [ ] Set up Azure AI Search (if RAG)

**Development:**
- [ ] Build prompt flow orchestration
- [ ] Implement RAG pipeline (chunking, embedding, retrieval)
- [ ] Configure content safety filters
- [ ] Develop evaluation dataset (test queries + expected outputs)
- [ ] Deploy to pre-production endpoint

**Evaluation:**
- [ ] Run Azure AI Foundry evaluation suite (groundedness, relevance, fluency)
- [ ] Test adversarial prompts (jailbreak attempts)
- [ ] Measure latency and throughput
- [ ] Validate cost per request
- [ ] Collect SME feedback on output quality

**Governance:**
- [ ] Enforce Azure Policy (allowed models, regions)
- [ ] Configure RBAC for deployment
- [ ] Enable monitoring (Application Insights, Azure Monitor)
- [ ] Document model version and configuration

---

### Power Platform AI (AI Builder) POC Checklist

**Pre-Development:**
- [ ] Identify AI Builder capability (document processing, text classification, object detection)
- [ ] Prepare training data (labeled datasets)
- [ ] Validate Power Platform capacity (AI Builder credits)
- [ ] Define integration points (Power Apps, Power Automate)

**Development:**
- [ ] Train AI Builder model
- [ ] Validate model accuracy on test dataset
- [ ] Build Power Automate flow or Power App integration
- [ ] Test end-to-end automation

**Evaluation:**
- [ ] Measure model precision/recall
- [ ] Test on real-world data
- [ ] Validate processing speed
- [ ] Collect user feedback

**Governance:**
- [ ] Configure DLP policies
- [ ] Review data residency
- [ ] Document model performance metrics

---

## Risk Assessment Template

### Risk Identification Matrix

| Risk Category | Risk Description | Likelihood (1-5) | Impact (1-5) | Risk Score (L×I) | Mitigation Plan |
|---------------|------------------|------------------|--------------|------------------|-----------------|
| **Technical** | _[Example: Model accuracy below target]_ | _[X]_ | _[X]_ | _[X]_ | _[Retrain with more data, fine-tune prompts]_ |
| **Data** | _[Example: Insufficient training data]_ | _[X]_ | _[X]_ | _[X]_ | _[Synthetic data generation, expand data sources]_ |
| **Security** | _[Example: PII leakage in outputs]_ | _[X]_ | _[X]_ | _[X]_ | _[Implement PII detection, anonymization]_ |
| **Compliance** | _[Example: GDPR violation]_ | _[X]_ | _[X]_ | _[X]_ | _[Legal review, data residency controls]_ |
| **Organizational** | _[Example: Lack of user adoption]_ | _[X]_ | _[X]_ | _[X]_ | _[Change management, training, communication]_ |
| **Budget** | _[Example: Cost overruns]_ | _[X]_ | _[X]_ | _[X]_ | _[Monitor spending, set cost alerts]_ |
| **Responsible AI** | _[Example: Bias in model outputs]_ | _[X]_ | _[X]_ | _[X]_ | _[Fairness testing, diverse training data]_ |

**Risk Scoring:**
- 1-5: Low risk (monitor)
- 6-10: Medium risk (active mitigation required)
- 11-25: High risk (escalate, consider showstopper)

---

### Common AI POC Risks & Mitigations

#### Technical Risks

**Risk:** Model decay over time (accuracy degrades)
- **Mitigation:** Implement continuous monitoring, plan for retraining cadence

**Risk:** Latency exceeds user expectations
- **Mitigation:** Optimize prompt length, use faster models, implement caching

**Risk:** Integration failures with existing systems
- **Mitigation:** Early integration testing, API contract validation

---

#### Data Risks

**Risk:** Data quality issues (missing, incomplete, biased data)
- **Mitigation:** Data profiling upfront, data cleaning pipelines, diverse data sources

**Risk:** Insufficient data volume for training
- **Mitigation:** Synthetic data generation, transfer learning, start with simpler models

**Risk:** Data access blocked by governance/compliance
- **Mitigation:** Early stakeholder engagement, privacy-preserving techniques (anonymization)

---

#### Security & Compliance Risks

**Risk:** Prompt injection attacks
- **Mitigation:** Input validation, content filtering, prompt engineering defenses

**Risk:** Data residency violations
- **Mitigation:** Use compliant Azure regions, review data flow architecture

**Risk:** Unauthorized data access
- **Mitigation:** RBAC, private endpoints, encryption at rest/in transit

---

#### Organizational Risks

**Risk:** User resistance to AI adoption
- **Mitigation:** Involve users early, transparent communication about AI capabilities/limitations

**Risk:** Insufficient team skills
- **Mitigation:** Training programs, external consultants, phased learning approach

**Risk:** Unclear ownership and accountability
- **Mitigation:** Define RACI matrix, establish AI governance board

---

## Timeline Templates

### 1-Week Sprint POC

**Anbefalt for:** Simple use cases (Copilot Studio med pre-built connectors, basic chatbot)

| Day | Activities | Deliverables |
|-----|------------|--------------|
| **Day 1** | Kickoff, scope definition, environment setup | Approved scope, dev environment ready |
| **Day 2-3** | Build prototype, integrate data sources | Working prototype |
| **Day 4** | Testing (functional, UAT) | Test results, feedback collected |
| **Day 5** | Document findings, prepare recommendation | POC report, go/no-go decision |

**Total Effort:** ~40 person-hours

---

### 2-Week Standard POC

**Anbefalt for:** Moderate complexity (Azure AI Foundry RAG, Copilot Studio med custom topics)

| Week | Activities | Deliverables |
|------|------------|--------------|
| **Week 1** | - Kickoff & planning (Day 1-2)<br>- Data preparation (Day 2-3)<br>- Environment setup (Day 3-4)<br>- Initial prototype build (Day 4-5) | Data ready, dev environment, initial prototype |
| **Week 2** | - Iterate on prototype (Day 1-2)<br>- Testing & validation (Day 3-4)<br>- Documentation & presentation (Day 5) | Validated POC, test results, final report, go/no-go decision |

**Total Effort:** ~80-120 person-hours

---

### 4-Week Extended POC

**Anbefalt for:** Complex use cases (Azure ML model training, multi-agent systems, advanced RAG)

| Week | Phase | Activities | Deliverables |
|------|-------|------------|--------------|
| **Week 1** | **Prepare** | - Kickoff, detailed planning<br>- Data collection & preparation<br>- Infrastructure setup<br>- Team onboarding | Data pipeline ready, infra provisioned, team aligned |
| **Week 2** | **Build** | - Develop core functionality<br>- Model training/fine-tuning<br>- Integration with systems | Working prototype (alpha) |
| **Week 3** | **Evaluate** | - Functional testing<br>- Performance testing<br>- Responsible AI evaluation<br>- User acceptance testing<br>- Iterate based on feedback | Validated prototype (beta), test reports |
| **Week 4** | **Decide** | - Final validation<br>- Documentation (lessons learned, architecture)<br>- Stakeholder presentation<br>- Go/no-go decision | POC final report, production roadmap, decision |

**Total Effort:** ~200-320 person-hours

---

### Timeline Adjustment Factors

Legg til ekstra tid hvis:
- [ ] **Data ikke er klar:** +1-2 uker for data cleaning, labeling
- [ ] **Komplekse integrasjoner:** +1 uke per critical integration
- [ ] **Compliance reviews:** +1-2 uker for legal/security approvals
- [ ] **New team to AI:** +1 uke for onboarding/training
- [ ] **Custom model training:** +2-4 uker for ML model development

**Anbefaling:** Legg til 20-30% buffer for uforutsette utfordringer.

---

## Stakeholder Communication Template

### POC Kickoff Email

**Subject:** [POC Name] - Kickoff & Plan

**To:** Project team, stakeholders

**Body:**

> Vi starter POC for [use case name] med mål om å [brief objective]. POC vil løpe fra [start date] til [end date] ([X uker]).
>
> **Mål:**
> - [Goal 1]
> - [Goal 2]
>
> **Team:**
> - Project Lead: [Name]
> - Solution Architect: [Name]
> - Developer: [Name]
>
> **Neste steg:**
> - [Action 1]
> - [Action 2]
>
> **Beslutningspunkt:** [Date for go/no-go decision]
>
> Spørsmål? Kontakt [Lead].

---

### Weekly Status Update Template

**Subject:** [POC Name] - Week [X] Status

**Progress This Week:**
- [Completed item 1]
- [Completed item 2]

**Blockers/Risks:**
- [Risk 1 + mitigation plan]

**Next Week:**
- [Planned item 1]
- [Planned item 2]

**On Track?** [Yes / No / At Risk]

---

### Final POC Report Template

**Executive Summary:**
- **Objective:** [What we set out to prove]
- **Outcome:** [What we learned/achieved]
- **Recommendation:** [GO / NO-GO / CONDITIONAL GO]

**Technical Results:**
- Accuracy: [X%] (Target: [Y%])
- Performance: [X seconds] (Target: [Y seconds])
- [Other KPIs]

**Business Value:**
- Efficiency gains: [X hours/week saved]
- User satisfaction: [X% CSAT]
- Estimated ROI: [X]

**Responsible AI:**
- Fairness: [Pass/Fail + details]
- Safety: [Pass/Fail + details]
- Privacy: [Pass/Fail + details]

**Risks & Mitigations:**
- [Risk 1 + status]
- [Risk 2 + status]

**Next Steps:**
- If GO: [Production roadmap, timeline, budget]
- If NO-GO: [Reasons, alternative approaches]

**Attachments:**
- Test results
- User feedback summary
- Cost analysis

---

## Go/No-Go Decision Framework

### Decision Criteria Scorecard

| Category | Weight | Pass Threshold | Actual Score | Weighted | Pass? |
|----------|--------|---------------|--------------|----------|-------|
| **Technical Feasibility** | 30% | >75% | _[X%]_ | _[X]_ | _[Y/N]_ |
| **Business Value** | 30% | >70% | _[X%]_ | _[X]_ | _[Y/N]_ |
| **Responsible AI** | 20% | >80% | _[X%]_ | _[X]_ | _[Y/N]_ |
| **User Acceptance** | 10% | >70% | _[X%]_ | _[X]_ | _[Y/N]_ |
| **Risk Management** | 10% | No critical risks | _[X/5 risks mitigated]_ | _[X]_ | _[Y/N]_ |
| **TOTAL** | **100%** | **>75%** | | **_[X%]_** | **_[Y/N]_** |

---

### Decision Paths

#### GO Decision
**Criteria:**
- Overall score >75%
- All critical dimensions pass threshold
- No unmitigated high risks (score >15)
- Stakeholder approval obtained

**Next Steps:**
1. Finalize production architecture
2. Secure production budget
3. Define production roadmap (6-12 months)
4. Establish MLOps/GenAIOps processes
5. Plan change management/training

**Timeline to Production:** _[X weeks/months]_

---

#### CONDITIONAL GO Decision
**Criteria:**
- Overall score 60-75%
- Some dimensions below threshold
- High risks present but mitigatable

**Conditions to Meet:**
- _[Condition 1: e.g., Improve accuracy to 85% before production]_
- _[Condition 2: e.g., Complete security audit]_
- _[Condition 3: e.g., Obtain legal approval for data usage]_

**Re-evaluation Date:** _[Date]_

---

#### NO-GO Decision
**Criteria:**
- Overall score <60%
- Critical dimension failures
- Unmitigatable high risks
- Stakeholder concerns unresolved

**Reasons:**
- _[Reason 1]_
- _[Reason 2]_

**Alternatives:**
1. **Pivot:** Change approach (different platform, simpler use case)
2. **Delay:** Address blockers, re-run POC in [X months]
3. **Cancel:** Not viable, explore non-AI solutions

---

## Example POC Plan

### POC: Customer Support Chatbot (Copilot Studio)

**Executive Summary:**
- **Hensikt:** Automatisere repetitive kundehenvendninger (ordrestatus, returer, leveringsspørsmål) via chatbot i Teams og på web.
- **Varighet:** 2 uker
- **Ressurser:** 3 personer (1 solution architect, 1 developer, 1 SME)
- **Beslutningsdato:** 2025-02-14

---

**Business Case:**

**Problem:** Kundestøtte bruker 40% av tiden (16 timer/uke) på repetitive spørsmål. Gjennomsnittlig responstid er 15 minutter.

**Målsetting:**
- Automatisere 60% av repetitive henvendelser
- Redusere responstid til <2 minutter
- Frigjøre 10 timer/uke for støtteteamet

**Strategic Value:**
- Business Impact: 4/5 (betydelig effektivisering)
- User Value: 5/5 (raskere svar for kunder)
- Innovation: 3/5 (standard chatbot-løsning)
- Strategic Alignment: 4/5 (aligner med AI-strategi)

---

**Technical Scope:**

**AI Maturity:** Level 2 (har litt erfaring med Power Platform, basic AI-forståelse)

**Chosen Solution:** Copilot Studio
- Hvorfor: Low-code, rask utvikling, godt integrert med Teams/Dataverse, møter compliance-krav

**Data Sources:**
1. **Dataverse:** Ordredata (Order Status, Tracking Numbers)
2. **SharePoint:** FAQ-dokumenter, return policies
3. **Customer Service API:** Live order lookup

**Infrastructure:**
- Copilot Studio capacity: 1000 conversations/month
- Azure AI Search: For FAQ grounding
- Dataverse: For order data
- Content Safety: Azure AI Content Safety filters

---

**Success Criteria:**

**Technical:**
- Intent recognition accuracy: >85%
- Response time: <3 seconds
- Availability: >99%
- Content Safety: 100% pass rate

**Business:**
- Automation rate: >60% of test queries handled without human
- User satisfaction: >70% CSAT
- Cost per conversation: <5 NOK

**Responsible AI:**
- No bias in responses across customer demographics
- All PII handled securely
- Transparent AI disclosure to users

---

**Implementation Plan (2 weeks):**

**Week 1:**
- Day 1-2: Setup Copilot Studio environment, define topics (Order Status, Returns, Shipping)
- Day 3-4: Integrate Dataverse + SharePoint, configure gen AI orchestration
- Day 5: Build initial conversation flows

**Week 2:**
- Day 1-2: Test with internal users, iterate on prompts
- Day 3-4: User acceptance testing (10 customer service reps), collect feedback
- Day 5: Document results, prepare go/no-go recommendation

---

**Team:**
- **Project Lead:** Kari Nordmann (10 timer/uke)
- **Solution Architect:** Ola Hansen (15 timer/uke)
- **Developer (Copilot Studio):** Emma Larsen (20 timer/uke)
- **SME (Customer Service):** Per Johansen (5 timer/uke)

---

**Testing Plan:**

**Functional Tests:**
- Test all 3 main topics (Order Status, Returns, Shipping)
- Test escalation to human agent

**Performance:**
- Load test: 50 concurrent conversations
- Latency: Measure p50, p95, p99

**Responsible AI:**
- Test 20 adversarial prompts (jailbreak attempts)
- Validate content filters active

**UAT:**
- 10 customer service reps test for 2 days
- Survey: CSAT, ease of use, accuracy

---

**Risks:**

| Risk | Likelihood | Impact | Score | Mitigation |
|------|-----------|--------|-------|------------|
| Low intent recognition accuracy | 3 | 4 | 12 | Add more training phrases, use gen AI fallback |
| Dataverse integration delays | 2 | 3 | 6 | Start integration early, have mock data ready |
| User resistance (prefer human support) | 2 | 2 | 4 | Change management, involve users early |

---

**Budget:**

| Item | Cost |
|------|------|
| Copilot Studio license (1 month) | 5,000 NOK |
| Azure AI Search (dev tier) | 500 NOK |
| Personnel (80 hours × 1000 NOK/hr) | 80,000 NOK |
| **TOTAL** | **85,500 NOK** |

---

**Go/No-Go Criteria:**

- [ ] Intent accuracy >85%
- [ ] Response time <3s
- [ ] User satisfaction >70%
- [ ] No critical safety issues
- [ ] Budget for production <50,000 NOK/year

**Expected Outcome:** GO (90% confidence based on similar implementations)

---

## Vedlegg: Nyttige Ressurser

### Microsoft Documentation
- [AI Adoption Framework (CAF)](https://learn.microsoft.com/azure/cloud-adoption-framework/scenarios/ai/)
- [Copilot Studio Implementation Guidance](https://learn.microsoft.com/microsoft-copilot-studio/guidance/overview)
- [Azure AI Foundry Evaluation](https://learn.microsoft.com/azure/ai-foundry/concepts/evaluation-evaluators/)
- [Responsible AI Standard](https://www.microsoft.com/ai/responsible-ai)

### Tools
- **Azure AI Foundry:** Model evaluation, deployment
- **Copilot Studio:** Agent development, testing
- **Azure AI Content Safety:** Content moderation
- **Responsible AI Dashboard:** Fairness, bias detection (Azure ML)

### Templates
- [AI Impact Assessment Template](https://www.microsoft.com/ai/tools-practices)
- [Responsible AI Maturity Model](https://www.microsoft.com/research/publication/responsible-ai-maturity-model/)

---

**Sist oppdatert:** 2026-01-XX
**Versjon:** 1.0
**Eier:** AI Architect Plugin