The Integrated 8D AI Solution Engineering Framework: Banking Customer-Service Final Playbook
The 8D AI Solution Engineering Framework turns an unclear AI ambition into a valuable, secure, governed and operational service. For MonGo Bank, it transforms “build a chatbot to cut cost” into a trusted hybrid customer-service capability—and maps every framework from Parts I–VIII into one controlled learning cycle.
1. Purpose of the 8D framework
| # | Stage | Primary question | Core output |
|---|---|---|---|
| 1 | Define | What are we solving and who decides? | Engagement mandate |
| 2 | Discover | What do users, processes and evidence tell us? | Evidence-based problem definition |
| 3 | Diagnose | What causes the problem and what prevents success? | Root-cause and readiness assessment |
| 4 | Design | What business, operating and technical solution should exist? | Target solution design |
| 5 | De-risk | What could cause harm, failure or non-compliance? | Controlled risk position |
| 6 | Demonstrate | Does the solution work under realistic conditions? | Evaluation and pilot evidence |
| 7 | Decide | Should we fund, scale, redesign, restrict or stop? | Investment and release decision |
| 8 | Deliver | Can the organisation operate, adopt and improve it? | Sustainable production service |
Activities overlap: discovery reveals risks; evaluation changes architecture; commercial analysis changes scope; production monitoring restarts diagnosis; regulation forces redesign. Operate as a controlled learning cycle.
2. Integrated MonGo scenario
Original request: build a generative AI chatbot to reduce customer-service cost.
8D objective: create a trusted hybrid AI service that helps customers and employees resolve routine banking requests quickly, while preserving human control for sensitive, regulated and high-impact situations.
Includes: agent knowledge assist; source-grounded drafts; summarisation; intelligent routing; authenticated payment/card status; human escalation; selected reversible actions after confirmation.
Excludes: autonomous lending; final complaint adjudication; fraud liability; unrestricted financial advice; irreversible account changes; cross-customer data access.
Series map:
| Part | Focus | Primary 8D stages |
|---|---|---|
| I Strategy & Discovery | Ambition, frameworks | Define, Discover |
| II Readiness & Prioritisation | Maturity, scoring | Diagnose, Decide |
| III Commercial Case | TCO, NPV, benefits | Decide |
| IV Architecture & Ops Model | TOM, C4, LLMOps | Design |
| V Engineering & Evaluation | RAG, pilots, PRR | Demonstrate |
| VI Responsible AI & Security | RMF, OWASP, DPIA | De-risk |
| VII Delivery & Operations | Adoption, ITIL, SRE | Deliver |
| VIII Portfolio & Scaling | LPM, CoE, FinOps | Deliver (scale) |
Part I — DEFINE
Purpose: problem, outcome, scope, ownership, governance, assumptions, risks, success criteria—before uncontrolled experimentation.
Frameworks: Project Charter, AI North Star, MECE, RACI, RAPID, RAID, Stakeholder Influence–Interest, OKRs, Problem Statement Canvas, Intended-Purpose Statement.
MonGo: from “build a chatbot” to fragmented knowledge, disconnected processes, poor status visibility and weak continuity. Outcomes: successful safe resolution, lower effort, employee productivity, human support, consistency.
Artefacts: charter, problem statement, North Star, scope/exclusions, outcomes, RACI/RAPID/RAID, stakeholder map, initial risk class, intended/prohibited use, high-level roadmap.
Gate: problem without assumed solution; named business owner; explicit exclusions; measurable success; high-risk uses identified; decision rights clear; sponsor accepts mandate.
Part II — DISCOVER
Purpose: replace assumptions with evidence—customers, employees, processes, data, systems, pain points, behaviour, constraints.
Frameworks: Design Thinking, Double Diamond, VoC, JTBD, Journey Mapping, Service Blueprinting, SIPOC, VSM, BPMN, Process Mining, Assumption Mapping, Opportunity Solution Tree.
MonGo evidence: dislike of repetition; want human access; confusing payment terms; distrust generic chatbots; 95s search; 18% transfers; 12% recontact. Core problem is not “no chatbot.”
Artefacts: VoC, personas, JTBD, journeys, blueprints, SIPOC, VSM, process mining, pain-point registers, assumption map, OST, evidence repository.
Gate: representative users; observed/analysed processes; evidenced pain points; needs separated from technology; documented assumptions; first target journey defined.
Part III — DIAGNOSE
Purpose: root causes, readiness gaps, maturity, constraints, dependencies, risks, barriers to value.
Frameworks: Five Whys, Fishbone, Problem Tree, Pareto; Enterprise AI Readiness, capability/data/LLMOps/RAI/cyber/change/ops/agentic maturity; SWOT/TOWS, PESTLE, Porter, Value Chain, Capability-Based Planning.
Root cause example: inconsistent pending-payment answers → weak knowledge ownership—not “add GenAI” alone. Fix ownership, consolidation, metadata, review dates, versioning, retrieval controls.
Readiness: knowledge/eval/LLMOps/governance/AI security/product ownership lag; general cyber strong. Ready for controlled agent-assist pilot; not broad autonomous CS.
Artefacts: root-cause analysis, readiness heatmap, data/knowledge assessments, constraint register, change/ops readiness, risk/dependency map, capability gaps, remediation roadmap.
Gate: evidenced root causes; AI vs non-AI causes separated; critical gaps funded/planned; high-risk assumptions have tests; clarity on what not to automate.
Part IV — DESIGN
Purpose: future CX, process, operating model, data/app/tech architecture, AI design, governance, human oversight—a coherent target solution.
Frameworks: Strategy Choice Cascade, Playing to Win, Three Horizons, Value-Driver Tree, BMC, OMC, Wardley; TOM, AI ops hub-and-spoke, CoE/C4E, Three Lines; TOGAF, ArchiMate, C4, DDD, Event Storming, API-first, EDA, CAF, Well-Architected, Zero Trust, Data Mesh/Fabric, lakehouse/medallion, ADRs; CRISP-DM, ML/Agent lifecycles, RAG, model routing, HITL, MLOps/LLMOps/AgentOps.
Design principle: deterministic systems for banking facts; LMs for interpretation, explanation and summarisation. Status from API → policy from approved knowledge → LM explains → validator checks → human available.
Flow: authenticate → orchestrate → classify → policy rules → retrieve → tools → model gateway → structured response → validate → respond/escalate → log → telemetry.
Gate: coherent journey; named business/service owners; AI only where appropriate; SoR responsibilities explicit; meaningful oversight; fallbacks; security boundaries; trade-offs understood; build–buy–partner justified.
Part V — DE-RISK
Purpose: Responsible AI, regulatory, privacy, security, supplier, operational, customer-harm and financial risk—early and continuous.
Frameworks: NIST AI RMF, ISO 42001/23894/42005, EU AI Act, AIA, control library, cards, oversight, Assurance Case; NIST CSF, ISO 27001, Zero Trust, STRIDE, ATLAS, OWASP LLM, Secure AI SDLC; Privacy by Design, DPIA; TPRM, AI BOM, concentration risk, exit plans.
Examples: wrong pending-payment explanation → SoR API, normalisation, grounding, validation, citations, escalation, monitoring. Prompt-injection cross-customer access → session identity, ownership checks, scoped tokens, deny-by-default, redaction, immutable logs.
Gate: intended/prohibited uses; material harms assessed; legal class considered; DPIA/security complete where required; effective oversight; residual risk owned; kill switch and IR; supportable Assurance Case.
Part VI — DEMONSTRATE
Purpose: prove the complete system under realistic conditions—not demo fluency.
Frameworks: PoC, prototype, MVP, pilot; golden datasets; LLM/RAG/agent evaluation; offline/online/human eval; A/B, shadow, champion–challenger; adversarial/red team; regression; independent validation; PRR.
Golden set: standard, ambiguous, misspell, multi-intent, tool failure, complaint, vulnerability, fraud, human request, injection, conflicting knowledge.
Pilot: AHT 8.3→7.4 min; search 93→31s; FCR 69%→76%; policy error 2.8%→1.4%; CSAT 72%→78%; adoption 82%—plus 14% overrides feeding the backlog.
Gate: representative datasets; safety thresholds; escalation quality; security tests; user acceptance; ops support tested; pilot supports business case; limitations documented; rollback works.
Part VII — DECIDE
Purpose: proceed / proceed with conditions / redesign / restrict / pause / scale / stop / retire—beyond model scores.
Frameworks: DVF, Value–Feasibility–Risk, weighted scoring, portfolio matrix, WSJF, RICE, Cost of Delay, risk-adjusted value; Business Case, Five Case, TCO, ROI, NPV, IRR, payback, break-even, sensitivity, scenarios, Monte Carlo, real options, benefits dependency/realisation; RAPID, Decision Log, Stage-Gate, Investment/Design/Risk committees.
Commercial headline: ~$47M benefit / $23.1M TCO / 103.5% ROI / 2.2-year payback / 78% P(positive NPV)—still contingent on groundedness, critical errors, complaints, escalation, adoption, resilience and knowledge quality.
Proceed now: agent knowledge, summarisation, citations, intent. After enablers: payment/card status, routing. Research: vulnerability, fraud assist, agentic orchestration. Do not automate: complaint outcomes, fraud liability, creditworthiness, account closure, unrestricted advice.
Gate: measurable value; full lifecycle cost; cash vs capacity; explicit residual risk; named benefit owners; ops ownership; funded dependencies; stop criteria; documented authority.
Part VIII — DELIVER
Purpose: reliable, adopted, continuously improving service—product delivery, change, training, release, ops, reliability, benefits, scaling, retirement.
Frameworks: Product Operating Model, Agile/Scrum/Kanban, Dual-Track, Stage-Gate, Lean Startup, DevOps/DevSecOps, CI/CD, progressive delivery, flags; Change Impact, 7S, Kotter, ADKAR, TNA, TAM, COM-B, champions, CoPs, Kirkpatrick; ITIL 4, SRE, SLIs/SLOs, error budgets, IR/problem/change/KM, observability, BCP/DR, FinOps; Benefits Realisation, LPM, Three Horizons, enterprise AI ops, CoE/C4E, platform, Scaling Readiness, Continuous Assurance, retirement.
Rollout: Foundations → Employee pilot (100 agents) → Employee scale → Customer pilot (5%) → Customer scale → Controlled actions (freeze/callback/case with confirmation).
Scale gate: persistent ownership; effective (not merely high) adoption; stable SLOs; tested IR; realised benefits; acceptable CX; sustainable cost; risk in appetite; continuous assurance running.
12. VALUE quality gate
Every major deliverable: Valuable · Actionable · Logical · Understandable · Executable.
Fails: “Deploy the largest LM to improve CS.”
Passes: “Use deterministic payment APIs, hybrid retrieval and a medium LM for explanations; reserve larger models for complex employee summarisation—lower cost while staying above evaluation thresholds.”
13. Integrated stage gates
| Gate | Decision | Required evidence |
|---|---|---|
| 1 | Approve discovery | Charter, sponsor, scope, initial risk |
| 2 | Approve diagnosis | User/process evidence, assumptions |
| 3 | Approve design | Readiness, target journey, architecture |
| 4 | Approve experiment | Data, controls, eval plan, supplier approval |
| 5 | Approve pilot | Offline eval, threat model, oversight, ops |
| 6 | Approve production | Assurance Case, DPIA, monitoring, support, risk acceptance |
| 7 | Approve scale | Pilot benefits, stable risk, cost, adoption |
| 8 | Continue or retire | Strategic value, quality, risk, cost, ownership |
14. Framework selection guide
| Decision need | Start with |
|---|---|
| Problem unclear | Charter, MECE, Design Thinking, Double Diamond, JTBD, Five Whys |
| Weak CX | VoC, Journey, Blueprint, TAM, COM-B |
| Operational inefficiency | SIPOC, VSM, BPMN, Process Mining, Fishbone, Value-Driver Tree |
| Organisation not ready | Readiness, maturity, data, LLMOps, change, ops readiness |
| Prioritise use cases | DVF, Value–Feasibility–Risk, weighted scoring, portfolio matrix, WSJF |
| Justify investment | Five Case, TCO, ROI, NPV, payback, sensitivity, benefits network |
| Design architecture | TOGAF, ArchiMate, C4, DDD, Event Storming, API-first, Well-Architected, Zero Trust |
| Engineer GenAI | RAG, prompts, routing, LLMOps, golden datasets, LLM/RAG eval, HITL |
| Agent takes actions | Agent Lifecycle, AgentOps, tool registry, least privilege, trajectory eval, kill switch |
| Governance evidence | AI RMF, ISO 42001/23894/42005, AIA, DPIA, System Card, Assurance Case |
| Security | CSF, STRIDE, ATLAS, OWASP LLM, Zero Trust, Secure AI SDLC, AI BOM |
| Weak adoption | ADKAR, Kotter, 7S, TAM, COM-B, Change Impact, champions, TNA |
| Scale | LPM, Three Horizons, AI ops model, CoE/C4E, platform, FinOps, Scaling Readiness, Continuous Assurance |
15–16. RACI and RAPID
| Activity | Sponsor | Business owner | Product owner | AI eng | Risk/security | Ops | Finance |
|---|---|---|---|---|---|---|---|
| Approve problem/scope | A | R | C | C | C | I | C |
| Conduct discovery | I | A | R | C | C | C | I |
| Assess readiness | I | A | R | R | R | R | C |
| Design solution | I | A | R | R | C | C | I |
| Approve architecture | I | C | C | R | A/C | C | I |
| Approve risk position | I | C | C | C | A/R | C | I |
| Build and evaluate | I | C | A | R | C | C | I |
| Approve pilot / production | A | R | R | C | C/R | C/R | C |
| Operate service | I | A | R | C | C | R | I |
| Realise benefits | I | A/R | R | C | I | C | C |
| Approve scale / retire | A | R | R/C | C | C | C/R | R/C |
Card-freeze production: Recommend AI Product Director · Agree Payments Risk, Cyber, Service Ops · Perform AI Engineering + Card Services · Input CS, Legal, Research · Decide Digital Banking Executive Sponsor.
17–18. Workplan and consulting workstreams
| Phase | Duration | Focus |
|---|---|---|
| Define | 2–4 weeks | Charter, scope, measures, risk, governance |
| Discover | 4–8 weeks | Research, process, journeys, data, assumptions |
| Diagnose | 4–6 weeks | Root cause, readiness, gaps, prioritisation |
| Design | 6–12 weeks | Journey, TOM, architecture, AI, oversight, vendors |
| De-risk | Parallel | RAI, legal, privacy, security, assurance |
| Demonstrate | 8–16 weeks | PoC, eval, red team, employee/customer pilots |
| Decide | 2–4 weeks / gate | Business case, risk, investment, production, scale |
| Deliver | Continuous | Release, training, ops, benefits, improve, retire |
Seven workstreams: Strategy & value · Customer & service design · Data & knowledge · Architecture & engineering · RAI/security/privacy · Operating model & change · Delivery & operations.
19. Executive deliverables
AI strategy · Opportunity portfolio · Transformation roadmap · Business Case (Five Case + TCO/ROI/NPV) · Target Operating Model · Architecture decision pack · Responsible AI and assurance pack · Scale decision paper.
20–22. ConsultAI Lab catalogue and selection rules
Prioritise canvases that produce a decision or artefact. Full catalogues by stage: Define (Charter, North Star, RACI, RAID…) · Discover (JTBD, Journey, SIPOC, Five Whys…) · Diagnose (Readiness, maturity heatmaps…) · Design (Cascade, C4, RAG Design, Tool & Permission…) · De-risk (AI RMF, STRIDE, OWASP, cards, Assurance Case…) · Demonstrate (Golden Dataset Planner, eval scorecards, Pilot Design, PRR…) · Decide (DVF, TCO/ROI/NPV, Decision Paper, Stage-Gate…) · Deliver (Roadmap, ADKAR, SLOs, Adoption/Benefits dashboards, Retirement Checklist…).
Guided notes (not full canvases) for TOGAF, ArchiMate, DDD, ITIL, SRE, FinOps, LLMOps, AgentOps, ISO standards, ATLAS, TAM, 7S, Kotter, LPM, sales frameworks.
Example sequences:
- Unclear opportunity: Problem Statement → MECE → JTBD → Five Whys → AI Canvas → DVF
- Customer-service AI: Journey → Blueprint → SIPOC → VSM → Readiness → RAG Design → Oversight → Value–Feasibility–Risk → Business Case → PRR
- Agentic AI: Purpose → Agentic Readiness → Tools/Permissions → STRIDE → AI RMF → Oversight → Agent Eval → Assurance Case → PRR
- AI strategy: North Star → Cascade → Value Chain → Capability Map → Three Horizons → Portfolio → Operating Model → Benefits Roadmap
23. Minimum artefact map
| Stage | Minimum artefacts |
|---|---|
| Define | Charter, North Star, scope, RACI, RAID |
| Discover | Customer evidence, journey, blueprint, process map |
| Diagnose | Root causes, readiness, capability gaps, assumptions |
| Design | Future journey, operating model, architecture, AI design |
| De-risk | Risk assessment, DPIA, threat model, controls, assurance |
| Demonstrate | Golden dataset, evaluation, red team, pilot evidence |
| Decide | Business Case, scorecard, risk acceptance, decision paper |
| Deliver | Roadmap, training, ops, adoption, benefits, monitoring |
24–26. Narrative, principles, definition
MonGo needed better knowledge ownership, process redesign, secure integration, controlled generation, escalation, evaluation, monitoring, adoption and benefits ownership—not a chatbot. The result is a hybrid customer-service operating capability.
- Begin with the outcome, not the model.
- Do not automate a broken process without diagnosing it.
- Separate deterministic facts from generative explanations.
- Treat data and knowledge quality as product capabilities.
- Test the riskiest assumptions first.
- Use risk to determine governance intensity.
- Evaluate the complete system, not only the model.
- Design meaningful human oversight.
- Include full lifecycle cost.
- Make benefits someone’s responsibility.
- Release progressively and preserve rollback.
- Treat AI as a persistent product and service.
- Build reusable platforms without centralising all business ownership.
- Measure customer, business, technical and risk outcomes together.
- Stop or retire AI when value, ownership or risk is no longer acceptable.
Definition: End-to-end AI solution engineering is the disciplined conversion of a business or customer problem into a valuable, feasible, secure, responsible and operable AI-enabled service through evidence-based discovery, architecture, engineering, governance, evaluation, commercial decision-making, adoption and continuous improvement.
The AI solution engineer connects strategy, customers, processes, data, models, architecture, security, regulation, commercial value, operating models, people, delivery and operations. The goal is not the most sophisticated system—it is the most appropriate system the organisation can trust, fund, operate, govern, improve and stop when necessary.
Discussion
Comments
Share feedback or questions about this page. No account required.
Loading comments…