feat: add master notebook library scaffolding and review tooling
Add CLAUDE.md defining the Palladium master notebook conventions and Red Panda Approval criteria, plus a review-notebook slash command for LLM-driven notebook review. Expand .gitignore to block client/engagement documents and generated exports, keeping masters client-clean while allowing text/image sources. Normalize slider widget numeric values from floats to integers in notebook JSON.
This commit is contained in:
184
assessments/CX_AI_Diagnostic/configs/base.yaml
Normal file
184
assessments/CX_AI_Diagnostic/configs/base.yaml
Normal file
@@ -0,0 +1,184 @@
|
||||
# CX AI Advisory Diagnostic — universal config (industry-independent).
|
||||
#
|
||||
# This file is the diagnostic's *_VERBATIM anchor (Mercury Notebook Pattern):
|
||||
# the competency model, level descriptors, and capping heuristic that every
|
||||
# industry overlay extends. Editing wording here is editing the instrument —
|
||||
# do it deliberately, and re-run tests + notebooks afterwards.
|
||||
|
||||
version: "1.0"
|
||||
|
||||
dimensions:
|
||||
- id: strategy_value
|
||||
name: "Strategy & Value"
|
||||
- id: foundations
|
||||
name: "Foundations"
|
||||
- id: delivery
|
||||
name: "Delivery"
|
||||
- id: sustain
|
||||
name: "Sustain"
|
||||
|
||||
competencies:
|
||||
# ── Strategy & Value ─────────────────────────────────────────────────
|
||||
- id: automation_ai_strategy
|
||||
dimension: strategy_value
|
||||
name: "Automation & AI Strategy"
|
||||
description: "Is there a written thesis for why AI, where, and what it changes about the operating model?"
|
||||
failure_vignette: "We're doing AI because the CEO read an article."
|
||||
level_descriptors:
|
||||
1: "No thesis. AI driven by executive impulse or vendor pitch."
|
||||
2: "Aspirational vision, no operating model implications defined."
|
||||
3: "Documented strategy, partial linkage to operating model."
|
||||
4: "Strategy drives portfolio decisions and operating model changes."
|
||||
5: "Strategy is reviewed quarterly; operating model evolves with capability."
|
||||
|
||||
- id: value_realization
|
||||
dimension: strategy_value
|
||||
name: "Value Realization"
|
||||
description: "Are AI benefits defined before investment, measured after go-live, and actually harvested?"
|
||||
failure_vignette: "The chatbot saved us four million dollars — nobody can say where it went."
|
||||
level_descriptors:
|
||||
1: "No benefit definition. Success is anecdote and vendor slideware."
|
||||
2: "Business cases exist pre-investment; nobody measures after go-live."
|
||||
3: "Benefits tracked for flagship initiatives; harvesting is ad hoc."
|
||||
4: "Standard value framework; benefits measured and attributed per initiative."
|
||||
5: "Value realization steers the portfolio: funding follows measured returns."
|
||||
|
||||
- id: executive_alignment
|
||||
dimension: strategy_value
|
||||
name: "Executive Alignment"
|
||||
description: "Do the executives who own budget, operations, and technology pull in the same direction on AI?"
|
||||
failure_vignette: "The CIO and the COO each run their own AI program — neither knows the other's roadmap."
|
||||
level_descriptors:
|
||||
1: "No accountable executive. AI initiatives appear wherever budget leaks."
|
||||
2: "One sponsor evangelizes; peer executives are indifferent or resistant."
|
||||
3: "Named executive owner; cross-functional steering exists on paper."
|
||||
4: "Steering meets and decides; budget and priorities move as one portfolio."
|
||||
5: "AI accountability sits in executive scorecards and compensation."
|
||||
|
||||
# ── Foundations ──────────────────────────────────────────────────────
|
||||
- id: process_discovery
|
||||
dimension: foundations
|
||||
name: "Process Discovery"
|
||||
description: "Do you know, at task level, how customer-facing work actually flows today?"
|
||||
failure_vignette: "We automated the process as documented — it turns out nobody follows it."
|
||||
level_descriptors:
|
||||
1: "Processes undocumented; the knowledge lives in agents' heads."
|
||||
2: "High-level process maps exist — stale and aspirational."
|
||||
3: "Priority journeys mapped at task level with volumes and handle data."
|
||||
4: "Discovery is instrumented (mining, analytics); maps reflect observed work."
|
||||
5: "Continuous process intelligence feeds an automation pipeline."
|
||||
|
||||
- id: data_readiness
|
||||
dimension: foundations
|
||||
name: "Data Readiness"
|
||||
description: "Is the data AI needs — knowledge, interactions, customer context — accessible, clean, and governed?"
|
||||
failure_vignette: "The bot's knowledge base is a SharePoint folder last updated two reorgs ago."
|
||||
level_descriptors:
|
||||
1: "Data siloed and unmanaged; no owner, no quality measures."
|
||||
2: "Key sources identified; access is manual and quality unknown."
|
||||
3: "Priority data consolidated and cleansed for first use cases; stewardship assigned."
|
||||
4: "Governed pipelines feed AI in production; quality is monitored."
|
||||
5: "Data products with SLAs; a new use case onboards in days, not quarters."
|
||||
|
||||
- id: technical_architecture
|
||||
dimension: foundations
|
||||
name: "Technical Architecture"
|
||||
description: "Can your platform stack integrate, orchestrate, and scale AI services safely?"
|
||||
failure_vignette: "Every new bot needs a six-month integration project and its own credentials spreadsheet."
|
||||
level_descriptors:
|
||||
1: "Legacy estate; point-to-point integrations; no API layer."
|
||||
2: "Some APIs exist; each AI effort builds bespoke plumbing."
|
||||
3: "Reference architecture defined; shared integration layer for priority systems."
|
||||
4: "Platform approach: reusable services, identity, and observability across AI workloads."
|
||||
5: "Composable architecture; new AI capability ships on a paved road."
|
||||
|
||||
# ── Delivery ─────────────────────────────────────────────────────────
|
||||
- id: use_case_prioritization
|
||||
dimension: delivery
|
||||
name: "Use Case Prioritization"
|
||||
description: "Is there a managed portfolio that chooses AI work by value and feasibility?"
|
||||
failure_vignette: "We have forty AI ideas on a whiteboard, and the loudest stakeholder goes first."
|
||||
level_descriptors:
|
||||
1: "No pipeline; initiatives start on executive impulse."
|
||||
2: "An idea list exists; no scoring, no sequencing."
|
||||
3: "Value and feasibility scoring; a prioritized backlog is reviewed."
|
||||
4: "Portfolio managed against capacity and dependencies; stop/pivot rules are applied."
|
||||
5: "The portfolio rebalances continuously on measured value and capability growth."
|
||||
|
||||
- id: delivery_capability
|
||||
dimension: delivery
|
||||
name: "Delivery Capability"
|
||||
description: "Can you take an AI use case from concept to production, repeatably?"
|
||||
failure_vignette: "Every pilot succeeds; nothing ever reaches production."
|
||||
level_descriptors:
|
||||
1: "No delivery method for AI; experiments die in the lab."
|
||||
2: "Vendor-led one-off projects; nothing reusable remains."
|
||||
3: "A standard delivery path exists; a few use cases run in production."
|
||||
4: "Product teams ship AI iteratively; reusable components accelerate delivery."
|
||||
5: "Factory model: concept-to-production in weeks, with automated quality gates."
|
||||
|
||||
- id: talent_and_skills
|
||||
dimension: delivery
|
||||
name: "Talent & Skills"
|
||||
description: "Are the skills AI delivery needs — conversation design, prompting, data, MLOps — in the right seats?"
|
||||
failure_vignette: "Our bot team is one hero contractor whose contract ends in March."
|
||||
level_descriptors:
|
||||
1: "No AI-relevant skills in-house; total vendor dependence."
|
||||
2: "Isolated enthusiasts self-teach; no roles or paths defined."
|
||||
3: "Core roles staffed for current initiatives; a training program has started."
|
||||
4: "Skills strategy: career paths, internal academy, knowledge-transfer clauses with vendors."
|
||||
5: "Talent is a differentiator: bench depth, low key-person risk, a magnet for hires."
|
||||
|
||||
# ── Sustain ──────────────────────────────────────────────────────────
|
||||
- id: ai_operations
|
||||
dimension: sustain
|
||||
name: "AI Operations"
|
||||
description: "Once AI is live, who watches it, tunes it, and fixes it — with what telemetry?"
|
||||
failure_vignette: "Containment fell for three weeks before anyone noticed — a menu change had broken the intents."
|
||||
level_descriptors:
|
||||
1: "No monitoring; failures surface as customer complaints."
|
||||
2: "Manual spot checks; tuning happens when someone escalates."
|
||||
3: "Dashboards for containment and accuracy; scheduled tuning cycles."
|
||||
4: "Full observability: drift alerts, feedback loops, a named run team."
|
||||
5: "Self-optimizing operations; automated retraining inside governed guardrails."
|
||||
|
||||
- id: change_adoption
|
||||
dimension: sustain
|
||||
name: "Change & Adoption"
|
||||
description: "Are agents, supervisors, and customers brought along — or does AI happen to them?"
|
||||
failure_vignette: "Agents learned about the copilot from the go-live email — they've been closing it ever since."
|
||||
level_descriptors:
|
||||
1: "No change effort; adoption is assumed."
|
||||
2: "Announcement-and-training-deck change; adoption unmeasured."
|
||||
3: "Structured change program for major rollouts; adoption tracked."
|
||||
4: "Co-design with the front line; champions network; adoption is a launch KPI."
|
||||
5: "Change muscle is institutional; the front line pulls the roadmap forward."
|
||||
|
||||
- id: governance_and_risk
|
||||
dimension: sustain
|
||||
name: "Governance & Risk"
|
||||
description: "Are AI risk, compliance, and ethics governed — at the speed production AI moves?"
|
||||
failure_vignette: "Legal found out about the voice bot when a customer complaint reached the regulator."
|
||||
level_descriptors:
|
||||
1: "No AI governance; risk is handled after incidents."
|
||||
2: "Generic IT policies stretched over AI; approvals ad hoc and slow."
|
||||
3: "AI policy and a review board for high-risk use cases."
|
||||
4: "Risk-tiered governance embedded in delivery; audit trails standard."
|
||||
5: "Governance is an accelerator: pre-approved patterns, continuous compliance."
|
||||
|
||||
# ── Value capping heuristic ────────────────────────────────────────────
|
||||
# Applied to the WEAKEST foundational competency score: the fraction of
|
||||
# theoretical annual value an organization at that level can realistically
|
||||
# capture. All bands are ranges — never point estimates.
|
||||
capping_heuristic:
|
||||
1: {realized_low: 0.00, realized_high: 0.15}
|
||||
2: {realized_low: 0.25, realized_high: 0.40}
|
||||
3: {realized_low: 0.50, realized_high: 0.65}
|
||||
4: {realized_low: 0.65, realized_high: 0.85}
|
||||
5: {realized_low: 0.80, realized_high: 1.00}
|
||||
|
||||
# Which competencies act as "foundational" — their weakness caps everything.
|
||||
foundational_competencies:
|
||||
- process_discovery
|
||||
- data_readiness
|
||||
- technical_architecture
|
||||
62
assessments/CX_AI_Diagnostic/configs/contact_center.yaml
Normal file
62
assessments/CX_AI_Diagnostic/configs/contact_center.yaml
Normal file
@@ -0,0 +1,62 @@
|
||||
# CX AI Advisory Diagnostic — contact-center industry overlay.
|
||||
#
|
||||
# Value-driver ranges are 🟡 placeholder benchmarks pending citation work
|
||||
# (see docs/build_spec_v1.md §12): before running with a real client, back
|
||||
# each range with public sources or "based on N engagements" framing.
|
||||
# `value_formula` strings are documentation of the math implemented in
|
||||
# diaglib/value_math.py (dispatched on `kind`) — they are carried into
|
||||
# exports verbatim, not evaluated.
|
||||
|
||||
extends: base
|
||||
industry: contact_center
|
||||
display_name: "Contact Center"
|
||||
|
||||
value_drivers:
|
||||
- id: deflection_lift
|
||||
name: "Deflection / containment improvement"
|
||||
kind: containment_lift
|
||||
baseline_field: current_containment_rate
|
||||
lift_range_pts_low: 0.15
|
||||
lift_range_pts_high: 0.35
|
||||
value_formula: "annual_contact_volume * lift_pts * blended_cost_per_contact"
|
||||
source: "Public benchmarks; virtual agent maturity studies" # 🟡 placeholder
|
||||
|
||||
- id: aht_reduction
|
||||
name: "Average handle time reduction"
|
||||
kind: aht_reduction
|
||||
baseline_field: average_handle_time_seconds
|
||||
reduction_pct_low: 0.15
|
||||
reduction_pct_high: 0.25
|
||||
value_formula: "annual_contact_volume * (baseline_seconds * reduction_pct) * (blended_cost_per_contact / baseline_seconds)"
|
||||
source: "Agent assist / copilot case data" # 🟡 placeholder
|
||||
|
||||
- id: attrition_reduction
|
||||
name: "Attrition reduction"
|
||||
kind: attrition_reduction
|
||||
baseline_field: annual_attrition_rate
|
||||
reduction_pct_low: 0.10
|
||||
reduction_pct_high: 0.20
|
||||
cost_per_replacement_default: 15000 # 🟡 industry-tunable per engagement
|
||||
value_formula: "agent_headcount * (annual_attrition_rate * reduction_pct) * cost_per_replacement"
|
||||
source: "Job quality / copilot studies" # 🟡 placeholder
|
||||
|
||||
# ── Unlock costs ───────────────────────────────────────────────────────
|
||||
# Rough cost/time ranges per one-level lift, per foundational competency.
|
||||
# 🟡 estimates — sparse is OK for MVP; a missing lift renders as
|
||||
# "cost not configured" in the unlock sequence rather than a guess.
|
||||
unlock_costs:
|
||||
data_readiness:
|
||||
lift_1_to_2: {cost_low: 150000, cost_high: 300000, weeks: 8}
|
||||
lift_2_to_3: {cost_low: 300000, cost_high: 600000, weeks: 12}
|
||||
lift_3_to_4: {cost_low: 400000, cost_high: 800000, weeks: 16}
|
||||
lift_4_to_5: {cost_low: 500000, cost_high: 1000000, weeks: 20}
|
||||
process_discovery:
|
||||
lift_1_to_2: {cost_low: 80000, cost_high: 160000, weeks: 6}
|
||||
lift_2_to_3: {cost_low: 120000, cost_high: 250000, weeks: 8}
|
||||
lift_3_to_4: {cost_low: 150000, cost_high: 300000, weeks: 10}
|
||||
lift_4_to_5: {cost_low: 200000, cost_high: 400000, weeks: 12}
|
||||
technical_architecture:
|
||||
lift_1_to_2: {cost_low: 100000, cost_high: 200000, weeks: 8}
|
||||
lift_2_to_3: {cost_low: 200000, cost_high: 400000, weeks: 10}
|
||||
lift_3_to_4: {cost_low: 250000, cost_high: 500000, weeks: 12}
|
||||
lift_4_to_5: {cost_low: 350000, cost_high: 700000, weeks: 16}
|
||||
14
assessments/CX_AI_Diagnostic/configs/financial_services.yaml
Normal file
14
assessments/CX_AI_Diagnostic/configs/financial_services.yaml
Normal file
@@ -0,0 +1,14 @@
|
||||
# CX AI Advisory Diagnostic — financial-services overlay (STUB, MVP).
|
||||
#
|
||||
# The competency model and capping heuristic come from base.yaml unchanged.
|
||||
# Value drivers and unlock costs are not yet configured for this industry:
|
||||
# selecting it in the notebook scores capability normally but computes no
|
||||
# value-at-stake (an on-stage notice says so). Populate value_drivers and
|
||||
# unlock_costs before using this config with a client.
|
||||
|
||||
extends: base
|
||||
industry: financial_services
|
||||
display_name: "Financial Services (stub)"
|
||||
|
||||
value_drivers: []
|
||||
unlock_costs: {}
|
||||
Reference in New Issue
Block a user