==================================================
 STORYGEN AI — STORY EXPORT
==================================================
Story ID:           26
Title:              Test_AF_v2 (hybrid)
Owner:              Ang Chwee Geok Karen - Digital Innovation Consultant <karen.ang@educlaas.com>
App Type:           Agentic AI App
Input Type:         file
Status:             features_generated
Source File:        PIL_function_spec_procodevslowcode_nocode_29Apr2026.pdf
Created:            2026-04-29 08:21:09 UTC
Updated:            2026-04-29 08:38:10 UTC
Features Generated: 2026-04-29 08:38:10 UTC
Total Clusters:     8
Total Features:     20

--- ORIGINAL INPUT ---
Index
PIL's Agentic Project 
Scope
PIL Original Problem Statement
Feature Cluster 
(Master Catalogue)
Feature Name 
(Master Catalogue)
Description Actors/Users Expected Outcome
Human-in-the-loop (role & 
action)
Clarification Needed
Recommendation / Next 
Action
MoSCoW 
Priority
Potential 
MVP
6-12 Month 
Horizon Tag
Recommended 
Approach
Why
Comments (Angela)
1 Automated 
Workflow for 
Submission of AFS to 
GFRA/CAC
The current AFS submission 
process lacks a standardized 
workflow and centralized tracking, 
resulting in limited visibility, 
unclear accountability, and 
increased risk of late or missed 
submissions. Manual coordination 
and follow-ups also weaken 
auditability and compliance 
oversight.
Financial Close & 
Reporting
AFS Submission 
Agent
Standardises and tracks AFS 
submission end-to-end by 
capturing submission triggers, 
validating required packs, 
routing reviews, monitoring 
status and logging approvals 
through a governed workflow.  
Financial Reporting 
team, CAC, 
Controllership.  
AFS submissions become 
visible, standardised and 
traceable, reducing late or 
incomplete submissions and 
improving accountability.  
CAC / controllership reviewer 
approves submissions and 
resolves late or incomplete 
cases.
Confirm whether scope is 
only 
workflow/orchestration or 
also includes intelligence 
checks on completeness, 
anomalies, and submission 
quality.
Keep as Financial Close & 
Reporting. Position as 
workflow-led with 
optional intelligence 
checks for completeness, 
lateness risk, and reviewer 
prioritisation.
Must have Yes 0-6 months / 
Wave 1
Low code / no code 
first
Workflow-centric: task routing, 
reminders, submission tracking, 
approvals, escalations, and status 
visibility are strong fits for Power 
Automate, while Copilot/virtual 
agent can guide users on submission 
steps and FAQs, and Power BI can 
provide submission dashboards.
Referring to the column of Expected Outcome, 
1. Visible - does it mean to control the timeliness of the submission? What about 
version controls or revision that were update after first submission? 
2. Standardisation - what is the definition of standardisation - standardise in term of 
the definition of the account mapping, standardise format etc? How are these AFS 
prepared, from the Oracle GFS and CAC? What format?
3. Incomplete - which are the field that will define incomplete? 
4. Does it also require Quick Dashboard numbers consolidated to provide quick review 
and variance to enhance accuracy of submission?
2 Automated 
Prepayments 
Computations
Prepayments calculations are 
currently performed manually. 
There is high risk of formula 
errors, incorrect amortisation 
periods, and inconsistent 
assumptions. The manual process 
creates key-person dependency 
and a weak audit trail.
Financial Close & 
Reporting
Prepayments 
Computation Agent
Automates monthly 
prepayment amortisation and 
recognition by classifying 
prepayment items, computing 
schedules by policy, preparing 
journal proposals and routing 
exceptions for review.  
GL / Record-to-
Report 
accountants.  
Prepayment calculations 
become faster, more 
consistent and auditable, 
with lower spreadsheet and 
formula risk.  
R2R accountant reviews 
exceptions and approves 
prepayment journals before 
posting.
Clarify prepaid asset types 
in scope (e.g. subscriptions, 
insurance, rent), required 
validation rules, whether a 
workbench is needed, and 
whether Oracle GPS/GFS 
already supports 
amortisation schedules.
Keep as Financial Close & 
Reporting for PIL, but 
explicitly define policy 
rules, schedule logic, ERP 
touchpoints, and 
exception handling. Add 
ERP-native capability 
check.
Must have Yes 0-6 months / 
Wave 1
Pro-code core + low-
code wrapper
Prepayment schedules, amortisation 
logic, exception handling, and 
accounting-rule consistency are 
calculation-heavy and audit-sensitive, so 
the computation engine should be 
engineered in pro-code; Power 
Automate can trigger runs and 
approvals, Copilot can explain 
outcomes, and Power BI can expose 
schedules and exceptions. 
Need to clarify:
1. On vendor invoices, how is the period to amortise is captured? When is the start 
date? 
2. Are there fields to capture the classifications of such prepaid expense? 
3. Are all amortisation straight line or other methods eg reducing balance etc?
4. What are the exceptions that will arise that need to route for review?
5. Amortised expenses are offset against invoice in the prepayment account to reflect 
the outstanding yet to amortise prepayment for audit?
3 Automated GFS AP 
Payment Review
The AP payments review process 
is heavily manual and sample-
based, requiring the team to 
manually open each invoice to 
verify bank details. This limits 
coverage and increases the risk of 
errors or missed issues before 
execution.
AP Controls & 
Payments
AP Payment Review 
Agent
Reviews GFS AP payment 
proposals before execution by 
extracting vendor and bank 
details, comparing critical 
fields, flagging mismatches and 
prioritising exceptions for 
human review without 
executing payments directly.  
AP team, payment 
control reviewers.  
Payment review coverage 
expands beyond manual 
sampling, reducing bank-
detail error risk and 
improving pre-payment 
control traceability.  
AP payment controller 
validates flagged payments and 
confirms release, hold, or 
follow-up.
Confirm critical payment-
risk scenarios, what fields 
must be matched, how 
split payments are handled, 
and which exception types 
require reviewer decision.
Keep under AP Controls & 
Payments. Narrow MVP to 
pre-payment review of 
vendor/bank detail 
mismatches and high-risk 
exceptions, then expand 
to more scenarios later.
Must have Yes 0-6 months / 
Wave 1
Hybrid, leaning pro-
code
Bank/vendor master validation, 
duplicate detection, rule scoring, or risk 
checks before payment, the control 
logic should be pro-code; Power 
Automate is suitable for review 
workflow and evidence capture, 
while Power BI supports exception/risk 
reporting and Copilot supports reviewer 
Q&A.
Need to clarify:
1. Where are the bank details of vendors captured? Are there different bank accounts 
for a single vendor?
2. What are the critical fields that they are referring to?
3. What are the criteria on the prioritising requirement to consider?
4 AP Payments 
Dashboard
AP payment information is 
currently spread across multiple 
systems and reports, with limited 
consolidated visibility across 
entities. Finance relies on manual 
extraction and tracking to 
determine payments made to 
date and outstanding payables.
AP Controls & 
Payments
Payments Visibility 
Agent
Aggregates AP status feeds 
and payment files to provide a 
consolidated view of paid, 
outstanding, overdue and 
upcoming AP positions across 
entities through dashboards, 
alerts and drill-through views.  
AP finance leads, 
entity finance 
managers, 
Treasury.  
Finance gains a single, timely 
view of AP liabilities and 
payment status, improving 
monitoring, reporting and 
cash-planning decisions.  
AP lead or treasury reviewer 
investigates overdue or 
exception items surfaced in the 
dashboard.
Clarify whether MVP is 
dashboard-only or includes 
alerts and case 
management. Confirm 
source systems, frequency, 
entity coverage, and 
required due-date / 
overdue logic.
Keep under AP Controls & 
Payments. Start with one-
entity sample and a 
dashboard-led MVP, then 
scale with pro-code 
ingestion for multi-source 
/ multi-entity rollout.
Must have Yes 0-6 months / 
Wave 1
Low code / no code 
if data is already 
accessible; 
otherwise hybrid
If source systems can already feed a 
usable data model, Power BI is ideal for 
payment status visibility and Power 
Automate can refresh/alert; but if data 
must be stitched from multiple 
fragmented systems with complex 
integration and reconciliation rules, the 
integration layer should be pro-code. 
No comments, looks straight forward. So show them the Cluster view
5 Automated Lease 
Schedule 
Computation
Lease schedule computations are 
highly manual and spreadsheet-
driven, requiring significant effort 
to extract contract details, 
compute lease liabilities and right-
of-use assets, and maintain 
schedules over time.
Financial Close & 
Reporting
Lease Accounting 
Agent
Computes lease liabilities, ROU 
assets and schedules by 
ingesting lease terms, 
identifying amendments, 
applying policy rules and 
generating postings for review 
through a lease accounting 
cockpit.  
Lease accounting 
team, 
Controllership.  
Lease schedules and 
postings are produced more 
accurately and consistently, 
reducing manual effort and 
reporting risk.  
Lease accountant reviews 
schedule exceptions, 
amendments, and posting 
proposals before submission.
Confirm whether PIL 
already has a lease engine 
or if this is entirely 
spreadsheet-based. Clarify 
amendment handling, 
discount-rate assumptions, 
and posting integration.
Keep as Financial Close & 
Reporting. Treat as a 
schedule-computation 
and controlled-posting 
capability similar to 
prepayments, but with 
lease-specific policy logic.
Should have Yes 6-12 months / 
Wave 2
1. How are amendments tracked in the system? Does it provide update prompt from 
Oracle?
2. What are the policy rules? Are there different criteria for different rules?
6 Capital Accounting 
Dashboard
Capital accounting data is highly 
fragmented across sources. 
Significant manual effort is 
required to extract, validate, and 
consolidate data to obtain a 
complete view of capital assets, 
resulting in slow reporting and 
higher inconsistency risk.
Financial Close & 
Reporting
Capital Accounting 
Insight Agent
Consolidates asset, CIP and 
project data, performs 
integrity checks and presents 
review-ready capital views and 
exception queues for 
controllers.  
Capital accounting 
team, project 
controllers, 
finance managers.  
Capital accounting obtains a 
more complete and reliable 
view of balances and 
movements with less 
manual consolidation.  
Capital accountant or project 
controller reviews integrity 
breaks and resolves asset / CIP 
issues.
Clarify whether value is 
mainly dashboard visibility, 
data integrity checks, or 
journal / schedule support. 
Confirm sources for assets, 
CIP, and projects.
Keep as Financial Close & 
Reporting. Position as a 
review and exception 
dashboard first, with 
reusable validation 
patterns from 
prepayments / close 
review.
Should have Yes 6-12 months / 
Wave 2
1. How many systems sources that these data points from?
2. What is required to validate?
3. CIP (construction in progress) and Project - are these in Percentage of completion or 
build-up cost? Does it needs to compare to budget?
7 Automated Monthly 
SOAs to Customers 
Monthly SOAs are manually 
downloaded for each customer 
and emailed individually. This 
creates high manual effort during 
month-end closing and risk of 
incorrect customer selection or 
missed / delayed SOA delivery.
AR & Cash 
Application
SOA Dispatch 
Agent
Automates the generation, 
validation, dispatch and 
delivery tracking of monthly 
Statements of Account to 
customers through approved 
channels.  
AR team, 
customer service 
finance support.  
SOAs are delivered more 
accurately and on time, 
reducing manual month-end 
effort and communication 
errors.  
AR or customer finance 
support handles failed sends, 
invalid contacts, and resend 
decisions.
Confirm channel, schedule, 
customer-contact 
validation rules, bounce / 
failure handling, and 
whether approvals are 
required before send.
Keep under AR & Cash 
Application. Position as a 
workflow automation 
candidate with relatively 
fast time-to-value.
Must have Yes 0-6 months / 
Wave 1
Low code / no code 
first
Scheduled extraction, document 
dispatch, email delivery, status logging, 
and follow-up reminders are 
classic Power Automate use 
cases; Copilot can support 
customer/self-service queries, 
and Power BI can track dispatch 
timeliness and failure rates
No comments, looks straight forward. So show them the Cluster view
8 Automated Bank 
receipt classification 
(Trade vs Non-Trade)  
 
Bank statements are downloaded 
regularly and reviewed manually. 
Credit transactions require manual 
filtering and AR vs non-AR 
determination, creating high effort 
and misclassification risk.
AR & Cash 
Application
Bank Receipt 
Classification Agent
Ingests bank statements, 
classifies incoming credits as 
trade or non-trade using rules 
and remittance patterns, and 
routes ambiguous items for 
review before cash-application 
handover.  
Cash application 
team, AR, GL team.  
Receipt classification 
becomes faster and more 
consistent, reducing delays 
and misclassification risk in 
AR and GL.  
AR / GL reviewer confirms 
ambiguous receipts before 
cash-application handover.
Clarify classification rules 
for trade vs non-trade, 
handoff to GL, tolerance for 
ambiguous items, and 
whether bank recon 
overlap exists.
Keep under AR & Cash 
Application. Position as a 
classification and review 
queue that can later 
extend into Advanced 
Cash Application.
Should have Yes 6-12 months / 
Wave 2
1. Does Oracle perform the bank reconciliation? So the starting is from bank 
reconciliation or bank sttmt?
2. Where and how does the data on Trade and non-Trade receivables defined? 
3. to clarify remittance patterns

9Automated GFS data 
reconciliation for Tax 
Reporting
Manual adjustments and 
classifications of GFS output are 
required for tax reporting. This 
creates risk of delayed 
identification of errors, 
misclassifications, and operational 
inefficiencies, with increased 
scrutiny expected from IRAS.
Tax & Compliance Tax Reconciliation 
Agent
Pulls GFS outputs, applies tax 
mapping logic, identifies 
variances and unsupported 
adjustments, produces 
reconciliation evidence and 
routes unresolved breaks to 
tax reviewers.  
Group Tax, finance 
reporting, 
Singapore tax 
compliance team.  
Tax reporting becomes more 
standardised, auditable and 
timely, with lower 
misclassification and 
compliance risk.  
Group Tax reviewer 
investigates breaks and signs 
off reconciled outputs and 
evidence.
Confirm tax mapping logic, 
data sources, adjustment 
categories, reviewer 
workflow, and audit-
evidence requirements for 
Singapore entities.
Keep under Tax & 
Compliance. Position as a 
high-value reconciliation 
and evidence-generation 
use case with strong 
compliance justification.
Should have Yes 6-12 months / 
Wave 2
Are variances and unsupported adjustments referring to the same? If not, what's the 
difference.
10	Treasury & Liquidity Treasury 
Intelligence Agents
Provide advisory insights on 
cash positioning, FX exposure 
and short-term liquidity 
forecasting using treasury and 
ERP data feeds.  
Treasury, CFO, 
Finance 
leadership.  
Treasury gains earlier 
warning of funding, liquidity 
and FX risks and can make 
more proactive decisions.  
Treasury reviewer assesses 
alerts, validates assumptions, 
and decides follow-up actions.
Clarify whether PIL wants 
dashboard-only visibility or 
actionable advisory outputs 
on liquidity, FX, and short-
term cash moves.
Keep under Treasury & 
Liquidity. Treat as a later-
wave analytics use case 
unless treasury data 
readiness is already 
strong.
Won’t have 
now
No 12+ months / 
Strategic later 
wave
11	Ecosystem & Trade 
Validation
SGTraDex 
Validation Agents
Enrich AP, bunkering and 
document validation by cross-
checking finance transactions 
against trusted external trade 
events and ecosystem data 
from SGTraDex.  
AP, operations 
finance, bunkering 
teams.  
Transaction validation is 
strengthened with external 
corroboration, reducing 
reliance on internal records 
alone.  
AP or operations finance 
reviewer checks discrepancies 
and confirms disposition of 
flagged cases.
Clarify which PIL process 
should consume SGTraDex 
first: AP, bunkering, 
operational finance, or 
document validation.
Keep as ecosystem / 
operational extension. 
Position as future-wave 
unless a concrete high-
value validation scenario 
is selected.
Won’t have 
now
No 12+ months / 
Strategic later 
wave
12	AR & Cash 
Application
Advanced Cash 
Application Agents
Extend receipt classification 
into remittance matching, 
dispute routing and auto-
suggested cash allocation to 
reduce unresolved receipts.  
AR, Cash 
application, GL 
support.  
Cash application cycle time 
shortens and unapplied cash 
levels fall through better 
matching and routing.  
Cash application reviewer 
approves disputed or low-
confidence matches before 
posting.
Confirm volume of 
unapplied cash, remittance 
formats, dispute types, and 
whether PIL wants this in 
current scope or as next 
wave after classification.
Keep under AR & Cash 
Application. Treat as 
Phase 2 after Bank 
Receipt Classification 
unless data quality is 
already strong.
Could have Possible 6-12 months / 
Wave 2+
13	Cross-Process 
Governance
Cross-Process Risk 
Monitoring Agents
Consolidate abnormal activity 
and recurring control breaks 
across AP, AR, tax and close 
through shared risk flags, 
thresholds and dashboards.  
CFO, COO, Risk & 
Compliance, 
process owners.  
Leadership gets a single view 
of unusual finance activity 
and systemic control 
weaknesses across 
processes.  
Process owner, CFO, or COO 
reviews material risk patterns 
and assigns actions.
Clarify which cross-process 
KPIs and risk thresholds 
matter most to CFO/COO 
and which source agents 
will feed them.
Keep under Cross-Process 
Governance. Position as 
suite-level monitoring 
rather than first-wave 
MVP.
Won’t have 
now
No 12+ months / 
Strategic later 
wave
14	Cross-Process 
Governance
Agent Performance 
Governance Agents
Track throughput, exception 
rates, reviewer turnaround 
and overrides across all agents 
to govern scale-up and policy 
tuning.  
CFO, Finance 
Transformation 
Lead, IT.  
Finance and IT can scale 
agents in a controlled 
manner and tune policies 
based on evidence.  
Transformation lead or product 
owner reviews agent KPIs and 
approves tuning actions.
Clarify whether PIL wants 
governance of deployed 
agents now or only after 
several use cases go live.
Keep under Cross-Process 
Governance. Position as 
enablement for scale-up 
rather than immediate 
MVP.
Won’t have 
now
No 12+ months / 
Strategic later 
wave
15	Tax & Compliance Extended Tax 
Compliance Agents
Build on reconciliation outputs 
to generate audit-ready 
evidence packs, regulatory 
workpapers and recurring 
compliance schedules.  
Group Tax, 
compliance teams.  
Audit readiness improves 
and manual assembly of tax 
support files is reduced.  
Tax preparer / reviewer 
validates workpapers and signs 
off compliance packs.
Clarify which compliance 
packs, workpapers, and 
sign-off artefacts are in 
scope beyond tax 
reconciliation.
Keep under Tax & 
Compliance as an 
extension of Tax 
Reconciliation.
Won’t have 
now
No 12+ months / 
Strategic later 
wave
16	Treasury & Liquidity Working Capital 
Insight Agents
Combine AP, AR and 
statement-cycle data to show 
working-capital drivers and 
support cash-conversion 
decision-making.  
CFO, Treasury, 
Finance 
leadership.  
Leadership gains clearer 
visibility into payables, 
receivables and cash-
conversion performance.  
CFO, treasury, or finance lead 
reviews insights and confirms 
management actions.
Clarify target metrics, 
frequency, and whether 
leadership wants 
explanatory dashboards or 
scenario capability.
Keep under Treasury & 
Liquidity as a suite-level 
insight layer.
Won’t have 
now
No 12+ months / 
Strategic later 
wave
17	Operational Finance Operational 
Finance Agents
Reuse the same architecture 
for voyage cost checks, bunker 
reconciliation and operational 
billing validation across 
shipping operations 
workflows.  
Operations 
finance, shipping 
operations, 
Controllership.  
Finance-grade controls 
extend into shipping 
operations, improving end-
to-end visibility and 
validation without replacing 
core systems.  
Operations finance or 
controllership reviewer 
assesses exceptions and 
confirms case resolution.
Clarify which operational-
finance scenario matters 
first, e.g. voyage cost, 
bunker reconciliation, or 
billing validation.
Keep under Operational 
Finance as a future 
industry-specific 
extension.
Won’t have 
now
No 12+ months / 
Strategic later 
wave

--- USER STORY ---
# Automated AFS Submission Orchestration with AI-Assisted Quality Checks

## Overview
This is an **Agentic AI App** that standardizes and tracks the end-to-end submission of Annual Financial Statements (AFS) to the Group Financial Reporting & Analysis (GFRA) and Corporate Accounting Centre (CAC). Today, AFS submission relies on manual coordination, email follow-ups, and ad-hoc tracking, creating poor visibility, weak accountability, and audit risk. The proposed solution introduces an autonomous **AFS Submission Agent** that orchestrates the workflow, validates submission packs for completeness, monitors timeliness, and routes reviews and approvals — escalating to humans only when judgment or sign-off is required.

## Actors
- **Financial Reporting Preparer** (human): Compiles the AFS pack from Oracle GFS / CAC sources and triggers submission.
- **CAC / Controllership Reviewer** (human): Reviews AFS submissions, approves them, or sends them back for rework. Resolves late or incomplete cases.
- **Finance Manager / Submission Owner** (human): Owns the entity's submission timeline and is accountable for on-time, complete delivery.
- **AFS Submission Agent** (AI agent): Autonomously detects submission triggers, validates pack completeness against a defined checklist, runs anomaly and lateness-risk checks, routes the submission to the right reviewer queue, sends reminders and escalations, and logs every state change for audit. Defers to humans on judgment calls (approvals, exceptions, ambiguous completeness).
- **Notification & Escalation Sub-Agent** (AI agent): Monitors submission SLAs, predicts lateness risk based on historical patterns, and proactively nudges preparers and reviewers before deadlines are breached.

## Goals
- Establish a single, governed workflow for AFS submission to GFRA/CAC across all entities.
- Reduce late, missing, or incomplete submissions through proactive validation and reminders.
- Improve auditability with a complete, time-stamped trail of triggers, validations, reviews, approvals, and reworks.
- Free finance staff from manual coordination so they can focus on review and analysis.
- Provide leadership with real-time visibility into submission status, bottlenecks, and risk.

## User Story
As a **Financial Reporting Preparer / CAC Reviewer**, I want **an AI agent to orchestrate AFS submission, validate completeness, track timeliness, and surface only the items that need my judgment**, so that **AFS submissions to GFRA/CAC are consistently on-time, complete, and fully auditable, with reduced manual coordination effort and lower compliance risk**.

## Detailed Workflow

### 1. Trigger detection (Agent-led)
- The AFS Submission Agent monitors the financial close calendar and submission triggers (e.g., entity close completion, scheduled submission window, manual kickoff).
- Upon trigger, the agent creates a submission case with entity, reporting period, owner, and target deadline.

### 2. Pack assembly & ingestion (Human-initiated, Agent-supported)
- The Preparer uploads (or links) the AFS pack — Oracle GFS extracts, CAC outputs, supporting schedules, and disclosures.
- The agent ingests files and indexes them against the standard AFS pack checklist.

### 3. Automated completeness & quality validation (Agent decision point)
The agent runs a rules-based + LLM-assisted check covering:
- **Pack completeness** — all required documents present (P&L, BS, CF, notes, supporting schedules).
- **Standardisation** — file format, naming convention, account mapping consistency vs. master chart.
- **Quick consolidation check** — totals reconcile across primary statements; key control balances tie.
- **Variance / anomaly check** — period-over-period variances exceeding configurable thresholds are flagged.
- **Lateness risk score** — predicted likelihood of missing the deadline based on current state.

Decision logic:
- **All checks pass** → route to reviewer queue with "ready for review" status.
- **Minor issues** (e.g., naming) → auto-fix where safe, log change, continue.
- **Material gaps** (missing pack, broken totals, large unexplained variances) → return to Preparer with a structured exception list. **Agent does not approve or post anything.**

### 4. Review routing & reminders (Agent-led)
- The agent routes the validated pack to the assigned CAC / Controllership Reviewer.
- The Notification Sub-Agent sends scheduled reminders, escalates to the Finance Manager if SLA risk is high, and nudges reviewers nearing deadline.

### 5. Reviewer decision (Human hand-off — mandatory)
The Reviewer:
- Approves the submission, or
- Returns it with comments (agent re-opens the case, notifies preparer, tracks rework cycle), or
- Escalates anomalies for further investigation.

### 6. Submission logging & dashboard (Agent-led)
- On approval, the agent records the final approved pack, approver identity, timestamp, and any version history.
- All revisions after first submission are version-controlled with a clear audit trail.
- Status flows into a **Submission Dashboard** (Power BI) showing on-time %, in-progress, late, and exception cases by entity and period.

### 7. Audit & evidence pack (Agent-led)
- The agent generates an audit-ready evidence bundle per submission: triggers, validation results, reminders sent, reviewer comments, approval record, and final pack.

## Acceptance Criteria

### Functional
- All AFS submissions are initiated, tracked, and closed within a single governed workflow — no email-only submissions accepted.
- The agent correctly identifies and flags incomplete packs against the configurable AFS checklist with ≥95% accuracy on validation rule cases.
- Version control captures every revision after first submission, with timestamp, submitter, and change reason.
- Reminders are issued at configurable intervals (e.g., T-5, T-2, T-0, T+1 days) and escalations follow a defined hierarchy.
- A dashboard displays real-time submission status, on-time rate, late cases, and rework cycles by entity and period.
- Quick consolidation numbers and period-over-period variance summaries are surfaced to the reviewer at the point of review.

### Agent guardrails & autonomy boundaries
- The agent **must not** approve, sign off, or submit final AFS packs without explicit human reviewer approval.
- The agent **must defer to a human** when: (a) completeness check is ambiguous, (b) variance exceeds threshold without an explanation, (c) account mapping cannot be matched with high confidence, or (d) the reviewer queue is empty/unassigned.
- The agent **must stop** and raise a system alert if: source data (Oracle GFS / CAC) is unavailable, validation rules fail to load, or repeated automated retries exceed a configurable limit.
- Every autonomous action (validation, routing, reminder, auto-fix) is logged with a machine-readable audit trail.
- Auto-fixes are restricted to a whitelisted set (e.g., file naming, formatting); no financial-data values may be altered by the agent.

### Escalation rules
- If a submission is at risk of breaching its deadline, escalate to the Finance Manager 48 hours before due.
- If a reviewer does not action a pack within SLA, escalate to the next-level approver.
- Any anomaly flagged with high severity is escalated immediately, regardless of SLA timing.

### Audit & compliance
- Full immutable audit trail of all submissions, validations, agent actions, and approvals retained per group records-retention policy.
- Evidence packs are reproducible on demand for internal and external audit.

## Assumptions & Constraints
- AFS packs are sourced from Oracle GFS and CAC; both systems can provide structured outputs that the agent can ingest. *(Source format and frequency need confirmation during discovery.)*
- A standardised AFS pack checklist and account-mapping reference will be defined and maintained by Controllership before go-live.
- Definitions of "incomplete," variance thresholds, and standardisation rules will be agreed with Financial Reporting and CAC stakeholders. *(Open clarification per Angela's comments.)*
- The MVP is workflow-led with optional intelligence checks (completeness, lateness risk, reviewer prioritisation); advanced anomaly detection may be added in later waves.
- Build approach is **low-code-first** (Power Automate for orchestration, Copilot/virtual agent for user guidance, Power BI for dashboards), with pro-code components introduced only where validation logic exceeds low-code limits.
- The agent never executes external submissions or postings autonomously — human approval is a hard gate.
- MoSCoW priority: **Must Have**; targeted for **Wave 1 (0–6 months)** as part of the Financial Close & Reporting cluster.

--- FEATURE LIST SUMMARY ---
This solution enables an autonomous AFS Submission Agent to orchestrate the end-to-end submission of Annual Financial Statements to GFRA and CAC, replacing manual coordination and email follow-ups with a governed, auditable workflow. Primary actors are the Financial Reporting Preparer, CAC/Controllership Reviewer, Finance Manager, and the AFS Submission Agent supported by a Notification & Escalation Sub-Agent. The flow runs from trigger detection through pack assembly, automated completeness validation, reviewer routing, approval, dashboard publishing, and audit evidence generation. Master Data Configuration holds entities, users/roles, AFS checklist, account mappings, validation rules, SLA calendars, and escalation hierarchies. The 16 rows deliver agent-led orchestration, AI-assisted quality checks, and real-time submission visibility.

Feature Clusters & Features:
• Master Data Configuration
  - 1. User, Role & Reviewer Hierarchy Management — Maintains preparers, reviewers, finance managers, and escalation chains used to route AFS submissions and approvals.
  - 2. Entity & Reporting Calendar Registry — Catalog of legal entities, reporting periods, and submission deadlines that drive trigger detection and SLA tracking.
  - 3. AFS Pack Checklist Configuration — Configurable list of mandatory documents, schedules, and disclosures used by the agent for completeness validation.
  - 4. Account Mapping & Chart Reference — Master chart of accounts and mapping rules referenced during standardisation and consolidation checks.
  - 5. Validation Rules & Threshold Library — Stores variance thresholds, naming conventions, and quality rules used by the AI agent during automated checks.
  - 6. SLA, Reminder & Escalation Policy — Defines reminder cadences, SLA windows, and escalation hierarchies governing the Notification Sub-Agent.
• Submission Trigger & Initiation
  - 7. Submission Trigger Detection — Agent monitors close calendar and submission windows to autonomously open new AFS submission cases.
  - 8. Submission Case Creation — Creates a tracked case record with entity, period, owner, and target deadline once a trigger fires.
• Pack Assembly & Ingestion
  - 9. AFS Pack Upload & Source Linking — Preparer uploads or links Oracle GFS/CAC extracts and supporting schedules into the submission case.
  - 10. Document Indexing Against Checklist — Agent ingests files and maps each document to its corresponding checklist item for downstream validation.
• Automated Quality & Completeness Validation
  - 11. Pack Completeness & Standardisation Check — AI agent verifies required documents, naming conventions, and format compliance, auto-fixing safe issues only.
  - 12. Consolidation & Variance Anomaly Check — Validates totals tie across statements and flags period-over-period variances exceeding configured thresholds.
  - 13. Lateness Risk Scoring — Sub-agent predicts likelihood of deadline breach using historical patterns and current case state.
• Review Routing & Notifications
  - 14. Reviewer Queue Routing — Agent assigns validated packs to the correct CAC/Controllership reviewer based on entity and role mapping.
  - 15. Reminders & SLA Escalations — Notification Sub-Agent issues scheduled nudges and escalates to Finance Manager when SLA breach is imminent.
• Reviewer Decision & Rework
  - 16. Reviewer Approval, Return, or Escalate — Reviewer approves the pack, returns it with comments for rework, or escalates anomalies for investigation.
  - 17. Rework Cycle & Version Control — Agent reopens returned cases, tracks revisions with timestamp and change reason, and re-runs validations.
• Submission Logging & Reporting
  - 18. Submission Dashboard — Power BI dashboard surfaces on-time %, in-progress, late, and exception cases by entity and period for leadership.
  - 19. Audit Evidence Pack Generation — Agent compiles a reproducible bundle of triggers, validations, reminders, reviewer comments, and approvals per submission.
• Agent Orchestration & Guardrails
  - 20. Agent Action Audit Log & Guardrail Enforcement — Logs every autonomous action and enforces hard limits preventing approval, posting, or value changes without human sign-off.

--- FEATURE LIST (20 features across 8 clusters) ---

#1 | Cluster: Master Data Configuration | Feature: User, Role & Reviewer Hierarchy Management
  Description: Central registry of users, roles, and the reviewer/escalation hierarchy used by the AFS workflow. Drives routing, approvals, and notifications across all submissions.
  Workflow:
    1. Admin creates user accounts for preparers, reviewers, and managers.
    2. Assign roles and entity scope to each user.
    3. Define reviewer-to-entity mapping and escalation chain.
    4. Activate user with effective dates.
    5. Audit changes via change log.
  Table:       afs_users_roles
  Columns:     id (bigint, pk), user_name (varchar 150), email (varchar 200), role_code (varchar 50), entity_scope (varchar 255), escalation_parent_id (bigint, fk), active_flag (boolean), created_at (timestamp)
  Actor:       System Administrator
  AI Agent:    AFS Submission Agent
  ----
#2 | Cluster: Master Data Configuration | Feature: Entity & Reporting Calendar Registry
  Description: Holds entities, reporting periods, and submission deadlines that feed the agent's trigger detection and SLA monitoring. Single source of truth for what is due, when, and from whom.
  Workflow:
    1. Define legal entities and reporting units.
    2. Configure reporting periods and close calendar.
    3. Set submission window and target deadline per entity-period.
    4. Link entity to owner and reviewer.
    5. Publish calendar for agent monitoring.
  Table:       afs_entity_calendar
  Columns:     id (bigint, pk), entity_code (varchar 50), entity_name (varchar 200), period_code (varchar 20), submission_window_start (date), submission_due_date (date), owner_user_id (bigint, fk), reviewer_user_id (bigint, fk)
  Actor:       Controllership Admin
  AI Agent:    AFS Submission Agent
  ----
#3 | Cluster: Master Data Configuration | Feature: AFS Pack Checklist Configuration
  Description: Configurable checklist describing every document required in an AFS pack. Used by the agent to validate completeness and route exceptions back to preparers.
  Workflow:
    1. Define checklist items (P&L, BS, CF, notes, schedules).
    2. Mark each as mandatory or optional.
    3. Set expected file format and naming pattern.
    4. Version the checklist by effective date.
    5. Publish for agent ingestion.
  Table:       afs_pack_checklist
  Columns:     id (bigint, pk), checklist_version (varchar 20), item_code (varchar 50), item_name (varchar 200), is_mandatory (boolean), expected_format (varchar 50), naming_pattern (varchar 200), effective_from (date)
  Actor:       Controllership Admin
  AI Agent:    AFS Submission Agent
  ----
#4 | Cluster: Master Data Configuration | Feature: Account Mapping & Chart Reference
  Description: Master account mapping reference that powers standardisation and quick consolidation checks. The agent uses it to flag mapping mismatches or low-confidence cases for human review.
  Workflow:
    1. Load group chart of accounts.
    2. Map source accounts (Oracle GFS/CAC) to group accounts.
    3. Set confidence thresholds for auto-mapping.
    4. Approve mapping changes through workflow.
    5. Version mappings.
  Table:       afs_account_mapping
  Columns:     id (bigint, pk), source_system (varchar 50), source_account (varchar 100), group_account (varchar 100), mapping_confidence (decimal 5,2), version (varchar 20), approved_by (bigint, fk), effective_from (date)
  Actor:       Controllership Admin
  AI Agent:    AFS Submission Agent
  ----
#5 | Cluster: Master Data Configuration | Feature: Validation Rules & Threshold Library
  Description: Library of validation rules and variance thresholds the AI agent applies during quality checks. Severity flags determine whether to auto-fix, warn, or block submission.
  Workflow:
    1. Define rule type (completeness, variance, naming, totals).
    2. Configure threshold or pattern values.
    3. Set severity (minor, material, blocking).
    4. Specify auto-fix permission flag.
    5. Activate rule for agent runtime.
  Table:       afs_validation_rules
  Columns:     id (bigint, pk), rule_code (varchar 50), rule_type (varchar 50), threshold_value (decimal 18,4), severity (varchar 20), auto_fix_allowed (boolean), active_flag (boolean), updated_at (timestamp)
  Actor:       Controllership Admin
  AI Agent:    AFS Submission Agent
  ----
#6 | Cluster: Master Data Configuration | Feature: SLA, Reminder & Escalation Policy
  Description: Configurable policy for reminder cadence, SLA windows, and escalation recipients. Drives the Notification Sub-Agent's proactive nudging and escalation behaviour.
  Workflow:
    1. Define reminder offsets (T-5, T-2, T-0, T+1).
    2. Configure escalation thresholds and recipients.
    3. Set SLA windows for review and rework.
    4. Map policy to entity tiers.
    5. Activate policy.
  Table:       afs_sla_policy
  Columns:     id (bigint, pk), policy_code (varchar 50), reminder_offsets (varchar 200), review_sla_hours (int), rework_sla_hours (int), escalation_chain (varchar 255), active_flag (boolean)
  Actor:       Finance Manager
  AI Agent:    Notification & Escalation Sub-Agent
  ----
#7 | Cluster: Submission Trigger & Initiation | Feature: Submission Trigger Detection
  Description: Autonomous detection of conditions that warrant opening a new AFS submission. Eliminates manual kickoff and ensures every entity-period is tracked.
  Workflow:
    1. Agent polls close calendar and external triggers.
    2. Detects entity close completion or scheduled window opening.
    3. Validates entity is in scope and active.
    4. Creates pending submission case.
    5. Logs trigger event with source.
  Table:       afs_submission_triggers
  Columns:     id (bigint, pk), entity_code (varchar 50), period_code (varchar 20), trigger_type (varchar 50), trigger_source (varchar 100), detected_at (timestamp), case_id (bigint, fk)
  Actor:       AFS Submission Agent
  AI Agent:    AFS Submission Agent
  ----
#8 | Cluster: Submission Trigger & Initiation | Feature: Submission Case Creation
  Description: Creates the canonical submission case that all subsequent activity attaches to. Provides the spine for tracking, status, and audit.
  Workflow:
    1. Agent instantiates case record with entity, period, owner.
    2. Sets target deadline from calendar.
    3. Assigns initial status 'awaiting pack'.
    4. Notifies preparer of new case.
    5. Logs creation in audit trail.
  Table:       afs_submission_cases
  Columns:     id (bigint, pk), entity_code (varchar 50), period_code (varchar 20), owner_user_id (bigint, fk), reviewer_user_id (bigint, fk), target_deadline (date), status (varchar 30), created_at (timestamp)
  Actor:       AFS Submission Agent
  AI Agent:    AFS Submission Agent
  ----
#9 | Cluster: Pack Assembly & Ingestion | Feature: AFS Pack Upload & Source Linking
  Description: Lets the preparer attach all required AFS pack files and source extracts to the case. Triggers downstream agent ingestion and validation.
  Workflow:
    1. Preparer opens submission case.
    2. Uploads files or links Oracle GFS/CAC source extracts.
    3. Tags each file with checklist item.
    4. Submits pack for validation.
    5. Agent acknowledges receipt.
  Table:       afs_pack_documents
  Columns:     id (bigint, pk), case_id (bigint, fk), checklist_item_code (varchar 50), file_name (varchar 255), file_url (varchar 500), source_system (varchar 50), uploaded_by (bigint, fk), uploaded_at (timestamp)
  Actor:       Financial Reporting Preparer
  AI Agent:    AFS Submission Agent
  ----
#10 | Cluster: Pack Assembly & Ingestion | Feature: Document Indexing Against Checklist
  Description: Agent automatically maps each uploaded document to its checklist slot and reports unmatched items. Bridges raw uploads to structured validation.
  Workflow:
    1. Agent reads uploaded files and metadata.
    2. Matches each file to checklist item via name/content.
    3. Flags unmatched or duplicate items.
    4. Records mapping confidence.
    5. Marks pack ready for validation.
  Table:       afs_pack_index
  Columns:     id (bigint, pk), case_id (bigint, fk), document_id (bigint, fk), checklist_item_code (varchar 50), match_confidence (decimal 5,2), match_status (varchar 30), indexed_at (timestamp)
  Actor:       AFS Submission Agent
  AI Agent:    AFS Submission Agent
  ----
#11 | Cluster: Automated Quality & Completeness Validation | Feature: Pack Completeness & Standardisation Check
  Description: Verifies all mandatory items are present and standardised, applying safe auto-fixes only. Material gaps are returned with a structured exception list.
  Workflow:
    1. Agent runs checklist completeness check.
    2. Validates naming conventions and formats.
    3. Auto-fixes whitelisted issues (e.g., naming).
    4. Logs each fix and exception.
    5. Returns material gaps to preparer.
  Table:       afs_validation_results
  Columns:     id (bigint, pk), case_id (bigint, fk), rule_code (varchar 50), result_status (varchar 30), severity (varchar 20), auto_fixed (boolean), exception_detail (text), checked_at (timestamp)
  Actor:       AFS Submission Agent
  AI Agent:    AFS Submission Agent
  ----
#12 | Cluster: Automated Quality & Completeness Validation | Feature: Consolidation & Variance Anomaly Check
  Description: Performs quick consolidation tie-outs and variance checks against configurable thresholds. Anomalies are surfaced to the reviewer at the point of review.
  Workflow:
    1. Agent extracts totals from primary statements.
    2. Reconciles cross-statement balances.
    3. Computes period-over-period variances.
    4. Flags variances above threshold.
    5. Surfaces anomalies to reviewer summary.
  Table:       afs_anomaly_findings
  Columns:     id (bigint, pk), case_id (bigint, fk), metric_name (varchar 100), prior_value (decimal 18,2), current_value (decimal 18,2), variance_pct (decimal 8,2), severity (varchar 20), explanation (text)
  Actor:       AFS Submission Agent
  AI Agent:    AFS Submission Agent
  ----
#13 | Cluster: Automated Quality & Completeness Validation | Feature: Lateness Risk Scoring
  Description: Predictive score estimating the probability that a submission will miss its deadline. Drives proactive reminders and early escalations.
  Workflow:
    1. Sub-agent gathers case state and history.
    2. Applies predictive model for lateness risk.
    3. Outputs risk score (low/medium/high).
    4. Triggers proactive nudge if risk high.
    5. Updates case with score.
  Table:       afs_lateness_risk
  Columns:     id (bigint, pk), case_id (bigint, fk), risk_score (decimal 5,2), risk_band (varchar 20), model_version (varchar 30), scored_at (timestamp), recommended_action (varchar 200)
  Actor:       Notification & Escalation Sub-Agent
  AI Agent:    Notification & Escalation Sub-Agent
  ----
#14 | Cluster: Review Routing & Notifications | Feature: Reviewer Queue Routing
  Description: Routes validated submissions to the correct reviewer based on entity and role mapping. Eliminates manual hand-off and email follow-ups.
  Workflow:
    1. Agent confirms validation passed or minor only.
    2. Looks up reviewer assignment for entity.
    3. Routes case to reviewer's queue.
    4. Sets status to 'ready for review'.
    5. Notifies reviewer.
  Table:       afs_review_queue
  Columns:     id (bigint, pk), case_id (bigint, fk), reviewer_user_id (bigint, fk), routed_at (timestamp), queue_status (varchar 30), priority (varchar 20)
  Actor:       AFS Submission Agent
  AI Agent:    AFS Submission Agent
  ----
#15 | Cluster: Review Routing & Notifications | Feature: Reminders & SLA Escalations
  Description: Automates reminders and escalations to keep submissions on track. Escalation hierarchy and offsets follow the SLA policy master data.
  Workflow:
    1. Sub-agent checks SLA timers and risk score.
    2. Sends reminders at configured offsets.
    3. Escalates to Finance Manager 48 hrs before due.
    4. Escalates to next-level on reviewer SLA breach.
    5. Logs every notification.
  Table:       afs_notifications
  Columns:     id (bigint, pk), case_id (bigint, fk), recipient_user_id (bigint, fk), notification_type (varchar 50), channel (varchar 30), sent_at (timestamp), escalation_level (int)
  Actor:       Notification & Escalation Sub-Agent
  AI Agent:    Notification & Escalation Sub-Agent
  ----
#16 | Cluster: Reviewer Decision & Rework | Feature: Reviewer Approval, Return, or Escalate
  Description: Mandatory human decision point where the reviewer approves, returns, or escalates the pack. The agent never approves or submits autonomously.
  Workflow:
    1. Reviewer opens case with anomaly summary.
    2. Reviews pack and validation results.
    3. Approves, returns with comments, or escalates.
    4. Decision recorded with timestamp.
    5. Agent transitions case state.
  Table:       afs_review_decisions
  Columns:     id (bigint, pk), case_id (bigint, fk), reviewer_user_id (bigint, fk), decision (varchar 30), comments (text), decided_at (timestamp), escalation_target (varchar 100)
  Actor:       CAC / Controllership Reviewer
  AI Agent:    AFS Submission Agent
  ----
#17 | Cluster: Reviewer Decision & Rework | Feature: Rework Cycle & Version Control
  Description: Tracks revisions and rework cycles after first submission with full version history. Every change is timestamped with submitter and reason.
  Workflow:
    1. Returned case is reopened by agent.
    2. Preparer is notified with reviewer comments.
    3. New pack version is uploaded.
    4. Agent re-runs validations on new version.
    5. Routes back to reviewer.
  Table:       afs_pack_versions
  Columns:     id (bigint, pk), case_id (bigint, fk), version_no (int), submitted_by (bigint, fk), submitted_at (timestamp), change_reason (text), validation_run_id (bigint, fk)
  Actor:       Financial Reporting Preparer
  AI Agent:    AFS Submission Agent
  ----
#18 | Cluster: Submission Logging & Reporting | Feature: Submission Dashboard
  Description: Real-time Power BI dashboard for leadership visibility into submission status, bottlenecks, and risk. Highlights on-time rate, late cases, and rework cycles.
  Workflow:
    1. Data pipeline aggregates case status data.
    2. Power BI refreshes dashboard.
    3. Users filter by entity and period.
    4. View on-time %, late, in-progress, exceptions.
    5. Drill into individual cases.
  Table:       afs_dashboard_metrics
  Columns:     id (bigint, pk), entity_code (varchar 50), period_code (varchar 20), on_time_pct (decimal 5,2), late_count (int), in_progress_count (int), exception_count (int), refreshed_at (timestamp)
  Actor:       Finance Manager
  AI Agent:    AFS Submission Agent
  ----
#19 | Cluster: Submission Logging & Reporting | Feature: Audit Evidence Pack Generation
  Description: Produces a reproducible audit-ready bundle for each submission. Supports internal and external audit with full immutable history.
  Workflow:
    1. Agent compiles trigger, validations, reminders, comments, approval.
    2. Bundles final approved pack and version history.
    3. Generates immutable evidence package.
    4. Stores per retention policy.
    5. Available for on-demand audit retrieval.
  Table:       afs_audit_evidence
  Columns:     id (bigint, pk), case_id (bigint, fk), evidence_url (varchar 500), generated_at (timestamp), retention_until (date), checksum (varchar 128), generated_by_agent (varchar 100)
  Actor:       AFS Submission Agent
  AI Agent:    AFS Submission Agent
  ----
#20 | Cluster: Agent Orchestration & Guardrails | Feature: Agent Action Audit Log & Guardrail Enforcement
  Description: Enforces autonomy boundaries — no approvals, no value changes, defer-to-human triggers — and logs every agent action. Provides the trust layer for autonomous operation.
  Workflow:
    1. Every agent action is captured with context.
    2. Guardrail engine validates action against policy.
    3. Blocks restricted actions (approval, value changes).
    4. Raises system alert on stop conditions.
    5. Logs all attempts and outcomes.
  Table:       afs_agent_action_log
  Columns:     id (bigint, pk), case_id (bigint, fk), agent_name (varchar 100), action_type (varchar 50), action_payload (text), guardrail_outcome (varchar 30), executed_at (timestamp), alert_raised (boolean)
  Actor:       AFS Submission Agent
  AI Agent:    AFS Submission Agent
  ----

==================================================
 END OF STORY EXPORT
==================================================
