Layer 0 · Corpus Ingestion

UK Publisher
Intelligence Context Framework

Intelligent Context Framework (ICF) — corpus-grounded analysis of Customer interactions, SOPs and Process Maps, AI Coach Scripts, SME Interviews and Subscriber Journeys.
Firstsource — Intelligence that Operates.
Chat Transcripts
7,960
Agent–customer conversations across subscription, delivery, payment, digital access (1–26 Feb 2026)
Message Rows Parsed
257,791
Individual MessageText rows grouped by QueryId (Col A); avg 32.4 turns/chat
SOP / Process Decks
11
Cancellation, Delivery, Digital, General, Payment, Subscription Mgmt, Overview, Knowledge Base
AI Coach Scripts
12
Free Trial, Too Expensive, Espresso, Switch, Change Product, Update Email, Renewal, Pause Print, Confirmation, Reset Password
Sales : Service Mix
64 : 36
5,074 Sales · 2,883 Service — Sales handles the bulk of cancellation save
Qualitative Signals
25,749
Cancel intent, refund requests, silence patterns, auto-renew surprises, save-offer pitches, transfers, escalations

Processing Pipeline

1
Parse — tokenise 11 SOP decks, 12 coach scripts & 7,960 chat transcripts
2
Extract — identify intents, journeys, agent patterns & exceptions
3
Map — build node-edge graph from entity relationships
4
Flag — classify gaps (Process / SOP / Training / Product)
5
Synthesize — assemble ICF with advisory, KB & transcript layers
Layer 1 · Operational Analysis

UK Publisher — 7,960 Chats · 257K Rows · 11 SOPs · 12 Coach Scripts

Journey Distribution (top 15 by volume)

Product Variants

Resolution Mix (7,960 chats)

Gap Profile

Issue Volume by Domain

Quality vs Benchmark

Top Operational Risks

Transcript Insight — Agent Patterns

Issue
Exception
System
Decision
Resolution
Layer 2 · Gap Intelligence

Gap Register — 42 Findings

5
CRITICAL
Save-offer mismatch, Auto-renew comms, Backdate window, Student validation, Save retention TBC
17
HIGH
Long silence, Multi-miss escalation, International address, Refund visibility, iTunes template, Transfer loop
20
MEDIUM
MMA self-serve, Editorial dialog, Email change warn, Pre-migration invoices, Newsletter monitoring
7,960
CHATS ANALYSED
~257K message rows · 1–26 Feb 2026 · 11 SOPs · 12 coach scripts
All Types
Process
SOP
Training
Product
All Severity
Critical
High
Medium
Layer 3A · SOP Decision Tool

SOP Reviews — Owner Decisions

Total 0 Incorporate 0 Ignore 0 Pending 0 Selected 0
Layer 3B · Capability Development

Training Modules & Performance Appraisals

Training Modules

Performance Appraisals

Layer 3C · Strategic Advisories

Process & Product Advisories

Process Advisories

Product Advisories

Priority × Effort Matrix

Layer 4 · Agent Knowledge Base

Knowledge Base — UK Publisher CSD

Articles
ICF Co-Pilot
Select a category to view articles
Layer 4 · Data Deep Dive

Analytical Deep Dive — Charts & Insights

Slice the 7,960-chat corpus by domain, severity, volume and remediation load.
Powered by Firstsource Intelligence

AI-Driven Interventions

Four intelligent pillars working across the subscriber journey — from cancel-save lift to autonomous dispatch escalation.

4
AI Pillars
+15pp
Save Rate Lift Target
−40%
AHT Reduction Target
£2.4M
Annual Save Value (est)
Pillar 01
Proactive Engagement
Detect risk signals before the subscriber chats in — auto-renewal in 7 days, missing copies, declined save offers — and intervene with timely reminders and pre-pitched save offers.
Pillar 02
Smart Routing
AI concierge classifies subscriber intent and complexity in real time, routing each to the optimal channel — MMA self-serve, AI chat, or specialist (Retention / Distribution / Tech).
Pillar 03
AI Co-Pilot
Real-time agent assist during live chat — intent classification, knowledge surfacing, compliance guardrails and auto-wrap — all contextual.
Pillar 04
Agentic AI
Autonomous reasoning over ICF context — observe, recall, probe, reason, govern, recommend — with human-in-the-loop governance.

Intervention Overview

Each pillar addresses a distinct layer of the customer interaction — from pre-contact engagement through to post-contact intelligence. Together they form a closed loop that learns from every conversation.

How the Pillars Connect

1. Proactive Engagement detects risk signals from subscription data, engagement patterns and ICF context — and sends timely renewal reminders + pre-pitched save offers before the subscriber needs to chat in.

2. Smart Routing classifies inbound subscriber intent and complexity in real time using the ICF entity graph, routing each to the right channel first time.

3. AI Co-Pilot assists the agent during live conversations with contextual suggestions, knowledge articles, compliance checks and automated after-call work.

4. Agentic AI reasons autonomously over ICF context for complex decisions — cancellation risk scoring, retention escalation routing, proactive save outreach — with human governance.

Projected Impact

62%→75%
First Contact Resolution
24:17→14:30
Avg Handle Time
8.4%→4.5%
Escalation Rate
7.4→8.7
CSAT Score

Pillar 01 · Proactive Engagement

ICF detects risk signals from subscription and engagement patterns — and triggers proactive renewal reminders before the subscriber needs to chat in.

ICF Signal Feed

Pillar 02 · Smart Routing

AI Concierge classifies subscriber intent, complexity and friction signal in real time — routing each to the optimal resolution channel (Self-Serve / AI Chat / Retention / Distribution).

Low · Self-Service

Medium · AI Chat + Handoff

High · Specialist Agent

--:--:--ReadyAI Concierge initialised · Domain Harness loaded · ICF connected

Pillar 03 · AI Co-Pilot

Live agent assist during a customer chat — intent classification, knowledge surfacing, compliance guardrails and automated after-call work.

Co-Pilot actions: 0

Live Chat Transcript

Co-Pilot Actions

Pillar 04 · Agentic AI

Autonomous reasoning over ICF context — a transparent chain-of-thought trace for a cancellation risk + retention escalation decision.

Reasoning Trace

ICF Context Read

Entity Context
Account: Digital + Print bundle · 6yr tenure
Prior contacts: 3 in last 90 days (delivery, save, refund)
Save offer history: declined 30% discount once
Product: Annual Digital + Print bundle
Channel preference: Live chat
Last contact: Missing copy refund (cap reached)
Domain Harness Match
Rule: DH-RETN-014 — "Repeat contact + cap-reached refund + cancel keyword → flag retention specialist within 2 minutes and surface tenure-loyalty save"
Confidence: 0.91
Trust tier: Human-in-the-Loop

Recommended Outcome

Cancellation riskHIGH (0.87)
Recommended actionRetention specialist + tenure-loyalty save
SLA targetResponse within 2 min
Save value at risk£249 annual LTV
Trace latency1.6s total

ICF Intelligence Architecture

Five-layer stack — ICF sits at the centre, binding operational sensors below to domain intelligence above.

Layer 5 — AI-Native Operations
Agents (illustrative — varies by client) e.g. cancellation save bot, proactive renewal assistant, delivery escalation agent
Illustrative
Layer 4 — Domain Intelligence
Domain Harness — Skills, Playbooks, Guardrails, Eval e.g. cancel-save offer hierarchy, delivery escalation playbook, GDPR / data-privacy routing
Core OS
Layer 3 — Organisational Context
Intelligent Context Framework (ICF) — entity graph, gap register, decision traces, SOP alignment
Core OS
Layer 2 — Operations Intelligence
Sensors — Process, Task, Conversation, Knowledge, Doc e.g. chat transcripts, Salesforce case notes, agent screen activity, QA calibrations, AI Coach Scripts
Core OS
Layer 1 — Raw Data & Subscriber Records
Systems of Record + Channels (illustrative) e.g. Salesforce CRM, Manage My Account (MMA), Knowledge Base, App Store billing, live chat, chatbot
Illustrative

Why ICF is the Centrepiece

Below ICF — Operations Intelligence

Sensors observe what is actually happening on the ground: process flows, desktop activity, conversations, documents, knowledge use. For UK Publisher this means every chat transcript, case narrative, and agent desktop action is captured in real time.

Above ICF — Domain Harness

Encodes 25 years of Firstsource domain expertise — skills, playbooks, guardrails — as the baseline of what should happen. For UK Publisher: cancel-save offer hierarchies, delivery escalation rules, GDPR / data-privacy routing, and subscriber lifecycle SOPs.

ICF Binds the Two

ICF stores the live state of every interaction, decision, exception, and outcome — closing the should-vs-did gap and feeding the learning loop. It connects what the agent actually did with what the playbook prescribed, surfacing gaps before they become complaints.

Top & Bottom — Illustrative

Agents and Systems of Record vary by client. The core value — Layers 2, 3 and 4 — is the intelligence stack that Firstsource owns and operates.

Outcome Forecast

Projected impact across key metrics — each improvement attributed to specific intervention pillars.

First Contact Resolution
68%
84%
Proactive + Co-Pilot + Routing
Average Handle Time
8m 45s
5m 40s
Co-Pilot + Routing
Escalation Rate
3.5%
1.8%
Agentic AI + Smart Routing
Repeat Contact Rate
1.0%
0.4%
Proactive + Co-Pilot
CSAT Score
7.2
8.6
All Pillars
Annual Cost Saving
Baseline
£2.4M
Cancel-save lift + AHT reduction + auto-renewal trust