Echo
Content platform (audiobook & media)
Improved session duration and retention through a real-time recommendation decision system.
The challenge
Generic discovery and recommendations were failing to retain subscribers.
Content platforms struggle to retain users because discovery is inefficient and generic.
Client
Audiobook and content platform
Decision type
What to show
The system
Decision system built
We engineered a content intelligence system that continuously analyses user behaviour, listening patterns, and engagement signals to decide what content to recommend, when to surface it, and how to personalise the experience.
System components
Behavioural data ingestion layer
Recommendation engine (ranking + filtering logic)
CDN-backed delivery optimisation
Feedback loop for continuous model improvement
How we worked
Engagement scope
End-to-end design and implementation of the recommendation and personalisation decision layer, including data pipelines, ranking logic, and delivery integration.
Timeline
Phased delivery aligned to platform release cycles, with iterative model and ranking improvements post-launch.
Operating model
Joint product and engineering squads with clear ownership of data quality, model performance, and content governance checkpoints.
Outcomes
Business impact & measurable results
Improved session duration and retention through a real-time recommendation decision system.
Increased session duration and retention
More efficient content consumption
Scalable personalisation without manual curation
Governance
Trust, collaboration & governance
Transparent ranking objectives and guardrails agreed with stakeholders
Knowledge transfer on operating and tuning the recommendation loop
Governance for content eligibility and compliance-sensitive catalogues
Reframe
Not an audiobook app — a real-time recommendation decision system.
Across every engagement, the goal is the same: engineer a system that makes better decisions — faster, more consistently, and at scale — than the process it replaces.
Insights
Related perspectives.
Articles and guides that reference this problem space — useful for committees still in the learning stage.
- Read article
Original research
Scale-Up AI Implementation Benchmarks 2026
- Read article
Landscape report
The AI Voice Agent Industry Report 2026
- Read article
Industry landscape report
The Children’s Voice Economy
- Read article
Guide
RAG and Knowledge Systems: From Pilot to Production
- Read article
Guide
ML Monitoring and Model Governance: A Pragmatic Baseline
- Read article
Guide
MVP Scope Discipline: What to Ship First
Start a discovery
Most engagements begin with a conversation about context.
We do not send a proposal before we understand the problem. Start by telling us about your decision context — we will identify the highest-leverage intervention areas before any scope is agreed.