Automating the Full Customer Support Iceberg: How Gradient Labs Built a Multi-Agent Platform
Show notes
Guests**
- Jack Taylor, Product Engineer, Gradient Labs
- Ibrahim Faruqi, AI Engineer, Gradient Labs
In this episode
- The iceberg metaphor: why frontline support is only the tip of automation potential
- How three agent types (inbound, back office, outbound) coordinate on complex tasks like fraud disputes
- Natural language procedures that let subject matter experts train agents without engineering bottlenecks
- The "turn" architecture: state machines that orchestrate agent logic across async, multi-day conversations
- Skills as modular agent capabilities—and how they're scoped deterministically per turn
- Defining "done" for outbound agents when the customer isn't the one ending the conversation
- Guardrails as classification problems: balancing recall and precision for regulatory compliance
- Ask a Human: a tool call that brings humans into the loop for approvals or missing APIs
- Auto-eval pipelines that flag conversations for manual review and feed labeled datasets
Links & References
- Gradient Labs
- Incident.io episode – Referenced in the conversation
00:00 Meet the Engineers: Jack and Ibrahim 00:39 The Role of Product Engineers in Tech 01:21 Introduction to Gradient Labs 02:11 The Three Pillars of Customer Support Automation 04:32 The Evolution and Growth of Gradient Labs 05:29 Building and Refining AI Agents 06:39 Outbound Agent: Addressing Customer Problems 09:12 Defining Success in Outbound Procedures 17:08 Ensuring Compliance and Guardrails 30:17 Understanding Agent Guardrails 31:54 Complexities of Natural Language Input 36:21 Skill Design and Management 39:53 Deterministic Skill Execution 41:54 Customer-Specific Guardrails 44:21 APIs and Customer Tools Integration 46:02 Ask A Human Tool 48:24 Guardrails as Classification Problems 57:12 Auto Eval System 59:12 Future of Multi-Agent Systems