Automating the Full Customer Support Iceberg: How Gradient Labs Built a Multi-Agent Platform

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

Chapters

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