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