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

Listen to this episode on: Spotify | Apple Podcasts

What happens when a customer reports a stolen credit card? The frontline answer is simple—freeze it. But underneath lies a cascade of follow-ups: dispute filings, fraud investigations, merchant communications, and proactive outreach to gather more details. Most AI support tools handle only the tip of the iceberg.

In this episode, Teresa Torres talks with Jack Taylor (Product Engineer) and Ibrahim Faruqi (AI Engineer) from Gradient Labs, an AI-native startup building agents that automate the full scope of customer support in fintech. They share how they’ve architected a platform with three coordinating agents—inbound, back office, and outbound—all built on a shared foundation of natural language procedures, modular skills, and configurable guardrails.

You’ll hear how they:

• Let non-technical subject matter experts define agent behavior through natural language procedures—no coding required
• Architected a state machine orchestrator that manages turns, triggers, and skill selection across long-running conversations
• Built guardrails as binary classifiers with eval pipelines, tuning for high recall on critical regulatory checks
• Designed an auto-eval system that samples conversations for human review to catch edge cases and build labeled datasets

It’s a detailed look at how one startup is moving beyond simple Q&A bots to agents that can actually take action, coordinate across workflows, and handle the messy reality of customer support.

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

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

Full Transcript

Podcast transcripts are only available to paid subscribers.