Amperity Reimagines Data and Developer Workflows with AI - Ep. 271

What It Covers

Derek Slager, CTO of Amperity, explains how his company uses AI agents to unify customer data across enterprises, discusses vibe coding workflows that transform developer productivity, and shares practical implementation strategies for agentic systems.

Key Questions Answered

• •Agentic AI Definition: Define agentic systems as programs where the LLM controls flow through retries, tool calls, or agent interactions—this shifts evaluation metrics, monitoring approaches, and system capabilities compared to traditional programs with simple LLM calls.
• •Vibe Coding Workflow: Launch 10 parallel LLM processes simultaneously, continue other work, then review results—discard 3-4 failures, refine 3-4 partial solutions, accept 2-3 complete outputs. This asynchronous approach multiplies engineering capacity beyond sequential coding methods.
• •Non-Technical Data Access: Text-to-SQL interfaces for non-programmers drove sustained adoption increases in cohort analysis, with users moving from occasional to frequent data introspection once SQL barriers were removed, enabling data-informed decisions across broader organizational roles.
• •Business Context Integration: Bootstrap LLMs with company-specific terminology and domain knowledge immediately—a car dealer's "taco" means Toyota Tacoma while a restaurant's means food item. Context-aware systems dramatically improve efficacy and user empowerment in customer data applications.