Skip to content

VoC Agent Architecture Patterns

How to structure a Voice of the Customer agent system — from data infrastructure to agent orchestration.

Data Infrastructure First

Before deploying any agents, you need a unified data layer:

  • CDP Stack (Ramp's choice): Snowflake + dbt + Hightouch
    • Snowflake: warehouse + Cortex AI for natural language queries
    • dbt: transforms raw data into queryable models
    • Hightouch: reverse ETL pushes insights back into tools (Salesforce, Slack, etc.)
  • Unstructured data handling: Gong transcripts, support tickets, emails — all flowing into the warehouse
  • PII controls: Exclude SSNs, partial identifiers — build privacy in from day one
  • MCP Server: Snowflake now supports Model Context Protocol for direct LLM connectivity

Parallel Agent Architecture

Ramp's core pattern — launch multiple specialized agents simultaneously:

[Coordinator Agent]
    |
    ├── [Gong Agent] ——> scans call transcripts
    ├── [Zendesk Agent] ——> scans support tickets
    ├── [Competitor Agent] ——> scrapes competitor sites
    ├── [Codebase Agent] ——> searches internal code
    ├── [Salesforce Agent] ——> pulls CRM data
    └── [Usage Agent] ——> analyzes product analytics
    |
    v
[Synthesis Agent] ——> merges artifacts into insights
  • Each agent writes a markdown artifact with its findings
  • A coordinator agent applies map-reduce synthesis — identifies patterns across all artifacts
  • 6-10 agents per research task is Ramp's sweet spot

Agent Design Principles

Constrained Decision Spaces

  • Learned from Ramp's Tour Guide agent: the most effective improvement is constraining what the agent can do
  • Give agents narrow, well-defined tasks rather than broad mandates
  • Single-step action generation — agent produces one action at a time based on current state

L0-L3 AI Adoption Framework

LevelDescriptionExample
L0No AIManual research
L1AI assists humanCopilot suggests, human decides
L2AI acts, human reviewsAgent drafts spec, PM edits
L3Full autonomyAgent handles end-to-end

Ramp pushes every function toward L2-L3.

Two-Tier Model Strategy

TierDataUse Case
GeneralAggregated across 15K+ customersBenchmarks, trends, category insights
SensitiveOpt-in, in-context onlyCustomer-specific analysis, no persistent training

RAG Pipeline for Customer Data

For ingesting Gong transcripts and similar unstructured sources:

  1. Chunking: Fixed-size 512-1024 tokens (recommended for transcripts)
  2. Metadata enrichment: Call ID, participants, timestamps, topic labels, sentiment
  3. Speaker mapping: Map speaker IDs to actual names
  4. Namespace partitioning: Isolate by tenant/customer for security
  5. Vector indexing: Embed chunks with metadata for semantic search
  6. Sync strategy: Historical bulk load + webhook/polling for ongoing updates

Key Takeaways

  • Data infrastructure is prerequisite #1 — agents without clean, unified data just hallucinate faster
  • Parallel agent execution with map-reduce synthesis is the dominant pattern for multi-source VoC
  • Constrain agent decision spaces aggressively — narrow tasks >> broad mandates
  • Build two model tiers (general aggregated vs. sensitive opt-in) to handle data privacy
  • RAG with 512-1024 token chunks, rich metadata, and namespace isolation is the standard approach for transcript data