Back to Prompt Library
planning

Claude Agent System and Voiceflow Integration Design

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: AI Patent Analysis & Cloud Optimization Agents

Format
Code-aware
Lines
11
Sections
6
Linked challenge
AI Patent Analysis & Cloud Optimization Agents

Prompt source

Original prompt text with formatting preserved for inspection.

11 lines
6 sections
No variables
1 code block
Design the architecture for an intelligent assistant using Claude Agents SDK. Define two primary agent personas: a 'Patent Analyst Agent' and a 'Cloud Optimizer Agent'. Outline their specific capabilities and how they will share context. Detail how Voiceflow will serve as the user-facing conversational interface, routing user queries to the appropriate Claude agent or triggering a mode switch. Specify the necessary custom tools each agent will need.

```python
from anthropic import Anthropic

client = Anthropic()

# Example agent creation (simplified)
# You'll use the Claude Agents SDK for actual agent definition
# For initial planning, imagine defining roles and tools

# Patent Analyst Agent - focuses on legal documents
# Cloud Optimizer Agent - focuses on cost data

# Voiceflow integration will involve webhooks or custom integrations
```

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.

Tune next

Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.

Verify after

Check whether the prompt asks for the right evidence, confidence signal, and escalation path.