Skip to main content
Back to Prompt Library
implementation

Build CrewAI Team for Patent Prior Art Analysis

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

Linked challenge: Patent Prior Art Analysis Team for Single-Cell Tech with CrewAI & Bedrock

Format
Code-aware
Lines
10
Sections
3
Linked challenge
Patent Prior Art Analysis Team for Single-Cell Tech with CrewAI & Bedrock

Prompt source

Original prompt text with formatting preserved for inspection.

10 lines
3 sections
No variables
0 checklist items
from crewai import Agent, Crew, Process, Task
from langchain_aws import BedrockLLM

# Configure Bedrock LLM and setup CrewAI agents
bedrock_llm = BedrockLLM(model_id='anthropic.claude-3-5-sonnet-20240620-v1:0')

patent_analyst = Agent(
    role='Patent Claims Analyst',
    goal='Analyze genomic patent claims against biological protocol steps',
    backstory='You are a registered patent attorney specializing in single-cell genomics.',
    llm=bedrock_llm
)

Adaptation plan

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

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.