Operator-ready prompt for reuse, tuning, and workspace runs.
This item is set up for developers who want to inspect the original language, fork it into Workspace, and adapt the evidence model without losing the source prompt structure.
Implementation handoffs, eval setup, and prompt tuning where you need the original structure intact.
Inspect first, copy once, then fork into Workspace when you want variants, notes, and model settings attached to the same run.
Swap domain facts, examples, and any hard-coded entities for your own context.
Tighten the evidence or verification requirement if this is headed toward production.
Decide which failure mode you want to evaluate first before you branch the prompt.
This prompt already carries implementation detail, tool context, and a final-output instruction. Keep that structure intact when you tune it, or your comparison runs get noisy fast.
Open this prompt inside Workspace when you want a live iteration loop.
Copy for quick reuse, or run it in Workspace to keep prompt variants, model settings, and prompt-history changes in one place.
Structured source with 23 active lines to adapt.
Already linked to a challenge workflow.
Sign in to keep private prompt variations.
Prompt content
Original prompt text with formatting preserved for inspection and clean copy.
Using the Claude Agents SDK, implement the 'Patent Analyst Agent'. This agent should be capable of:
1. Receiving a user query about patent novelty or prior art.
2. Utilizing Claude Opus 4.1 for deep textual understanding of patent claims.
3. Interacting with a Qdrant vector database (via a custom tool) to search for relevant prior art documents based on the claim text's embeddings.
4. Synthesizing an assessment of the patent's novelty, referencing retrieved documents.
Ensure your agent defines tools for interacting with Qdrant and uses Claude's advanced reasoning. You can mock the Qdrant interaction if a full setup is too complex initially.
```python
# Example of Claude Agents SDK basic structure (simplified)
# This will vary based on the latest SDK version, focus on patterns.
from anthropic.agents import AnthropicAgent, Tool
def search_qdrant(query: str) -> str:
# Simulate Qdrant search
print(f"Searching Qdrant for: {query}")
return "Found relevant prior art document US9876543B1 related to AI content generation."
qdrant_tool = Tool(
name="qdrant_search",
description="Searches the Qdrant vector database for patent documents.",
input_schema={"type": "object", "properties": {"query": {"type": "string"}}, "required": ["query"]},
function=search_qdrant
)
# Your agent definition will incorporate this tool
# agent = AnthropicAgent(model="claude-opus-4.1", tools=[qdrant_tool], ...)
```Adaptation plan
Keep the source stable, then branch your edits in a predictable order so the next prompt run is easier to evaluate.
Hold the task contract and output shape stable so generated implementations remain comparable.
Update libraries, interfaces, and environment assumptions to match the stack you actually run.
Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.
Copy once for a pristine source snapshot, then move the prompt into Workspace when you want variants, run history, and side-by-side tuning without losing the original.
Prompt diagnostics
Quick signals for how structured this prompt already is and where adaptation work is likely to happen first.
This prompt already mixes executable detail with instructions, so the safest path is to tune examples and interfaces before you rewrite the overall scaffold.
AI Patent Analysis & Cloud Optimization Agents
Create an intelligent assistant using Claude Agents SDK that helps navigate the complexities of AI patent law (inspired by the USPTO shift) and simultaneously optimizes cloud resource allocation for AI/ML workloads (addressing cloud backlog). The agent system should be capable of analyzing patent documents, extracting key claims, identifying relevant precedents, and providing recommendations for cloud cost reduction specific to AI infrastructure. The interface will be conversational, leveraging advanced reasoning and tool use.
Use the challenge page to recover the original task boundaries before you tune the prompt. That keeps your variants grounded in the same evaluation target instead of drifting into a different problem.