Skip to main content
Back to Prompt Library
implementation

Configure CrewAI & Agno KV Cache Planner

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

Linked challenge: CrewAI & Agno Long-Context KV-Cache Capacity Planner

Format
Code-aware
Lines
7
Sections
4
Linked challenge
CrewAI & Agno Long-Context KV-Cache Capacity Planner

Prompt source

Original prompt text with formatting preserved for inspection.

7 lines
4 sections
No variables
0 checklist items
from crewai import Agent, Crew, Task
from agno.agent import Agent as AgnoAgent

# Define Agno telemetry agent
telemetry_agent = AgnoAgent(name='VRAM Monitor', instructions='Track GPU memory fragmentation and KV-cache blocks')

# Define CrewAI capacity planning agent
planner_agent = Agent(role='Capacity Planner', goal='Compute precise KV-cache bounds for GQA models', backstory='Expert in LLM VRAM allocation')

# Create task to evaluate context scaling up to 1M tokens

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.