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 33 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.
Set up a basic AutoGen environment. Define at least three agents: a `UserProxy` agent, a `ContextAnalyst` agent (which understands user history and current context), and an `ActionPlanner` agent (which decides what tools to use or what information to retrieve). Ensure they can communicate. Provide Python code for initialization.
```python
import autogen
# Configuration for LLM (replace with your actual Gemini setup)
config_list = [
{
"model": "gemini-2.5-pro",
"api_key": "YOUR_GEMINI_API_KEY", # Or via Google Vertex AI setup
"base_url": "..." # if using custom endpoint
}
]
# User Proxy Agent
user_proxy = autogen.UserProxyAgent(
name="user_proxy",
human_input_mode="NEVER",
max_consecutive_auto_reply=10,
is_termination_msg=lambda x: x.get("content", "").rstrip().endswith("TERMINATE"),
code_execution_config=False, # Disable code execution for this challenge
)
# Context Analyst Agent
context_analyst = autogen.AssistantAgent(
name="context_analyst",
llm_config={"config_list": config_list},
system_message="You are an expert at understanding user intent, extracting preferences from history, and identifying relevant context. Your goal is to provide insights to the ActionPlanner."
)
# Action Planner Agent
action_planner = autogen.AssistantAgent(
name="action_planner",
llm_config={"config_list": config_list},
system_message="You are an expert planner. Based on context from the ContextAnalyst, you decide what actions to take or what information to retrieve. You can suggest tools or information needs. Conclude your plan with 'PLAN_COMPLETE'."
)
# (Further agents and group chat setup will go here)
```Adaptation plan
Keep the source stable, then branch your edits in a predictable order so the next prompt run is easier to evaluate.
Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.
Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.
Check whether the prompt asks for the right evidence, confidence signal, and escalation path.
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.
Build Proactive Personalized Assistant with AutoGen & Gemini 2.5 Pro
Inspired by Apple's shift towards a personalized, Gemini-powered Siri, this challenge tasks you with building a sophisticated multi-agent system using Microsoft's AutoGen framework. The goal is to create a proactive digital assistant that anticipates user needs, learns from interactions, and leverages dynamic tool use to provide personalized assistance in real-time. This system should be capable of understanding complex user contexts, synthesizing information from various sources, and initiating relevant actions without explicit prompting, mimicking a truly intelligent personal assistant.
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.