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 1 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.
Design and implement a data pipeline for ingesting simulated telco network traffic logs (e.g., NetFlow, firewall, syslog). Pre-process this data, perform necessary feature engineering, and then train a baseline anomaly detection model (e.g., Isolation Forest or Autoencoder) to identify deviations from normal network behavior. Document your data schema and feature set.
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 is mostly narrative and instruction-driven, so you can adapt examples and output constraints first without disturbing the structure.
AI-Driven Telco Network Anomaly & Threat Detection
Telecommunication networks are vital infrastructure, constantly targeted by cyber threats and susceptible to operational anomalies that can impact service quality and security. This challenge focuses on building an advanced, AI-driven system capable of real-time anomaly and threat detection within a simulated telco network environment. The system should identify unusual traffic patterns, unauthorized access attempts, or performance degradations that deviate from normal operational baselines. Participants will employ sophisticated AI models and orchestration frameworks. Mixtral 8x22B (or a compatible open-source mixture-of-experts model) will serve as the core analytical engine, processing network telemetry data to identify complex anomalies and categorize potential threats. AutoGen will be used to orchestrate a multi-agent system, automating the data ingestion, anomaly scoring, alert generation, and initial response recommendation workflows. Furthermore, RAGAS will be critical for evaluating the quality and relevance of explanations or summaries generated by the AI system for human operators, ensuring the alerts are actionable and transparent. The primary goal is to create a proactive defense mechanism for telco networks, significantly reducing detection and response times to emerging threats and anomalies. Success will be measured by the system's accuracy in identifying anomalies, the efficiency of its automated workflows, and the clarity and helpfulness of its threat intelligence outputs.
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.