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.
Elaborate on the `CRMAccessTool` by integrating Aembit for secure, policy-based access to a simulated CRM system. The tool should enforce granular permissions, ensuring the `SalesGuidanceAgent` can only retrieve data relevant to its current context and authorized by Aembit. Show how the agent would dynamically call this tool based on a sales query requiring customer-specific information. Detail the Aembit policy structure that would govern this access. Also, incorporate Libretto for routing requests to Llama 4 Maverick, ensuring optimal model selection and performance.
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 is mostly narrative and instruction-driven, so you can adapt examples and output constraints first without disturbing the structure.
Real-time Personalized Sales Guidance
This challenge involves developing a sophisticated multi-agent system using the Claude Agents SDK to provide personalized, real-time sales guidance. The system will act as an intelligent sales assistant, offering deal-specific recommendations, objection handling strategies, and next-step actions to sales representatives. The core of this system will be its ability to understand complex sales conversations and leverage extensive knowledge for strategic advice. Developers will design agents with extended thinking capabilities using Claude 4 Sonnet, which will then interact with a specialized 'Knowledge Agent' powered by Llama 4 Maverick for in-depth data retrieval and synthesis from various sales enablement resources. The system will integrate with a secure access platform like Aembit to ensure controlled and auditable access to sensitive CRM data. Libretto will be used for intelligent model routing and A/B testing of different guidance strategies, optimizing performance. Bito AI will serve as the conversational interface for sales reps, providing instant, context-aware advice. The overall agent orchestration will leverage Letta AI's capabilities for managing agent lifecycles and tool orchestration.
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.