Explore Prompts

Design a finance AI roadmap: close automation, variance analysis, forecasting, and controls. Include policy for human sign-off and metrics tied to close time and accuracy.

Create a strategy for agentic CRM: lead research, email drafting, call summaries, next-best-action, and governance for customer data. Include ‘do-not-do’ rules and auditability.

Design an agent-enabled support strategy: deflection without hallucinations, verified knowledge, escalation, QA sampling, and customer trust metrics. Include a phased rollout and KPI ladder.

Propose a talent strategy: ‘forward-deployed engineers’ model, upskilling paths, incentives, and org design for AI product delivery. Include hiring profiles and interview rubrics.

Write a procurement playbook: evaluation criteria, red flags, security review, data terms, SLAs, pricing traps, and exit clauses. Include a scoring matrix and interview questions for vendors.

Create an AI governance program aligned to common frameworks: policy stack, model inventory, risk register mapping, approvals, audits, and incident management. Provide templates and RACI.

Draft a 2026 cost engineering playbook: caching, quantization, distillation, batching, and SLA tiers. Provide a KPI dashboard linking cost per task to business outcomes.

Propose a model routing architecture (‘model mesh’): task-based routing, fallback policies, confidence thresholds, and cost controls. Include an observability plan for routing quality.

Create an enterprise unstructured data strategy: ingestion, classification, redaction, indexing, provenance, and access control. End with a ‘document-to-decision’ workflow and KPIs.

Design a hybrid retrieval strategy combining vector search, lexical search, and a knowledge graph layer (‘Graph-RAG’). Specify when to use which, how to evaluate, and how to keep citations reliable.

Create an eval-first LLMOps design: golden sets, adversarial tests, continuous regression, cost/latency tracking, and release gates. Include a ‘model change control’ policy.

Build a P&L-style ROI model for deploying agents as digital workers: labor displacement vs augmentation, quality risk, error cost, cycle time reduction, and governance overhead. Provide a template with assumptions.