Automation & Agents Prompts

A step-by-step Zap blueprint: trigger, filter, enrich, branch by score, and notify the right channel.

Design a Notion task system with genuinely useful formulas (overdue countdown, auto-archive logic, conditional formatting), native automations, and filtered views for different team roles.

Blueprint a Make.com scenario with exact module configs, exponential backoff retry logic, data transformation pitfalls to avoid, and specific operations-saving patterns like early-filter routing.

Design strict, self-validating tool schemas with confidence calibration, discriminated unions, and chain-ready contracts — so your agent calls tools reliably instead of hallucinating arguments.

Turn a goal into a coordinated planner→worker→critic agent workflow with clear handoffs and a stop condition.

Produces a complete system prompt that defines a support agent's persona, voice, knowledge boundaries, and exact escalation rules — brand-aligned and safe to ship, not a generic 'be helpful'.

Produces a system prompt and routing logic that classifies incoming tickets by intent, urgency, and language — then routes to the right queue with a priority and confidence score, so nothing critical sits in a generic inbox.

Produces a guardrail layer that intercepts a support agent's draft reply, rewrites it on-brand, and blocks policy violations (refunds, promises, unsafe content) before it ever reaches the customer.