"Ship agents that actually work—hours back, not hype. Tool-augmented assistants, not sci-fi—save 6+ hours a week. Automate the boring parts, keep judgment where it belongs.”
All
Modifiable
LLM-Conversation
All
This prompt guides the design of a Research Agent.
This prompt explains that the agent connects to external systems via MCP (Model Context Protocol) servers.
This prompt will interview you and help you pick the right agent—will work for you personally or for your team as a whole
This prompt describes an agent workflow built on a visual canvas with drag‑and‑drop nodes. Fill in the template to outline each node’s role, data flow, and handoffs.
This prompt guides the design of a Data Enrichment research agent
This prompt defines your agent’s safety boundaries through clear, enforceable rules. Complete the template to specify allowed actions, prohibited behaviors, and escalation paths.
This prompt centralizes agent logic and control flow in the API layer. It defines the agent—not individual chat turns—as the fundamental unit.
This prompt guides the design of a Customer Support–style research agent.
This prompt guides the design of test cases for your agent. Define inputs, expected outputs, edge conditions, and pass/fail criteria to validate behavior end-to-end.
This prompt defines when and how humans should intervene in the agent’s workflow. Specify triggers, roles, and decision points for review, approval, and override.
This prompt guides you to write a complete agent specification by filling in the provided template. Document goals, capabilities, tools, interfaces, safety rules, and evaluation criteria for end-to-end clarity.
This prompt outlines recovery strategies for each potential failure point. Specify detection signals, fallback actions, and escalation steps for quick, safe resolution.
This prompt helps translate an existing SOP or flow into a ChatGPT agent design. It maps each step to agent roles, tools, and handoffs for reliable execution.
Master framework for building Notion AI agents with standardized sections for role, scope, data models, and quality checks. Customize bracketed parameters to build custom workflows for any use case
Transforms raw meeting notes into structured PRDs with problem statements, success metrics, non-goals, risk matrices, evaluation plans, and auto-generated task backlogs for engineering/design/data/launch teams. Runs acceptance checks on each PRD before publishing.
This strategic diagnostic helps leaders make informed decisions about AI agent deployment by analyzing organizational context against six key principles: architecture vs models, institutional memory, workflow completion, vertical specialization, compliance infrastructure, and implementation velocity. It provides urgency assessment, architectural recommendations, first workflow targets, memory strategy, blocker resolution, and 30-day action plans tailored to specific organizational situations.
Notion AI agent that treats prompt variants like code, running them through user-defined evaluation rules with automated scoring, version tracking, and regression detection. Identifies top-performing prompt variants with specific pass/fail criteria.