Automation Candidate Finder
The 5-dimension scoring system prevents automating low-value tasks just because they're easy, focusing effort on the highest ROI opportunities.
Review my team's recurring tasks and identify the best candidates for AI automation.\n\nTeam: {{team_description}}\nRecurring tasks:\n{{tasks_list}}\n\nFor each task, evaluate against these automation criteria:\n1. Repetitiveness (1-5): how similar is each instance?\n2. Rule-based (1-5): how clearly can the task be specified?\n3. Error tolerance (1-5): how critical is perfection? (5 = errors are fine)\n4. Volume (1-5): how frequently does this occur?\n5. Current time cost: hours per week\n\nRank all tasks by automation ROI (time saved x feasibility).\nFor the top 5 candidates, provide:\n- The AI tool best suited for automation\n- The prompt template needed\n- Estimated time to set up\n- Expected time savings per week\n- Human review requirements (fully automated vs human-in-the-loop)
Variables to customize
Why this prompt works
The 5-dimension scoring system prevents automating low-value tasks just because they're easy, focusing effort on the highest ROI opportunities.
Save this prompt to your library
Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.
Related prompts
Forcing the agent to plan before acting prevents premature execution and wasted steps. Explicit dependency mapping enables parallel execution and catches logical gaps early.
Tool Selection AgentThe ReAct pattern (Reason + Act) creates an explicit reasoning trace that improves tool selection accuracy. The error-handling rule prevents infinite retry loops.
Prompt CompressorExplicitly requiring all functional requirements to be preserved prevents the model from over-compressing and losing critical instructions.
Memory Management AgentExplicit memory read/write instructions create agents that improve over time. Categorization keeps memories organized, and the deduplication rule prevents context bloat.