Design an AI pipeline where each step hands clean work to the next.
prompt.txt
Act as a systems designer for AI-assisted workflows. The end-to-end task: [describe task]. Tools I have: [list apps, AI tools, integrations]. Where humans must stay in the loop: [approval points]. Volume: [how often this runs].
Design the pipeline:
1. Break the task into 3-7 steps. For each: the input it needs, the exact instruction to give the AI or tool, and the output format it must produce.
2. Define the handoff contract between every pair of steps: what fields pass forward and what gets validated before the next step runs.
3. Mark the two steps most likely to fail and give a fallback for each.
4. Flag anything that should NOT be automated and why.
5. End with a one-paragraph description I can hand to a teammate so they can run this without me.
#automation#workflow
💡 Replace the [brackets] with your details — the more specific, the sharper the answer.
Sort a crowded inbox without losing the messages that matter.
Act as a practical specialist helping me with inbox triage blueprint. My context: [mail volume, categories, urgent senders, tools available].
1. Define priority tiers and exact inclusion rules.
2. Write example labels and false-positive cases.
3. Design a daily review queue and escalation path.
4. Give a five-message test set with expected labels..
Use my details, not a generic example. If a fact needed for the plan is missing, ask for it or mark the assumption. Keep the result ready to use.
Turn a broad question into a source-checked investigation.
Act as a practical specialist helping me with ai research brief architect. My context: [question, decision it supports, deadline, sources allowed].
1. Break the question into falsifiable subquestions.
2. Set a source hierarchy and recency requirements.
3. Create an evidence table with claim, source, date, confidence.
4. Specify when to stop researching and how to flag gaps..
Use my details, not a generic example. If a fact needed for the plan is missing, ask for it or mark the assumption. Keep the result ready to use.
Make messy documents yield clean, auditable fields.
Act as a practical specialist helping me with document extraction schema. My context: [document types, fields needed, sample document, downstream use].
1. Design a JSON schema with field types and null handling.
2. Write extraction rules with exact quote or page evidence.
3. List ambiguous cases and a human-review threshold.
4. Produce three test cases including a missing field..
Use my details, not a generic example. If a fact needed for the plan is missing, ask for it or mark the assumption. Keep the result ready to use.