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.
Convert transcripts into trustworthy follow-through.
Act as a practical specialist helping me with meeting notes automation. My context: [meeting type, transcript sample, destination tool, team norms].
1. Separate decisions from suggestions and open questions.
2. Map action, owner and deadline without inventing them.
3. Write a human-review checkpoint before sharing.
4. Define duplicate prevention and one-week follow-up..
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.
Help agents answer faster without making up policy.
Act as a practical specialist helping me with support reply copilot. My context: [support issue types, approved policy text, brand voice, escalation route].
1. Build a retrieval-first answer flow.
2. Draft three replies for resolved, unclear and escalation cases.
3. Mark claims that require a policy citation.
4. Define what the AI must never promise and a human handoff trigger..
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.
Test a workflow against instructions hidden in outside content.
Act as a practical specialist helping me with prompt injection stress test. My context: [workflow goal, trusted instructions, untrusted sources, available tools].
1. Write ten realistic injected snippets across email, page and PDF surfaces.
2. For each name the attempted deviation and safe expected behavior.
3. Grade the workflow against those tests.
4. Recommend boundaries without quoting secrets or live private data..
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.
Score generated answers on evidence, usefulness and errors.
Act as a practical specialist helping me with ai output evaluator. My context: [task, good answer example, failure examples, audience].
1. Create a five-criterion rubric with anchored scores 1 to 5.
2. Separate factual accuracy from presentation.
3. Write a blind comparison protocol for two outputs.
4. Give a template for recording disagreements and revisions..
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.
Organize notes so retrieval finds the right fact later.
Act as a practical specialist helping me with personal knowledge vault map. My context: [current note sources, use cases, privacy limits, update frequency].
1. Propose a folder and tagging scheme with five example notes.
2. Define canonical records and provenance fields.
3. Show dedupe and conflict-resolution rules.
4. Design a monthly stale-fact audit and search examples..
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 multistep AI work survive a change of worker.
Act as a practical specialist helping me with agent handoff contract. My context: [workflow, actors, tools, failure modes].
1. Define the minimum handoff packet: original goal, authority, verified facts, pending choices and durable IDs.
2. Write a sample handoff.
3. Add a readback checklist and duplicate-write recovery procedure.
4. Identify information that must not cross the handoff..
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.