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.
Act as a practical specialist helping me with human review gate designer. My context: [automated workflow, possible harms, reviewer, turnaround time].
1. Map reversible and irreversible steps.
2. Pick review gates based on consequence rather than habit.
3. Draft the approval card showing exact action and recipient or cost.
4. Set expiry, change detection and audit log rules..
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.
Translate messy business logic into tested sheet formulas.
Act as a practical specialist helping me with spreadsheet formula assistant. My context: [platform, column schema, examples, edge cases].
1. Restate the intended calculation in plain English.
2. Write the formula with absolute and relative references explained.
3. Test normal, blank, duplicate and zero cases.
4. Offer a simpler helper-column version if the single formula is brittle..
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.
Act as a practical specialist helping me with data cleaning recipe. My context: [columns, sample rows, known quality issues, expected output].
1. Identify type and format checks per column.
2. Propose deterministic normalization rules.
3. Quarantine ambiguous rows instead of guessing.
4. Give before-after examples and a validation report with row counts..
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.
Act as a practical specialist helping me with ai workflow roi calculator. My context: [task frequency, minutes per run, error cost, setup and review time].
1. Compute weekly and annual time saved after review overhead.
2. Estimate break-even with low, base and high adoption.
3. Include maintenance, exception and quality costs.
4. State the smallest pilot and stop rule..
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.
Act as a practical specialist helping me with search query decomposer. My context: [question, data sources, permissions, known terms].
1. Extract exact names and synonyms into separate queries.
2. Rank sources by authority and freshness.
3. Make a search order that avoids broad scans.
4. Specify how to reconcile conflicting hits and cite the final answer..
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.
Act as a practical specialist helping me with workflow failure simulator. My context: [workflow steps, inputs, external dependencies, critical deadline].
1. Generate ten failure scenarios ordered by probability and impact.
2. For each give detection signal, safe fallback and recovery owner.
3. Design two chaos tests that do not touch production.
4. Define a post-incident learning template..
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.
Keep generated copy sounding like the same person.
Act as a practical specialist helping me with ai tone guardrail. My context: [writing samples, audience, prohibited phrases, channel].
1. Extract measurable style features from the samples.
2. Write a do-and-don't guide with genuine examples.
3. Rewrite one generic paragraph in that voice.
4. Create a five-question final-review checklist..
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.
Run large AI jobs without duplicate sends or runaway costs.
Act as a practical specialist helping me with batch job safety checklist. My context: [job objective, batch size, write destinations, budget].
1. Design a dry run with representative records.
2. Set dedupe keys and idempotent write rules.
3. Define per-batch checkpoints and stop conditions.
4. Specify error reconciliation and an exact count report..
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.
Act as a practical specialist helping me with citation checker. My context: [draft answer, cited links or documents, stakes].
1. List every checkable claim in a table.
2. Mark which source passage actually supports each.
3. Flag unsupported inference and stale figures.
4. Rewrite only the claims with evidence gaps and list what must be verified live..
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.
Summarize private material without leaking the wrong details.
Act as a practical specialist helping me with privacy-safe summarizer. My context: [source text, intended audience, purpose, sensitive fields].
1. Separate facts needed by this audience from irrelevant private details.
2. Redact identifiers with a consistent mapping.
3. Write the minimal summary and an internal omissions list.
4. Check that quotes and metadata do not re-identify people..
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.
Move a useful prototype into dependable daily use.
Act as a practical specialist helping me with ai project launch checklist. My context: [prototype, users, integrations, hosting, owner].
1. Define acceptance tests with real-world edge cases.
2. Check permissions, observability, rollback and cost ceiling.
3. Write a staged rollout to five, fifty and all users.
4. Set the first-week dashboard and intervention triggers..
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.