PromptSharp › Daily briefs › November 19, 2026
PromptSharp Daily · free web issue · #145Prompt of the day
November 19, 2026 · the free cross-vertical sampler: get better at AI and prompting, and see the sharpest prompts from across the network. Today's comes from Learning.
Exam plan from your practice-test breakdown to the weeks you have left
You took a practice test and got a score and a breakdown. Turn that breakdown into a plan that puts your remaining weeks where the points actually are.
You are an exam coach who plans from diagnostic data, not from the syllabus order. I will paste my practice-test results by section or topic, the exam's published weighting if I have it, my exam date and my weekly hours. Produce: A) THE DIAGNOSIS TABLE — for each section or topic: my score, the exam weighting (quoted from what I pasted, or "not provided"), and the points available if I improved. Rank topics by likely points gained per hour of study, and show the reasoning. B) THE ERROR TYPES — from the questions I got wrong (if I paste them or describe them), sort my mistakes into: did not know the content, knew it but misread the question, ran out of time, or careless. Each type needs a different fix; say which dominates. C) THE WEEKLY PLAN — my remaining weeks laid out: which topics each week, the mix of learning new content versus timed practice, and a full practice test every two or three weeks. D) THE TIMING PLAN — if time pressure cost me points, a pacing plan per section and how to practise it. E) THE LAST WEEK — what to do in the final seven days (review and light practice, no new topics) and the night before. Inputs: [PASTE PRACTICE-TEST RESULTS BY SECTION OR TOPIC] · [THE QUESTIONS I GOT WRONG, OR A DESCRIPTION] · [EXAM WEIGHTING, IF PUBLISHED] · [EXAM DATE] · [HOURS PER WEEK] Rules: Do not invent exam weightings, pass marks, section names or question formats — use only what I pasted and tell me to verify against the official exam guide. Do not invent study resources; describe what to look for. Do not predict my final score. Do not invent facts, sources, citations, links, or specifics you cannot support — say "I'm not sure" instead, and mark anything I must verify for myself rather than asserting it. Never paste confidential, client, medical, or personally identifying information into a consumer AI tool, and don't ask me for any.
Why it works — Most exam study follows the syllabus in order, spending equal time on topics regardless of where the points are. Ranking topics by points available per hour, and sorting wrong answers by error type, puts the remaining weeks on the gaps that cost the most, and separating content gaps from timing or misreading errors stops you re-studying material you already know.
Use AI today — a workflow to steal
Ask AI to grade its own answer and redo it as a 10
Models settle for 'good enough' on the first pass. One self-critique loop routinely lifts quality more than a longer original prompt.
After any output you find just okay, reply: 'Rate that 1-10 against what a top expert would produce, explain the gap, then rewrite it as a 10.'
- Get the first draft.
- Send the rate-and-improve line.
- Repeat once more if needed.
Sharpen it: For anything complex, break the ask into steps: outline first, then draft section by section. Big single asks produce shallow results; staged asks go deep.
Elsewhere in the network today
Two professional briefs and one personal brief, rotating daily — every one of them free to read right now.
C-suite
Today in C-suite: Monthly investor update: the numbers, the asks, and the bad news up front
Law
Today in Law: Defined-terms and cross-reference audit: the drafting errors that break a contract
Career & Job Search
Today in Career & Job Search: Achievement mining: let the model interview you until vague duties become measurable results
What changed in AI today
‘In for a Penny’ in AI. Nvidia, Anthropic & Waymo. ARD #209
Read this as a signal, not a to-do. The operators who stay current — scanning 5 minutes a day — compound a real edge over peers who tune AI out until it's forced on them. File it, watch the trend,…
Happy Anthropic IPO GTA VI Hunger Games eve
Follow the money in your own sector. Where AI capital is flowing signals where competitive pressure and customer expectations are heading next — use it to time your own AI bets, don't get caught…
🔔 Opening Bell: Anthropic and GTA VI arrive
No action required today — but note it. The operators who keep a running map of where AI is moving spot the shift that touches their work weeks before the ones who wait to be told. Log it and move on.
Subscribe free — PromptSharp Daily
One sharp, copy-paste prompt most weekday mornings, rotating across every vertical, plus a workflow to steal and a Sunday roundup. If a day's issue misses our quality bar, we hold it instead of padding your inbox. Free forever, double-opt-in, unsubscribe anytime.
Go Pro — the full set, personalization, and MCP
Free = today's prompt. Pro unlocks the full weekday prompt set in your vertical, personalization, and MCP access straight inside Claude, ChatGPT or Cursor.
See pricing → Browse free prompts← 2026-11-18 · All daily briefs
Even a sharp prompt starts from zero unless your AI knows you. Brainfile is persistent context — your work, voice, and priorities loaded into every session. Brainfile is the memory; PromptSharp is the playbook. Together they compound — the same prompt gets sharper because it runs on YOUR context.
Set up your brainfile →Want both? The All-Access + Brainfile annual bundle covers the pair.
Home · Daily Issues · Prompt Library · Glossary · Pricing · For Teams & Universities · Archive · PromptFluent alternative · Newsletter · PromptSharp on Substack · Privacy · Terms · Refunds
Marketing · Sales · Dev & Engineering · Finance · Product Management · Vibe Coding · C-suite · Consulting & Strategy · Law · CPG · Personal Finance · Career & Job Search · Trading · Health & Fitness · Students · Focus & Productivity · Learning · Travel Planning
Entry Point Trading
Free weekly stocks to watch —
how our model ranks the S&P 500 and Nasdaq 100.