Book Recommender (Honest)
Recommends 3-5 books based on what you actually liked before. No 'Sapiens for the 400th time.' Includes honest reasons and what NOT to expect.
The prompt
I want book recommendations. Help me pick 3-5. Ask me: - 3-5 books I've loved (and why, briefly, if I know) - 1-2 books I've hated (and why) - What I'm looking for: similar to what I love, adjacent, or a stretch - Non-fiction / fiction / either - Time commitment: short (under 250 pages), medium (250-450), doorstop (450+) Then output 3-5 recommendations, each in this format: **Title** — Author (Year) **Why this one for you** — 2-3 sentences tying it specifically to what I said I liked. **What to expect** — genre, structure, pace, difficulty. **What NOT to expect** — the common disappointment. "It's not a thriller even though the cover suggests it," "the first 100 pages are slow," "the author's next book is better, this is where he warms up." **If you like this, try next** — one further pick. Rules: - No default "everyone reads this" picks unless I actively haven't read them and they fit. Skip Sapiens, Atomic Habits, Meditations, The Alchemist, unless truly relevant. - Don't recommend a book you'd need to caveat as "problematic" without saying why. - If I gave you weird combinations of loves and hates, ask one question to clarify before generating. - Never invent a book. If you're not sure a book exists, don't include it. ## How to use it Paste this prompt, answer the questions honestly. Screenshot the recs to your notes. Try one, come back and iterate. ## Why it works Most AI book recs default to bestsellers. Anchoring to your actual likes/dislikes and forcing "what NOT to expect" produces recommendations you'll actually finish instead of abandoning at chapter 3.
How to use it
I want book recommendations. Help me pick 3-5.
Ask me:
- 3-5 books I’ve loved (and why, briefly, if I know)
- 1-2 books I’ve hated (and why)
- What I’m looking for: similar to what I love, adjacent, or a stretch
- Non-fiction / fiction / either
- Time commitment: short (under 250 pages), medium (250-450), doorstop (450+)
Then output 3-5 recommendations, each in this format:
Title — Author (Year)
Why this one for you — 2-3 sentences tying it specifically to what I said I liked.
What to expect — genre, structure, pace, difficulty.
What NOT to expect — the common disappointment. “It’s not a thriller even though the cover suggests it,” “the first 100 pages are slow,” “the author’s next book is better, this is where he warms up.”
If you like this, try next — one further pick.
Rules:
- No default “everyone reads this” picks unless I actively haven’t read them and they fit. Skip Sapiens, Atomic Habits, Meditations, The Alchemist, unless truly relevant.
- Don’t recommend a book you’d need to caveat as “problematic” without saying why.
- If I gave you weird combinations of loves and hates, ask one question to clarify before generating.
- Never invent a book. If you’re not sure a book exists, don’t include it.
How to use it
Paste this prompt, answer the questions honestly. Screenshot the recs to your notes. Try one, come back and iterate.
Why it works
Most AI book recs default to bestsellers. Anchoring to your actual likes/dislikes and forcing “what NOT to expect” produces recommendations you’ll actually finish instead of abandoning at chapter 3.
✦ More like this
Related prompts
Chart Type Chooser
Given the data you have and the question you're answering, picks the right chart type and explains what to avoid. No dual-axis, no pie chart traps.
Code Refactor Helper
Refactors a function or file without changing behavior. Explains what changed and why, and flags any behavior it wasn't sure about.
Cold Email Drafter
Writes a cold email that references a specific signal about the prospect, states one relevant point, and ends with a low-friction ask. No templated fluff.