# Compare options and recommend one

Weigh two or more options against your criteria and hard limits, see the trade-offs side by side, and get a recommendation when the facts support one.

Paste into: **a new Claude conversation**

## Prompt template

How the builder on the page fills in this template, so you can do the same:

- `{{key}}` becomes the text entered for that field, exactly as typed. Empty text, or text that is only whitespace (spaces, tabs or line breaks), counts as empty: a required field then becomes `[fill in: <label>]` with its label, and an optional field becomes nothing.
- For a choice field, `{{key}}` becomes the text of the chosen option, or of the default when none is chosen.
- Text between `{{#key}}` and `{{/key}}` stays only when that field is not empty; a choice field always counts as filled. The markers themselves are removed, and a marker that stands alone on its line takes its line break with it.
- Each value is inserted once, as it is: `{{…}}` inside a value stays as typed.

```text
<options>
{{options}}
</options>

Help me decide: {{decision}}
{{#criteria}}

My criteria, most important first:
{{criteria}}
{{/criteria}}
{{#constraints}}

Hard limits: {{constraints}}
{{/constraints}}

Please:
1. If I gave no criteria, propose up to five, most important first, and ask me to confirm them before you compare or recommend anything. Stop there.
2. Exclude any option that breaks a hard limit and say why. If it is unclear whether an option meets a limit, mark it as unresolved instead of excluding it. If no option qualifies, say so and stop.
3. Compare the remaining options in a table, one row per criterion.
4. Name the most important trade-off between the leading options.
5. Recommend one option only if the facts support the choice, and explain why in a few sentences, including what would change your recommendation. If key facts are missing, list what I need to find out first instead.

Use only the facts I gave about each option. Where a comparison depends on something I did not provide, write "unknown" in the table and list what I should find out, instead of filling the gap with assumptions.
```

## Fields

- `{{decision}}` (required): The decision.
- `{{options}}` (required): The options. Give each option a name and the facts you have: prices, features, limits, your experience with it.
- `{{criteria}}`: What matters most. Optional. List criteria in order of importance. If you leave this empty, the prompt asks Claude to suggest criteria for your confirmation before comparing.
- `{{constraints}}`: Hard limits.

This site doesn't run Claude or show model output. Results depend on your input and the model you use.

## When to use this template

- You have a short list of options and need a clear, defensible choice rather than an open discussion.
- You want the trade-offs laid out against criteria you set, so the reasoning can be shared with others.
- You suspect you are missing information and want a list of what to find out before deciding.

## When not to use it

- You have not gathered any facts about the options yet. Collect the basics first; a comparison built on guesses only looks precise.
- The decision depends on current prices, reviews or availability that you have not provided. Claude here works only with the facts you paste.
- The choice is personal or values-based with no criteria to weigh. A conversation about what you care about is a better starting point.

## Why this structure

- The option descriptions come first inside `<options>` tags, followed by the decision and your criteria, which helps Claude keep your facts apart from the task.
- Hard limits work as a filter: the prompt asks Claude to drop options that break them before comparing the rest, to mark unclear cases as unresolved, and to say so if nothing qualifies.
- Criteria are ordered by importance, which tells Claude how to weigh them. If you leave them out, the first step asks Claude to suggest criteria and wait for your confirmation, so the comparison uses criteria you agreed to.
- The table with "unknown" cells makes gaps visible, and the closing paragraph tells Claude not to fill them with assumptions.
- A recommendation is requested only when the facts support it, and asking what would change it gives you a decision you can revisit when the facts change.

## Example input (fictional)

The decision:

```
Which note-taking app our five-person design studio should use
```

The options:

```
Option A: Inkwell (fictional). 6 per person per month, works offline, no shared folders.
Option B: Paperlane (fictional). 9 per person per month, shared folders, web only.
Option C: Keep using shared documents. Free, already familiar, hard to search.
```

What matters most:

```
1. Sharing between team members 2. Search 3. Cost
```

Hard limits:

```
Must cost under 60 per month in total
```

## Follow-ups to send Claude

- Assume cost matters more than search. Does the recommendation change?
- Write a short note to my team explaining the choice and the main trade-off.
- For each "unknown" cell, suggest the quickest way to find the answer.

## Common mistakes

- Listing options with very different amounts of detail. The option you know best tends to win; give each one comparable facts.
- Treating the recommendation as final. It is only as good as the facts and criteria you supplied; check the table before the conclusion.
- Mixing hard limits with preferences. Put deal-breakers in the hard limits field so they are applied as filters, not weighed.

## Related templates

- [Critique an argument](https://awesomeclaudeprompts.com/prompts/critique-argument/): Test an argument before you rely on it: its main claim, hidden assumptions, weak links and the strongest objection, with fixes.
- [Analyze customer feedback](https://awesomeclaudeprompts.com/prompts/analyze-customer-feedback/): Group raw customer comments into themes, priorities or feature requests, with counts and quotes that show where each finding comes from.

## Sources

- [Prompting best practices: Be clear and direct](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#be-clear-and-direct) (Anthropic documentation)
- [Prompting best practices: Structure prompts with XML tags](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#structure-prompts-with-xml-tags) (Anthropic documentation)
- [Reduce hallucinations](https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/reduce-hallucinations) (Anthropic documentation)

---

Awesome Claude Prompts is an independent project. It is not affiliated with, endorsed by, or sponsored by Anthropic. Claude is a trademark of Anthropic, PBC.