AllNutrition

View saved version →

---
name: compact-references
description: Produce a compact, numbered reference list from AllNutrition results. Use when the user asks for "the references", "the sources", "a bibliography", or a copy-pasteable/shareable citation list — either for an answer AllNutrition already gave in this conversation or for a fresh topic.
---

# Compact reference list

Turn AllNutrition source lists into a short, numbered, plain-text bibliography
that fits in a tight character budget without losing any links.

## Input

One of:

- A prior `ask_nutrition` or `search_references` result in this conversation
  whose `sources` the user now wants listed.
- A fresh topic ("give me references on magnesium and sleep") with no prior
  result — call `search_references` with the topic first (default
  `max_results`, add `published_after` only if the user asked for recent work).

## Procedure

1. Collect the sources. Use only the `sources` array returned by AllNutrition
   tools. Never add sources from memory or the open internet, and never invent,
   guess, or "fix" a URL — reproduce each URL exactly as returned.
2. Deduplicate by URL, keeping the first occurrence. If the list annotates an
   existing answer's citations, keep the numbering the answer used so the
   numbers still match; otherwise number from 1 in the returned order.
3. Render one line per source in exactly this shape:

   ```
   References:
   1. Title https://example.org/...
   2. Title https://example.org/...
   ```

4. Fit the whole block into the character budget: 4,900 characters total
   unless the user gives a different limit. Shorten only the titles, never the
   URLs. Truncate every title at the same maximum length and append `...` to
   any title you cut; pick the largest uniform title length that keeps the
   whole block under budget. With a typical list of 10 sources, full titles
   usually fit — only shorten when they don't.

## Output

Only the `References:` block, ready to copy. No commentary, no verbatim
excerpts or quotes from the sources, no markdown link syntax (bare URLs are
the point — they survive copy-paste into plain-text contexts).

## Boundaries

- If there are no sources to list (the tool returned none, or the prior answer
  had none), say so — do not fill the gap with sources of your own.
- If the user asks for full abstracts or verbatim passages, explain that
  AllNutrition returns AI-written summaries, not verbatim source text, and
  offer the source links instead.

View saved version →

---
name: evidence-comparison
description: Compare two or more nutrition claims, diets, supplements, or interventions using AllNutrition's cited evidence. Use for "X vs Y" questions, "which is better for…", or whenever the user wants competing claims evaluated side by side rather than a single answer.
---

# Evidence comparison

Put competing nutrition claims side by side with the evidence behind each one,
so the user sees not just which option looks better but how sure the science
actually is.

## Input

Two or more named options and the outcome they should be compared on — e.g.
"creatine vs beta-alanine for strength", "Mediterranean vs low-carb for
longevity". If the outcome is missing, ask for it before calling any tool: a
comparison without an outcome is not answerable.

## Procedure

1. Call `ask_nutrition` once per option, phrasing each question identically
   except for the option ("Does X improve <outcome>?"). Identical phrasing
   keeps the answers comparable. Use `deep_research: true` only when the user
   explicitly asks for a deep or comprehensive review — it takes minutes per
   call, so mention the wait before starting.
2. Read each answer's `evidence_strength` (strong | moderate | limited |
   insufficient) and `consensus_level` (high | moderate | mixed | low). These
   labels are the comparison's backbone — never omit or soften them.
3. Compare only what the returned evidence supports. If the evidence for the
   two options was studied in different populations or doses, say so instead
   of forcing a winner.

## Output

1. A one-or-two-sentence verdict up front, hedged to match the weaker side's
   evidence labels.
2. A table with one row per option: what the evidence shows, `evidence
   strength`, `consensus`.
3. A single combined reference list for all options, deduplicated by URL, in
   the compact numbered format (`n. Title URL`) — cite only sources the tools
   returned.
4. A closing note naming the biggest gap or caveat (e.g. "no head-to-head
   trials; both compared to placebo separately").

## Boundaries

- Never declare a winner when both sides are `limited`/`insufficient` or
  consensus is `mixed`/`low` — say the evidence cannot separate them.
- Describe what the research shows for populations, not what this user should
  personally do; nutrition evidence is not a personal prescription.
- If the user adds their own claimed study ("I read that X cures Y"), check it
  against `search_references` results rather than accepting or contradicting
  it from memory.