# Ordering Content in a Long Context — Prompt & Context Engineering

Source: https://www.skillbyai.com/en/prompt-context-engineering/o-order

> Put the most important material where it is most reliably used.

## Edges are safer than the middle

Studies of long-context use have found that models often use information at the **beginning and end** of the input better than information in the **middle** ("lost in the middle"), although the effect varies by model and is shrinking in newer ones. Practical defaults: put stable instructions first, place the **most relevant documents** at the start or right before the question, and put the **question last**. When you have many ranked chunks, an edge ordering places the best items at both ends. Test on your model rather than assuming.

## Where things sit and how they are marked

Order and clear boundaries change how reliably the model uses each part of the context.

![Three ideas: order, delimiters, placement.](assets/figures/prompt-context-engineering/section-4-map.svg) — Figure 4.1 — Order, delimiters and placement.

## Edge ordering of ranked items, run

I ran this with plain Python 3 (standard library only); the data is made-up example data. Five ranked items are rearranged so the best (A) is first and the second best (B) is last, pushing the weakest (E) to the middle.

```python
ranked = ["A (best)", "B", "C", "D", "E (worst)"]
# put the strongest items at the edges, the weakest in the middle
front, back = [], []
for i, item in enumerate(ranked):
    (front if i % 2 == 0 else back).append(item)
print("ranked order :", ranked)
print("edge ordering:", front + back[::-1])
```

Output:

```
ranked order : ['A (best)', 'B', 'C', 'D', 'E (worst)']
edge ordering: ['A (best)', 'C', 'E (worst)', 'D', 'B']
```

## Run a position test

Place one key fact at the start, middle and end of a long context and measure accuracy for each position on your model.

**Quiz:** Where is a sensible default place for the user question in a long context?

- [ ] Repeated in every document
- [ ] Hidden in the middle of the documents
- [ ] Before the system rules
- [x] At the end, after the documents

*Answer:* At the end, after the documents. Question last keeps it close to where the model starts answering.