Rewrite synthetic data gen docs for Kiln Pro batch planning

docs/evals-and-specs/evaluations.md

@@ -187,7 +187,7 @@ Most commonly, you'll want to populate the datasets using synthetic data. Clicki
 
 We suggest at least 160 data samples per eval. Difficult or subjective tasks may require more.
 
-An appropriate data gen template will be populated when you enter data-gen via an eval. You can customize this template to guide data generation. See [the docs](../synthetic-data-generation.md#automatic-templates-and-custom-prompting) for details.
+An appropriate data gen template will be populated when you enter data-gen via an eval. You can customize this template to guide data generation. See [the docs](../synthetic-data-generation.md#templates-and-custom-guidance) for details.
 
 {% hint style="info" %}
 Golden eval datasets work best if they have a range of ratings (some pass, some fail, some of each star-score).
@@ -337,7 +337,7 @@ Like mean squared error, but scores are normalized to the range 0-1. For example
 If you see "N/A" scores in your correlation table, it means more data is needed. This can be one of two cases
 
 * _**Simply not enough data**_: if your golden dataset is very small (<10 items) it can be impossible to produce confident correlation scores. Add more data to resolve this case.
-* _**Not enough variation of human ratings in the golden dataset**_: if you have a larger dataset, but still get N/A, it's likely there isn't enough variation in your dataset for the given score. For example, if all of the golden samples of a score pass, the evaluator won't produce a confident correlation score, as it has no failing examples and everything is a tie. Add more content to your golden dataset, designing the content to fill out the missing score ranges. You can use synthetic data gen [human guidance](../synthetic-data-generation.md#human-guidance) to generate examples that fail.
+* _**Not enough variation of human ratings in the golden dataset**_: if you have a larger dataset, but still get N/A, it's likely there isn't enough variation in your dataset for the given score. For example, if all of the golden samples of a score pass, the evaluator won't produce a confident correlation score, as it has no failing examples and everything is a tie. Add more content to your golden dataset, designing the content to fill out the missing score ranges. You can use synthetic data gen [human guidance](../synthetic-data-generation.md#templates-and-custom-guidance) to generate examples that fail.
 
 </details>
 

docs/fine-tuning/fine-tuning-guide.md

@@ -182,7 +182,7 @@ Models and products are rarely perfect on their first try. When you find bugs or
 * Experiment with fine-tuning hyperparameters (see the "Advanced Options" section of the UI)
 * Experiment with shorter training prompts, which can reduce costs
 * For one-off bugs you encounter use Kiln to “[repair](../repairing-responses.md)” the issues. These get added to your training data for future iterations.
-* For recurring bugs/patterns, use [synthetic data generation](../synthetic-data-generation.md) to generate many samples of common bugs, ensure they have correct responses with [human guidance](../synthetic-data-generation.md#human-guidance), and add the results to the training set to prevent this class of issues in the future.
+* For recurring bugs/patterns, use [synthetic data generation](../synthetic-data-generation.md) to generate many samples of common bugs, ensure they have correct responses with [human guidance](../synthetic-data-generation.md#templates-and-custom-guidance), and add the results to the training set to prevent this class of issues in the future.
 * Rate your dataset using Kiln’s [rating system](../reviewing-and-rating.md), then build fine-tunes using only highly rated content.
 * Regenerate fine-tunes as your dataset grows and evolves
 * Try new foundation models (directly and with fine tuning) when new state of the art models are released.