diff --git a/DESCRIPTION b/DESCRIPTION
index 527b68090..47d3ab0d7 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -28,6 +28,7 @@ Imports:
     mlr3filters,
     mlr3fselect,
     mlr3hyperband,
+    mlr3inferr,
     mlr3learners,
     mlr3oml,
     mlr3mbo,
@@ -48,7 +49,8 @@ Remotes:
     mlr-org/mlr3extralearners,
     mlr-org/mlr3batchmark,
     mlr-org/mlr3proba,
-    mlr-org/mlr3fairness
+    mlr-org/mlr3fairness,
+    mlr-org/mlr3inferr
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
 RoxygenNote: 7.2.3
diff --git a/R/zzz.R b/R/zzz.R
index 3473d57c0..bad1e0335 100644
--- a/R/zzz.R
+++ b/R/zzz.R
@@ -5,7 +5,7 @@ NULL
 
 db = new.env()
 db$index = c("base", "utils", "datasets", "data.table", "stats", "batchtools")
-db$hosted = c("paradox", "mlr3misc", "mlr3", "mlr3data", "mlr3db", "mlr3proba", "mlr3pipelines", "mlr3learners", "mlr3filters", "bbotk", "mlr3tuning", "mlr3viz", "mlr3fselect", "mlr3cluster", "mlr3spatiotempcv", "mlr3spatial", "mlr3extralearners", "mlr3tuningspaces", "mlr3hyperband", "mlr3mbo", "mlr3verse", "mlr3benchmark", "mlr3oml", "mlr3batchmark", "mlr3fairness")
+db$hosted = c("paradox", "mlr3misc", "mlr3", "mlr3data", "mlr3db", "mlr3proba", "mlr3pipelines", "mlr3learners", "mlr3filters", "bbotk", "mlr3tuning", "mlr3viz", "mlr3fselect", "mlr3cluster", "mlr3spatiotempcv", "mlr3spatial", "mlr3extralearners", "mlr3tuningspaces", "mlr3hyperband", "mlr3mbo", "mlr3verse", "mlr3benchmark", "mlr3oml", "mlr3batchmark", "mlr3fairness", "mlr3inferr")
 
 lgr = NULL
 
diff --git a/book/book.bib b/book/book.bib
index 01dc8c14e..3653a293f 100644
--- a/book/book.bib
+++ b/book/book.bib
@@ -1436,3 +1436,21 @@ @book{hutter2019automated
     publisher = {Springer},
     keywords = {}
 }
+@misc{kuempelfischer2024ciforge,
+      title={Constructing Confidence Intervals for 'the' Generalization Error -- a Comprehensive Benchmark Study},
+      author={Hannah Schulz-Kümpel and Sebastian Fischer and Thomas Nagler and Anne-Laure Boulesteix and Bernd Bischl and Roman Hornung},
+      year={2024},
+      eprint={2409.18836},
+      archivePrefix={arXiv},
+      primaryClass={stat.ML},
+      url={https://arxiv.org/abs/2409.18836},
+}
+
+@article{bayle2020cross,
+  title={Cross-validation confidence intervals for test error},
+  author={Bayle, Pierre and Bayle, Alexandre and Janson, Lucas and Mackey, Lester},
+  journal={Advances in Neural Information Processing Systems},
+  volume={33},
+  pages={16339--16350},
+  year={2020}
+}
diff --git a/book/chapters/appendices/errata.qmd b/book/chapters/appendices/errata.qmd
index e245b8e93..4793e5ee8 100644
--- a/book/chapters/appendices/errata.qmd
+++ b/book/chapters/appendices/errata.qmd
@@ -18,6 +18,7 @@ This appendix lists changes to the online version of this book to chapters inclu
 ## 3. Evaluation and Benchmarking
 
 * Use `$encapsulate()` method instead of the `$encapsulate` and `$fallback` fields.
+* A section on the `mlr3inferr` package was added.
 
 ## 4. Hyperparameter Optimization
 
diff --git a/book/chapters/chapter3/evaluation_and_benchmarking.qmd b/book/chapters/chapter3/evaluation_and_benchmarking.qmd
index d41c4907e..9a543d700 100644
--- a/book/chapters/chapter3/evaluation_and_benchmarking.qmd
+++ b/book/chapters/chapter3/evaluation_and_benchmarking.qmd
@@ -285,6 +285,31 @@ print(plt2)
 ```
 
 
+### Confidence Intervals {#sec-resampling-ci}
+
+Confidence intervals (CIs) provide a range of values within which we can be confident that it covers the true generalization error.
+Instead of relying solely on a single point estimate, CIs offer a measure of uncertainty around this estimate, allowing us to understand the reliability of our performance estimate.
+While constructing CIs for the generalization error is challenging due to the complex nature of the inference problem, some methods have been shown to work well in practice @kuempelfischer2024ciforge.
+When employing such methods, it is important to be aware that they can fail in some cases -- e.g. in the presence of outliers or instable learning procedures -- and to be aware that the resulting CIs can either be too conservative or too liberal.
+
+The `r ref_pkg("mlr3inferr")` package extends the `mlr3` ecosystem with both inference methods and new resampling strategies.
+The inference methods are implemented as `r ref("Measure")` objects, that take in another measure for which to compute the CI.
+Below, we demonstrate how to use the inference method suggested by @bayle2020cross to compute a CI for the cross-validation result from above.
+As opposed to other mlr3 measures, the result is not a scalar value, but a vector containing the point estimate, as well as the lower and upper bounds of the CI for the specified confidence level.
+
+```{r}
+library(mlr3inferr)
+# alpha = 0.05 is also the default
+msr_ci = msr("ci.wald_cv", msr("classif.acc"), alpha = 0.05)
+rr$aggregate(msr_ci)
+```
+
+We can also use `msr("ci")`, which will automatically select the appropriate method based on the `Resampling` object, if an inference method is available for it.
+
+```{r}
+rr$aggregate(msr("ci", msr("classif.acc")))
+```
+
 ### ResampleResult Objects {#sec-resampling-inspect}
 
 As well as being useful for estimating the generalization performance, the `r ref("ResampleResult")` object can also be used for model inspection.
@@ -576,6 +601,22 @@ plt = plt + ggplot2::scale_fill_manual(values = c("grey30", "grey50", "grey70"))
 print(plt)
 ```
 
+It is also possible to plot confidence intervals by setting the type of plot to `"ci"`.
+Ignoring the multiple testing problem, @fig-benchmark-ci shows that the difference between the random forest and both other learners is statistically significant for the sonar task, whereas no final conclusion can be drawn for the german credit problem.
+
+```{r}
+#| fig-height: 5
+#| fig-width: 6
+#| label: fig-benchmark-ci
+#| fig-cap: 'Confidence intervals for accuracy scores for each learner across resampling iterations and the three tasks. Random forests (`lrn("classif.ranger")`) consistently outperforms the other learners.'
+#| fig-alt: Nine confidence intervals, one corresponding to each task/learner combination. In all cases the random forest performs best and the featureless baseline the worst.
+#| echo: false
+#| warning: false
+#| message: false
+autoplot(bmr, "ci", measure = msr("ci", msr("classif.acc")))
+```
+
+
 ## Evaluation of Binary Classifiers {#sec-roc}
 
 In @sec-basics-classif-learner we touched on the concept of a confusion matrix and how it can be used to break down classification errors in more detail.
diff --git a/book/common/chap_auths.csv b/book/common/chap_auths.csv
index f93c7c583..f4321d16c 100644
--- a/book/common/chap_auths.csv
+++ b/book/common/chap_auths.csv
@@ -1,7 +1,7 @@
 Chapter Number,Title,Authors
 1,Introduction and Overview,"Lars Kotthoff, Raphael Sonabend, Natalie Foss, Bernd Bischl"
 2,Data and Basic Modeling,"Natalie Foss, Lars Kotthoff"
-3,Evaluation and Benchmarking,"Giuseppe Casalicchio, Lukas Burk"
+3,Evaluation and Benchmarking,"Giuseppe Casalicchio, Lukas Burk, Sebastian Fischer"
 4,Hyperparameter Optimization,"Marc Becker, Lennart Schneider, Sebastian Fischer"
 5,Advanced Tuning Methods and Black Box Optimization,"Lennart Schneider, Marc Becker"
 6,Feature Selection,Marvin N. Wright