hud-evals · mintlify · Jul 8, 2026 · Jul 14, 2026 · Jul 15, 2026 · Jul 20, 2026
diff --git a/docs/v6/advanced/robots.mdx b/docs/v6/advanced/robots.mdx
@@ -1,5 +1,5 @@
 ---
-title: "Robots"
+title: "Robotics environments and VLA agents in HUD"
 description: "How HUD models physical robots: capability contracts, bridges that connect to sim or hardware, and the agent harness that drives VLA policies."
 icon: "robot"
 tag: "Beta"

diff --git a/docs/v6/guides/running-an-eval.mdx b/docs/v6/guides/running-an-eval.mdx
@@ -1,6 +1,6 @@
 ---
-title: "Evaluating Agents"
-description: "Point an agent at a HUD taskset, pick a runtime for each rollout, run the evaluation, and read the rewards your graders return for every task."
+title: "Evaluate agents against a HUD taskset"
+description: "Run an evaluation with hud eval: point an agent at a taskset, choose a runtime per rollout, and read the rewards your graders return."
 icon: "play"
 mode: "wide"
 ---

diff --git a/docs/v6/more/contributing.mdx b/docs/v6/more/contributing.mdx
@@ -1,5 +1,5 @@
 ---
-title: "Contributing"
+title: "Contributing to the HUD Python SDK"
 description: "Contribute to the HUD Python SDK: fork the repo, set up a dev environment with uv, run tests and ruff, and open a pull request against the main branch."
 icon: "hand-holding-heart"
 ---

diff --git a/docs/v6/more/faq.mdx b/docs/v6/more/faq.mdx
@@ -1,5 +1,5 @@
 ---
-title: "FAQ"
+title: "HUD frequently asked questions"
 description: "Answers to the most common questions about getting started with HUD: installation, environments, tasks, runtimes, graders, agents, and training loops."
 icon: "circle-question"
 ---

diff --git a/docs/v6/reference/capabilities.mdx b/docs/v6/reference/capabilities.mdx
@@ -1,5 +1,5 @@
 ---
-title: "Capabilities"
+title: "Capabilities: wire protocols and client factories"
 description: "Reference for HUD capabilities: the wire protocols an environment exposes, each capability's factory signature, and the clients agents use to attach."
 icon: "plug"
 ---

diff --git a/docs/v6/reference/cli.mdx b/docs/v6/reference/cli.mdx
@@ -1,6 +1,6 @@
 ---
-title: "CLI"
-description: "Reference for the hud command-line interface: init, dev, run, eval, models, and other commands that span the HUD environment and agent lifecycle."
+title: "HUD CLI command reference"
+description: "Reference for the hud command-line tools: init, dev, run, eval, task, and models commands that scaffold, iterate on, and evaluate environments."
 icon: "terminal"
 ---
 

diff --git a/docs/v6/reference/environment.mdx b/docs/v6/reference/environment.mdx
@@ -1,6 +1,6 @@
 ---
-title: "Environments"
-description: "Reference for the HUD Environment object: registering tasks, capabilities, and lifecycle hooks, plus serving an environment over the wire protocol."
+title: "Environment object and serving API"
+description: "Reference for the HUD Environment object: register tasks, capabilities, and lifecycle hooks, and serve an env.py over the wire protocol to agents."
 icon: "cube"
 ---
 

diff --git a/docs/v6/reference/runtime.mdx b/docs/v6/reference/runtime.mdx
@@ -1,6 +1,6 @@
 ---
-title: "Runtimes"
-description: "Reference for HUD runtimes: local Docker, remote workers, and the platform runtime that decides where each rollout's environment is started and executed."
+title: "Runtimes: LocalRuntime, SubprocessRuntime, HUDRuntime"
+description: "Reference for HUD runtimes that place each rollout's environment: LocalRuntime in-process, SubprocessRuntime in a child, and HUDRuntime on the platform."
 icon: "rocket"
 ---
 

diff --git a/docs/v6/reference/training.mdx b/docs/v6/reference/training.mdx
@@ -1,5 +1,5 @@
 ---
-title: "Training"
+title: "TrainingClient API and hud models CLI reference"
 description: "Reference for HUD training: the TrainingClient API, supported training paths, loss functions, run results, and the hud models CLI for managing forks."
 icon: "dumbbell"
 mode: "wide"

diff --git a/docs/v6/start/overview.mdx b/docs/v6/start/overview.mdx
@@ -1,6 +1,6 @@
 ---
-title: "Overview"
-description: "A high-level tour of HUD's core concepts - environments, tasks, capabilities, agents, runtimes, and graders - and how they connect in the central workflow."
+title: "HUD core concepts and evaluation workflow"
+description: "Tour of HUD's core concepts - environments, tasks, capabilities, agents, runtimes, and graders - and the five-step workflow for evaluating an agent."
 icon: "compass"
 mode: "wide"
 ---

diff --git a/docs/v6/start/quickstart.mdx b/docs/v6/start/quickstart.mdx
@@ -1,5 +1,5 @@
 ---
-title: "Quickstart"
+title: "HUD SDK quickstart: your first task in 5 minutes"
 description: "Install the HUD SDK, write your first task, run it against a model, and read the reward returned by the grader - the full quickstart in five minutes."
 icon: "bolt"
 ---