diff --git a/apps/web/astro.config.mjs b/apps/web/astro.config.mjs
index 2f751aeac..4f3c55212 100644
--- a/apps/web/astro.config.mjs
+++ b/apps/web/astro.config.mjs
@@ -1,27 +1,58 @@
-import { readFileSync } from 'node:fs';
+import { readFileSync, readdirSync } from 'node:fs';
+import path from 'node:path';
 import { fileURLToPath } from 'node:url';
 import starlight from '@astrojs/starlight';
 import { defineConfig } from 'astro/config';
 
-// Static builds can't redirect an open-ended `/docs/[...slug]` wildcard to
-// v4.42.4 (that requires enumerable paths), so generate one concrete
-// redirect per known v4.42.4 route from its route manifest instead.
-const v4RoutesPath = fileURLToPath(new URL('./src/data/docs-v4.42.4-routes.json', import.meta.url));
-const v4Routes = JSON.parse(readFileSync(v4RoutesPath, 'utf8'));
-const v4Redirects = Object.fromEntries(
-  v4Routes.map((route) => {
-    const bareRoute = route.replace('/docs/v4.42.4/', '/docs/');
-    const from = bareRoute === '/docs/' ? '/docs' : bareRoute.replace(/\/$/, '');
-    return [from, route];
+const currentDocsRoot = fileURLToPath(new URL('./src/content/docs/docs/next', import.meta.url));
+
+const currentRoutes = collectDocsRoutes(currentDocsRoot, '/docs');
+const nextRedirects = Object.fromEntries(
+  currentRoutes.map((route) => {
+    const suffix = route === '/docs/' ? '' : route.slice('/docs/'.length);
+    const from = suffix ? `/docs/next/${suffix}` : '/docs/next';
+    return [from.replace(/\/$/, ''), route];
   }),
 );
 
+function collectDocsRoutes(root, base) {
+  return collectMarkdownFiles(root)
+    .map((file) => {
+      const slug = getFrontmatterSlug(file);
+      if (slug) return `/${slug.replace(/^\/|\/$/g, '')}/`;
+
+      const relative = path.relative(root, file).replace(/\\/g, '/');
+      const suffix = relative
+        .replace(/\.mdx?$/, '')
+        .replace(/(^|\/)index$/, '')
+        .replace(/\/$/, '');
+      return suffix ? `${base}/${suffix}/` : `${base}/`;
+    })
+    .sort();
+}
+
+function getFrontmatterSlug(file) {
+  const source = readFileSync(file, 'utf8');
+  return source
+    .split('---')[1]
+    ?.match(/^slug:\s*(.+)$/m)?.[1]
+    ?.trim();
+}
+
+function collectMarkdownFiles(dir) {
+  return readdirSync(dir, { withFileTypes: true }).flatMap((entry) => {
+    const fullPath = path.join(dir, entry.name);
+    if (entry.isDirectory()) return collectMarkdownFiles(fullPath);
+    return /\.mdx?$/.test(entry.name) ? [fullPath] : [];
+  });
+}
+
 export default defineConfig({
   site: 'https://agentv.dev',
   image: { service: { entrypoint: 'astro/assets/services/noop' } },
   redirects: {
     '/docs/v4': '/docs/v4.42.4/',
-    ...v4Redirects,
+    ...nextRedirects,
   },
   integrations: [
     starlight({
diff --git a/apps/web/package.json b/apps/web/package.json
index c0f22be33..ad0cb42b2 100644
--- a/apps/web/package.json
+++ b/apps/web/package.json
@@ -6,6 +6,7 @@
     "dev": "astro dev",
     "docs:snapshot:v4.42.4": "node ../../scripts/snapshot-docs-version.mjs v4.42.4",
     "build": "astro build",
+    "check:routes": "node scripts/check-doc-routes.mjs",
     "preview": "astro preview"
   },
   "dependencies": {
diff --git a/apps/web/scripts/check-doc-routes.mjs b/apps/web/scripts/check-doc-routes.mjs
new file mode 100644
index 000000000..cfb3c2563
--- /dev/null
+++ b/apps/web/scripts/check-doc-routes.mjs
@@ -0,0 +1,69 @@
+import { existsSync, readFileSync } from 'node:fs';
+import path from 'node:path';
+import { fileURLToPath } from 'node:url';
+
+const webRoot = fileURLToPath(new URL('..', import.meta.url));
+const distRoot = path.join(webRoot, 'dist');
+const v4Routes = JSON.parse(
+  readFileSync(path.join(webRoot, 'src/data/docs-v4.42.4-routes.json'), 'utf8'),
+);
+
+const checks = [
+  {
+    path: 'docs/index.html',
+    includes: ['Introduction | AgentV', ' Current '],
+    excludes: ['Redirecting to:'],
+  },
+  {
+    path: 'docs/targets/llm-providers/index.html',
+    includes: ['LLM Providers | AgentV', '<h1 id="_top"'],
+    excludes: ['Redirecting to:'],
+  },
+  {
+    path: 'docs/v4.42.4/targets/llm-providers/index.html',
+    includes: ['LLM Providers | AgentV', '/docs/v4.42.4/targets/llm-providers/'],
+    excludes: ['Redirecting to:', '/docs/v4424/'],
+  },
+  {
+    path: 'docs/next/targets/llm-providers/index.html',
+    includes: ['Redirecting to: /docs/targets/llm-providers/'],
+  },
+];
+
+for (const check of checks) {
+  const file = path.join(distRoot, check.path);
+  if (!existsSync(file)) {
+    fail(`Missing built docs route: ${check.path}`);
+  }
+
+  const html = readFileSync(file, 'utf8');
+  for (const expected of check.includes ?? []) {
+    if (!html.includes(expected)) {
+      fail(`${check.path} does not include expected content: ${expected}`);
+    }
+  }
+
+  for (const unexpected of check.excludes ?? []) {
+    if (html.includes(unexpected)) {
+      fail(`${check.path} includes unexpected content: ${unexpected}`);
+    }
+  }
+}
+
+if (existsSync(path.join(distRoot, 'docs/v4424'))) {
+  fail('Unexpected normalized archive route directory emitted: docs/v4424');
+}
+
+for (const route of v4Routes) {
+  const routeFile = path.join(distRoot, route, 'index.html');
+  if (!existsSync(routeFile)) {
+    fail(`Missing archived manifest route: ${route}`);
+  }
+}
+
+console.log('Docs route checks passed');
+
+function fail(message) {
+  console.error(message);
+  process.exit(1);
+}
diff --git a/apps/web/src/components/VersionSelect.astro b/apps/web/src/components/VersionSelect.astro
index bf918231e..982102ecb 100644
--- a/apps/web/src/components/VersionSelect.astro
+++ b/apps/web/src/components/VersionSelect.astro
@@ -1,6 +1,6 @@
 ---
 const versions = [
-  { label: 'Next', base: '/docs/next' },
+  { label: 'Current', base: '/docs' },
   { label: 'v4.42.4', base: '/docs/v4.42.4' },
 ];
 
diff --git a/apps/web/src/components/VersionedSidebar.astro b/apps/web/src/components/VersionedSidebar.astro
index 2ae216237..08e07f33f 100644
--- a/apps/web/src/components/VersionedSidebar.astro
+++ b/apps/web/src/components/VersionedSidebar.astro
@@ -5,10 +5,9 @@ import SidebarSublist from '@astrojs/starlight/components/SidebarSublist.astro';
 import type { SidebarEntry } from '@astrojs/starlight/utils/routing/types';
 import v4Routes from '../data/docs-v4.42.4-routes.json';
 
-// The Starlight sidebar config autogenerates from docs/next/*, so the base
-// sidebar's hrefs already point at the live /docs/next/ tree unmodified.
-// Only genuinely archived versions below need their hrefs remapped.
-const LIVE_PREFIX = '/docs/next/';
+// The Starlight sidebar config autogenerates from docs/next/*, but those files
+// publish with root /docs/* slugs. Only archived versions need href remapping.
+const LIVE_PREFIX = '/docs/';
 const ARCHIVED_VERSIONS = [{ slug: 'v4.42.4', routes: v4Routes }];
 
 const { sidebar } = Astro.locals.starlightRoute;
diff --git a/apps/web/src/content/docs/docs/next/evaluation/batch-cli.mdx b/apps/web/src/content/docs/docs/next/evaluation/batch-cli.mdx
index ca4a52278..0a1854920 100644
--- a/apps/web/src/content/docs/docs/next/evaluation/batch-cli.mdx
+++ b/apps/web/src/content/docs/docs/next/evaluation/batch-cli.mdx
@@ -3,6 +3,7 @@ title: Batch CLI Evaluation
 description: Evaluate external tools that process all tests in a single invocation
 sidebar:
   order: 5
+slug: docs/evaluation/batch-cli
 ---
 
 Batch CLI evaluation handles tools that process multiple inputs at once — bulk classifiers, screening engines, or any runner that reads all tests and outputs results in one pass.
diff --git a/apps/web/src/content/docs/docs/next/evaluation/eval-cases.mdx b/apps/web/src/content/docs/docs/next/evaluation/eval-cases.mdx
index 485e1e2be..7e30b6060 100644
--- a/apps/web/src/content/docs/docs/next/evaluation/eval-cases.mdx
+++ b/apps/web/src/content/docs/docs/next/evaluation/eval-cases.mdx
@@ -3,6 +3,7 @@ title: Tests
 description: Defining individual tests
 sidebar:
   order: 2
+slug: docs/evaluation/eval-cases
 ---
 
 Tests are individual test entries within an evaluation file. Each test defines input messages, expected outcomes, and optional grader overrides.
diff --git a/apps/web/src/content/docs/docs/next/evaluation/eval-files.mdx b/apps/web/src/content/docs/docs/next/evaluation/eval-files.mdx
index 8c521f972..db8a64b41 100644
--- a/apps/web/src/content/docs/docs/next/evaluation/eval-files.mdx
+++ b/apps/web/src/content/docs/docs/next/evaluation/eval-files.mdx
@@ -3,6 +3,7 @@ title: Eval Files
 description: YAML and JSONL evaluation file formats
 sidebar:
   order: 1
+slug: docs/evaluation/eval-files
 ---
 
 Evaluation files define the test cases, graders, workspace lifecycle, and run
diff --git a/apps/web/src/content/docs/docs/next/evaluation/examples.mdx b/apps/web/src/content/docs/docs/next/evaluation/examples.mdx
index 0ce083124..2184a42d2 100644
--- a/apps/web/src/content/docs/docs/next/evaluation/examples.mdx
+++ b/apps/web/src/content/docs/docs/next/evaluation/examples.mdx
@@ -3,6 +3,7 @@ title: Example Evaluations
 description: Complete working examples of eval files for common patterns
 sidebar:
   order: 6
+slug: docs/evaluation/examples
 ---
 
 This page collects complete eval file examples you can copy and adapt. Each demonstrates a different AgentV pattern.
diff --git a/apps/web/src/content/docs/docs/next/evaluation/experiments.mdx b/apps/web/src/content/docs/docs/next/evaluation/experiments.mdx
index eb5f513b0..8740ab7e4 100644
--- a/apps/web/src/content/docs/docs/next/evaluation/experiments.mdx
+++ b/apps/web/src/content/docs/docs/next/evaluation/experiments.mdx
@@ -3,6 +3,7 @@ title: Experiments
 description: Configure how AgentV evals run
 sidebar:
   order: 2
+slug: docs/evaluation/experiments
 ---
 
 AgentV eval files are the runnable authoring artifact. Use top-level
diff --git a/apps/web/src/content/docs/docs/next/evaluation/rubrics.mdx b/apps/web/src/content/docs/docs/next/evaluation/rubrics.mdx
index c023bb48b..bfba4da4e 100644
--- a/apps/web/src/content/docs/docs/next/evaluation/rubrics.mdx
+++ b/apps/web/src/content/docs/docs/next/evaluation/rubrics.mdx
@@ -3,6 +3,7 @@ title: Rubrics
 description: Structured evaluation criteria with weights
 sidebar:
   order: 3
+slug: docs/evaluation/rubrics
 ---
 
 Rubrics are defined with `assert` entries and support binary checklist grading and score-range analytic grading.
diff --git a/apps/web/src/content/docs/docs/next/evaluation/running-evals.mdx b/apps/web/src/content/docs/docs/next/evaluation/running-evals.mdx
index 8148f884c..fe4a211aa 100644
--- a/apps/web/src/content/docs/docs/next/evaluation/running-evals.mdx
+++ b/apps/web/src/content/docs/docs/next/evaluation/running-evals.mdx
@@ -3,6 +3,7 @@ title: Running Evaluations
 description: CLI commands for running and managing evaluations
 sidebar:
   order: 4
+slug: docs/evaluation/running-evals
 ---
 
 ## Run an Evaluation
diff --git a/apps/web/src/content/docs/docs/next/evaluation/sdk.mdx b/apps/web/src/content/docs/docs/next/evaluation/sdk.mdx
index 262521348..725e3694e 100644
--- a/apps/web/src/content/docs/docs/next/evaluation/sdk.mdx
+++ b/apps/web/src/content/docs/docs/next/evaluation/sdk.mdx
@@ -3,6 +3,7 @@ title: TypeScript SDK
 description: Programmatic API for evaluations, custom assertions, and typed configuration
 sidebar:
   order: 6
+slug: docs/evaluation/sdk
 ---
 
 YAML remains AgentV's canonical, portable eval format. The SDK surfaces below are for cases where you want to generate YAML-shaped definitions in code, embed eval runs inside another application, or write executable graders and prompt templates. For authoring helpers, `@agentv/sdk` is AgentV's public lightweight SDK package.
diff --git a/apps/web/src/content/docs/docs/next/getting-started/installation.mdx b/apps/web/src/content/docs/docs/next/getting-started/installation.mdx
index 5d3eec5f8..b1ae0f053 100644
--- a/apps/web/src/content/docs/docs/next/getting-started/installation.mdx
+++ b/apps/web/src/content/docs/docs/next/getting-started/installation.mdx
@@ -3,6 +3,7 @@ title: Installation
 description: Install AgentV CLI and get started with bundled skills
 sidebar:
   order: 2
+slug: docs/getting-started/installation
 ---
 
 ## Prerequisites
diff --git a/apps/web/src/content/docs/docs/next/getting-started/quickstart.mdx b/apps/web/src/content/docs/docs/next/getting-started/quickstart.mdx
index 409e0a778..43971a8b3 100644
--- a/apps/web/src/content/docs/docs/next/getting-started/quickstart.mdx
+++ b/apps/web/src/content/docs/docs/next/getting-started/quickstart.mdx
@@ -3,6 +3,7 @@ title: Quick Start
 description: Create and run your first evaluation
 sidebar:
   order: 3
+slug: docs/getting-started/quickstart
 ---
 
 Follow these steps to create and run your first evaluation.
diff --git a/apps/web/src/content/docs/docs/next/graders/composite.mdx b/apps/web/src/content/docs/docs/next/graders/composite.mdx
index 4debe39eb..a6c6014d5 100644
--- a/apps/web/src/content/docs/docs/next/graders/composite.mdx
+++ b/apps/web/src/content/docs/docs/next/graders/composite.mdx
@@ -3,6 +3,7 @@ title: Composite Graders
 description: Combine multiple graders with aggregation strategies for multi-criteria evaluation.
 sidebar:
   order: 4
+slug: docs/graders/composite
 ---
 
 Composite graders combine multiple graders and aggregate their results into a single score. This enables sophisticated evaluation patterns like safety gates, weighted scoring, and conflict resolution.
diff --git a/apps/web/src/content/docs/docs/next/graders/custom-assertions.mdx b/apps/web/src/content/docs/docs/next/graders/custom-assertions.mdx
index d6d753009..43fb35500 100644
--- a/apps/web/src/content/docs/docs/next/graders/custom-assertions.mdx
+++ b/apps/web/src/content/docs/docs/next/graders/custom-assertions.mdx
@@ -3,6 +3,7 @@ title: Custom Assertions
 description: Build reusable assertion types with defineAssertion() and convention-based discovery
 sidebar:
   order: 7
+slug: docs/graders/custom-assertions
 ---
 
 Custom assertions let you add evaluation logic that goes beyond built-in types. Define a TypeScript function, drop it in `.agentv/assertions/`, and reference it by name in your YAML eval files.
diff --git a/apps/web/src/content/docs/docs/next/graders/custom-graders.mdx b/apps/web/src/content/docs/docs/next/graders/custom-graders.mdx
index 4489121d4..f88c90908 100644
--- a/apps/web/src/content/docs/docs/next/graders/custom-graders.mdx
+++ b/apps/web/src/content/docs/docs/next/graders/custom-graders.mdx
@@ -3,6 +3,7 @@ title: Custom Graders
 description: Patterns for building custom evaluation logic
 sidebar:
   order: 3
+slug: docs/graders/custom-graders
 ---
 
 AgentV supports multiple grader types that can be combined for comprehensive evaluation.
diff --git a/apps/web/src/content/docs/docs/next/graders/execution-metrics.mdx b/apps/web/src/content/docs/docs/next/graders/execution-metrics.mdx
index d67e742a8..d0c20f2d7 100644
--- a/apps/web/src/content/docs/docs/next/graders/execution-metrics.mdx
+++ b/apps/web/src/content/docs/docs/next/graders/execution-metrics.mdx
@@ -3,6 +3,7 @@ title: Execution Metrics
 description: Threshold-based checks on execution metrics
 sidebar:
   order: 5
+slug: docs/graders/execution-metrics
 ---
 
 AgentV provides built-in graders for checking execution metrics against thresholds. These are useful for enforcing efficiency constraints without writing custom code.
diff --git a/apps/web/src/content/docs/docs/next/graders/llm-graders.mdx b/apps/web/src/content/docs/docs/next/graders/llm-graders.mdx
index da6a8d270..5cdb1f75c 100644
--- a/apps/web/src/content/docs/docs/next/graders/llm-graders.mdx
+++ b/apps/web/src/content/docs/docs/next/graders/llm-graders.mdx
@@ -3,6 +3,7 @@ title: LLM Graders
 description: Customizable LLM-based evaluation
 sidebar:
   order: 2
+slug: docs/graders/llm-graders
 ---
 
 LLM graders use a language model to evaluate agent responses against custom criteria defined in a prompt file.
diff --git a/apps/web/src/content/docs/docs/next/graders/python-helpers.mdx b/apps/web/src/content/docs/docs/next/graders/python-helpers.mdx
index 37f102f47..3910714b9 100644
--- a/apps/web/src/content/docs/docs/next/graders/python-helpers.mdx
+++ b/apps/web/src/content/docs/docs/next/graders/python-helpers.mdx
@@ -3,6 +3,7 @@ title: Repo-Local Python Helpers
 description: Example-local Python helpers for canonical AgentV script graders and eval authoring
 sidebar:
   order: 7
+slug: docs/graders/python-helpers
 ---
 
 AgentV's Python surface currently starts as a repo-local helper example, not a separate runner or published package.
diff --git a/apps/web/src/content/docs/docs/next/graders/script-graders.mdx b/apps/web/src/content/docs/docs/next/graders/script-graders.mdx
index 81a78bc27..a95b60044 100644
--- a/apps/web/src/content/docs/docs/next/graders/script-graders.mdx
+++ b/apps/web/src/content/docs/docs/next/graders/script-graders.mdx
@@ -3,6 +3,7 @@ title: Script Graders
 description: Deterministic script graders in Python or TypeScript
 sidebar:
   order: 1
+slug: docs/graders/script-graders
 ---
 
 Script graders are scripts that evaluate agent responses deterministically. Write them in any language — Python, TypeScript, Node, or any executable.
diff --git a/apps/web/src/content/docs/docs/next/graders/structured-data.mdx b/apps/web/src/content/docs/docs/next/graders/structured-data.mdx
index 6e686b890..7c9fb28c0 100644
--- a/apps/web/src/content/docs/docs/next/graders/structured-data.mdx
+++ b/apps/web/src/content/docs/docs/next/graders/structured-data.mdx
@@ -3,6 +3,7 @@ title: Structured Data & Metrics Graders
 description: Built-in graders for JSON field comparison and performance gates (latency, cost, token usage).
 sidebar:
   order: 6
+slug: docs/graders/structured-data
 ---
 
 Built-in graders for grading structured outputs and gating on execution metrics:
diff --git a/apps/web/src/content/docs/docs/next/graders/tool-trajectory.mdx b/apps/web/src/content/docs/docs/next/graders/tool-trajectory.mdx
index bafc9e089..c0768784d 100644
--- a/apps/web/src/content/docs/docs/next/graders/tool-trajectory.mdx
+++ b/apps/web/src/content/docs/docs/next/graders/tool-trajectory.mdx
@@ -3,6 +3,7 @@ title: Tool Trajectory Graders
 description: Validate that agents use the right tools in the right order with argument matching and latency assertions.
 sidebar:
   order: 5
+slug: docs/graders/tool-trajectory
 ---
 
 Tool trajectory graders validate that an agent used the expected tools during execution. They work with trace data returned by agent providers (codex, vscode, cli with trace support).
diff --git a/apps/web/src/content/docs/docs/next/guides/agent-eval-layers.mdx b/apps/web/src/content/docs/docs/next/guides/agent-eval-layers.mdx
index 9c26efc9d..65cf7ff02 100644
--- a/apps/web/src/content/docs/docs/next/guides/agent-eval-layers.mdx
+++ b/apps/web/src/content/docs/docs/next/guides/agent-eval-layers.mdx
@@ -3,6 +3,7 @@ title: Agent Evaluation Layers
 description: A four-layer taxonomy for evaluating AI agents — Reasoning, Action, End-to-End, and Safety — mapped to AgentV graders.
 sidebar:
   order: 1
+slug: docs/guides/agent-eval-layers
 ---
 
 A practical taxonomy for structuring agent evaluations. Each layer targets a different dimension of agent behavior, and maps directly to AgentV graders you can drop into an `EVAL.yaml`.
diff --git a/apps/web/src/content/docs/docs/next/guides/autoresearch.mdx b/apps/web/src/content/docs/docs/next/guides/autoresearch.mdx
index 827cea502..5a1bfe4cf 100644
--- a/apps/web/src/content/docs/docs/next/guides/autoresearch.mdx
+++ b/apps/web/src/content/docs/docs/next/guides/autoresearch.mdx
@@ -3,6 +3,7 @@ title: Autoresearch
 description: Run an unattended eval-improve loop that iteratively optimizes agent skills
 sidebar:
   order: 5
+slug: docs/guides/autoresearch
 ---
 
 import { Image } from 'astro:assets';
diff --git a/apps/web/src/content/docs/docs/next/guides/benchmark-provenance.mdx b/apps/web/src/content/docs/docs/next/guides/benchmark-provenance.mdx
index f656eb4d9..a648e1429 100644
--- a/apps/web/src/content/docs/docs/next/guides/benchmark-provenance.mdx
+++ b/apps/web/src/content/docs/docs/next/guides/benchmark-provenance.mdx
@@ -3,6 +3,7 @@ title: Benchmark Provenance
 description: Patterns for source pins, task artifacts, hooks, and generated benchmark metadata.
 sidebar:
   order: 5
+slug: docs/guides/benchmark-provenance
 ---
 
 Benchmark suites usually need more than a prompt and a score. They carry source
diff --git a/apps/web/src/content/docs/docs/next/guides/enterprise-governance.mdx b/apps/web/src/content/docs/docs/next/guides/enterprise-governance.mdx
index 12ee529e1..6832e7496 100644
--- a/apps/web/src/content/docs/docs/next/guides/enterprise-governance.mdx
+++ b/apps/web/src/content/docs/docs/next/guides/enterprise-governance.mdx
@@ -3,6 +3,7 @@ title: Enterprise Governance
 description: A Git-native pattern for inventorying and reviewing the AI systems in your organisation, using a `.ai-register.yaml` per repo and a GitHub Action to aggregate them.
 sidebar:
   order: 9
+slug: docs/guides/enterprise-governance
 ---
 
 This guide describes a lightweight convention for keeping a documented
diff --git a/apps/web/src/content/docs/docs/next/guides/eval-authoring.mdx b/apps/web/src/content/docs/docs/next/guides/eval-authoring.mdx
index b8b0a35d0..bd1d69a3a 100644
--- a/apps/web/src/content/docs/docs/next/guides/eval-authoring.mdx
+++ b/apps/web/src/content/docs/docs/next/guides/eval-authoring.mdx
@@ -3,6 +3,7 @@ title: Eval Authoring Guide
 description: Practical guidance for writing workspace-based evals that work reliably across providers.
 sidebar:
   order: 3
+slug: docs/guides/eval-authoring
 ---
 
 ## Agent Rules and Skill Paths
diff --git a/apps/web/src/content/docs/docs/next/guides/evaluation-types.mdx b/apps/web/src/content/docs/docs/next/guides/evaluation-types.mdx
index 1bf67337f..7851f03e8 100644
--- a/apps/web/src/content/docs/docs/next/guides/evaluation-types.mdx
+++ b/apps/web/src/content/docs/docs/next/guides/evaluation-types.mdx
@@ -3,6 +3,7 @@ title: Execution Quality vs Trigger Quality
 description: Two distinct evaluation concerns for AI agents and skills — what AgentV measures, and what belongs to skill-creator tooling.
 sidebar:
   order: 2
+slug: docs/guides/evaluation-types
 ---
 
 Agent evaluation has two fundamentally different concerns: **execution quality** and **trigger quality**. They require different tooling, different methodologies, and different optimization surfaces. Conflating them leads to eval configs that are noisy, hard to maintain, and unreliable.
diff --git a/apps/web/src/content/docs/docs/next/guides/skill-improvement-workflow.mdx b/apps/web/src/content/docs/docs/next/guides/skill-improvement-workflow.mdx
index ac8374d0b..611542d12 100644
--- a/apps/web/src/content/docs/docs/next/guides/skill-improvement-workflow.mdx
+++ b/apps/web/src/content/docs/docs/next/guides/skill-improvement-workflow.mdx
@@ -3,6 +3,7 @@ title: Skill Improvement Workflow
 description: Iteratively evaluate and improve agent skills using AgentV
 sidebar:
   order: 4
+slug: docs/guides/skill-improvement-workflow
 ---
 
 ## Introduction
diff --git a/apps/web/src/content/docs/docs/next/guides/workspace-architecture.mdx b/apps/web/src/content/docs/docs/next/guides/workspace-architecture.mdx
index 6846c4921..985b81d20 100644
--- a/apps/web/src/content/docs/docs/next/guides/workspace-architecture.mdx
+++ b/apps/web/src/content/docs/docs/next/guides/workspace-architecture.mdx
@@ -3,6 +3,7 @@ title: Workspace Architecture
 description: How AgentV materializes eval workspaces, resolves repo acquisition, and keeps target comparisons fair.
 sidebar:
   order: 7
+slug: docs/guides/workspace-architecture
 ---
 
 AgentV workspaces are the shared substrate an eval runs against: templates,
diff --git a/apps/web/src/content/docs/docs/next/index.mdx b/apps/web/src/content/docs/docs/next/index.mdx
index 46a62ed46..a05e988e5 100644
--- a/apps/web/src/content/docs/docs/next/index.mdx
+++ b/apps/web/src/content/docs/docs/next/index.mdx
@@ -3,6 +3,7 @@ title: Introduction
 description: What AgentV is and why it exists
 sidebar:
   order: 1
+slug: docs
 ---
 
 AgentV is a CLI-first AI agent evaluation framework. It evaluates your agents locally with multi-objective scoring (correctness, latency, cost, safety) from YAML specifications. Deterministic script graders, structured `llm-rubric` scoring, and customizable LLM graders are all version-controlled in Git.
diff --git a/apps/web/src/content/docs/docs/next/integrations/agent-skills-evals.mdx b/apps/web/src/content/docs/docs/next/integrations/agent-skills-evals.mdx
index 8f262cc2a..61de784f0 100644
--- a/apps/web/src/content/docs/docs/next/integrations/agent-skills-evals.mdx
+++ b/apps/web/src/content/docs/docs/next/integrations/agent-skills-evals.mdx
@@ -3,6 +3,7 @@ title: Agent Skills evals.json Adapter
 description: Run or convert Agent Skills evals.json files through AgentV's built-in read adapter.
 sidebar:
   order: 2
+slug: docs/integrations/agent-skills-evals
 ---
 
 ## Overview
diff --git a/apps/web/src/content/docs/docs/next/integrations/autoevals-integration.mdx b/apps/web/src/content/docs/docs/next/integrations/autoevals-integration.mdx
index f19ba8b7b..0d74a6fa7 100644
--- a/apps/web/src/content/docs/docs/next/integrations/autoevals-integration.mdx
+++ b/apps/web/src/content/docs/docs/next/integrations/autoevals-integration.mdx
@@ -3,6 +3,7 @@ title: Autoevals Integration
 description: Use Braintrust's open-source autoevals scorers (Factuality, Faithfulness, etc.) as script graders in AgentV.
 sidebar:
   order: 3
+slug: docs/integrations/autoevals-integration
 ---
 
 ## Overview
diff --git a/apps/web/src/content/docs/docs/next/integrations/langfuse.mdx b/apps/web/src/content/docs/docs/next/integrations/langfuse.mdx
index d7de5c4b1..d6b375531 100644
--- a/apps/web/src/content/docs/docs/next/integrations/langfuse.mdx
+++ b/apps/web/src/content/docs/docs/next/integrations/langfuse.mdx
@@ -3,6 +3,7 @@ title: Langfuse
 description: Correlate AgentV runs with traces emitted directly to Langfuse.
 sidebar:
   order: 1
+slug: docs/integrations/langfuse
 ---
 
 AgentV does not export completed eval transcripts or run bundles to Langfuse.
diff --git a/apps/web/src/content/docs/docs/next/integrations/phoenix.mdx b/apps/web/src/content/docs/docs/next/integrations/phoenix.mdx
index 748513fc3..edd43f87d 100644
--- a/apps/web/src/content/docs/docs/next/integrations/phoenix.mdx
+++ b/apps/web/src/content/docs/docs/next/integrations/phoenix.mdx
@@ -3,6 +3,7 @@ title: Phoenix
 description: How AgentV relates to Phoenix without making Phoenix the owner of AgentV artifacts.
 sidebar:
   order: 4
+slug: docs/integrations/phoenix
 ---
 
 AgentV keeps completed runs, traces, transcripts, experiments, and indexes in
diff --git a/apps/web/src/content/docs/docs/next/reference/comparison.mdx b/apps/web/src/content/docs/docs/next/reference/comparison.mdx
index a91911931..b8d8f7ad9 100644
--- a/apps/web/src/content/docs/docs/next/reference/comparison.mdx
+++ b/apps/web/src/content/docs/docs/next/reference/comparison.mdx
@@ -1,6 +1,7 @@
 ---
 title: Ecosystem
 description: How AgentV fits into the AI agent lifecycle alongside complementary tools.
+slug: docs/reference/comparison
 ---
 
 AgentV is the **evaluation layer** in the AI agent lifecycle. It works alongside runtime governance and observability tools — each handles a different concern with zero overlap.
diff --git a/apps/web/src/content/docs/docs/next/reference/result-artifacts.mdx b/apps/web/src/content/docs/docs/next/reference/result-artifacts.mdx
index 3196a4bbe..735cb75d8 100644
--- a/apps/web/src/content/docs/docs/next/reference/result-artifacts.mdx
+++ b/apps/web/src/content/docs/docs/next/reference/result-artifacts.mdx
@@ -3,6 +3,7 @@ title: Result Artifact Contract
 description: The canonical AgentV run output layout, manifest roles, and integration contract.
 sidebar:
   order: 1
+slug: docs/reference/result-artifacts
 ---
 
 AgentV writes each eval invocation as a portable run bundle. The bundle is the
diff --git a/apps/web/src/content/docs/docs/next/targets/cli-provider.mdx b/apps/web/src/content/docs/docs/next/targets/cli-provider.mdx
index 9248f576a..626d3000e 100644
--- a/apps/web/src/content/docs/docs/next/targets/cli-provider.mdx
+++ b/apps/web/src/content/docs/docs/next/targets/cli-provider.mdx
@@ -3,6 +3,7 @@ title: CLI Provider
 description: Wrap any shell command as an evaluation target
 sidebar:
   order: 4
+slug: docs/targets/cli-provider
 ---
 
 The `cli` provider runs an arbitrary shell command per test case and captures its output as the target's response. It's the escape hatch that lets you evaluate *anything* that exposes a command-line entry point — your own agent, a third-party CLI, a stub that prints a fixed answer, a script that calls an in-house microservice, etc.
diff --git a/apps/web/src/content/docs/docs/next/targets/coding-agents.mdx b/apps/web/src/content/docs/docs/next/targets/coding-agents.mdx
index cbbbcabe5..971bcfdb3 100644
--- a/apps/web/src/content/docs/docs/next/targets/coding-agents.mdx
+++ b/apps/web/src/content/docs/docs/next/targets/coding-agents.mdx
@@ -3,6 +3,7 @@ title: Coding Agents
 description: Evaluate coding agent targets
 sidebar:
   order: 3
+slug: docs/targets/coding-agents
 ---
 
 Coding agent targets evaluate assistants that run against a real workspace. They
diff --git a/apps/web/src/content/docs/docs/next/targets/configuration.mdx b/apps/web/src/content/docs/docs/next/targets/configuration.mdx
index c66fc5a6c..046716aea 100644
--- a/apps/web/src/content/docs/docs/next/targets/configuration.mdx
+++ b/apps/web/src/content/docs/docs/next/targets/configuration.mdx
@@ -3,6 +3,7 @@ title: Targets Configuration
 description: Configure execution targets for providers and agents
 sidebar:
   order: 1
+slug: docs/targets/configuration
 ---
 
 Targets define which agent or LLM provider to evaluate. AgentV uses one
diff --git a/apps/web/src/content/docs/docs/next/targets/custom-providers.mdx b/apps/web/src/content/docs/docs/next/targets/custom-providers.mdx
index 7e810a233..77c5b9d95 100644
--- a/apps/web/src/content/docs/docs/next/targets/custom-providers.mdx
+++ b/apps/web/src/content/docs/docs/next/targets/custom-providers.mdx
@@ -3,6 +3,7 @@ title: Custom Providers (SDK)
 description: Implement native TypeScript providers using the ProviderRegistry API
 sidebar:
   order: 6
+slug: docs/targets/custom-providers
 ---
 
 Custom providers let you implement evaluation targets in TypeScript instead of shelling out to a CLI command. This is useful when you want to call an HTTP API, use an SDK, or implement custom logic that goes beyond what the CLI provider supports.
diff --git a/apps/web/src/content/docs/docs/next/targets/llm-providers.mdx b/apps/web/src/content/docs/docs/next/targets/llm-providers.mdx
index 0a0df092b..5752a96a4 100644
--- a/apps/web/src/content/docs/docs/next/targets/llm-providers.mdx
+++ b/apps/web/src/content/docs/docs/next/targets/llm-providers.mdx
@@ -3,6 +3,7 @@ title: LLM Providers
 description: Direct LLM API provider targets
 sidebar:
   order: 2
+slug: docs/targets/llm-providers
 ---
 
 LLM provider targets call language model APIs directly. These are used both as evaluation targets and as grader targets for scoring.
diff --git a/apps/web/src/content/docs/docs/next/targets/retry.mdx b/apps/web/src/content/docs/docs/next/targets/retry.mdx
index 725a5ded5..4442cc079 100644
--- a/apps/web/src/content/docs/docs/next/targets/retry.mdx
+++ b/apps/web/src/content/docs/docs/next/targets/retry.mdx
@@ -3,6 +3,7 @@ title: Retry Configuration
 description: Configure automatic retry with exponential backoff
 sidebar:
   order: 5
+slug: docs/targets/retry
 ---
 
 Configure automatic retry with exponential backoff for transient failures.
diff --git a/apps/web/src/content/docs/docs/next/tools/compare.mdx b/apps/web/src/content/docs/docs/next/tools/compare.mdx
index dfff2ee14..7fb511318 100644
--- a/apps/web/src/content/docs/docs/next/tools/compare.mdx
+++ b/apps/web/src/content/docs/docs/next/tools/compare.mdx
@@ -3,6 +3,7 @@ title: Compare
 description: Compare evaluation results between runs
 sidebar:
   order: 1
+slug: docs/tools/compare
 ---
 
 The `compare` command computes deltas between two evaluation runs for A/B testing.
diff --git a/apps/web/src/content/docs/docs/next/tools/convert.mdx b/apps/web/src/content/docs/docs/next/tools/convert.mdx
index 7ef00598b..7cd43ecac 100644
--- a/apps/web/src/content/docs/docs/next/tools/convert.mdx
+++ b/apps/web/src/content/docs/docs/next/tools/convert.mdx
@@ -3,6 +3,7 @@ title: Convert
 description: Convert between evaluation file formats
 sidebar:
   order: 2
+slug: docs/tools/convert
 ---
 
 The `convert` command converts evaluation files between formats: YAML ↔ JSONL, and Agent Skills `evals.json` → AgentV EVAL YAML.
diff --git a/apps/web/src/content/docs/docs/next/tools/dashboard.mdx b/apps/web/src/content/docs/docs/next/tools/dashboard.mdx
index f76ddd593..4a59fb530 100644
--- a/apps/web/src/content/docs/docs/next/tools/dashboard.mdx
+++ b/apps/web/src/content/docs/docs/next/tools/dashboard.mdx
@@ -3,6 +3,7 @@ title: Dashboard
 description: Visual dashboard for reviewing evaluation results
 sidebar:
   order: 6
+slug: docs/tools/dashboard
 ---
 
 import { Image } from 'astro:assets';
diff --git a/apps/web/src/content/docs/docs/next/tools/import.mdx b/apps/web/src/content/docs/docs/next/tools/import.mdx
index c0a7f8bbc..55a065fb1 100644
--- a/apps/web/src/content/docs/docs/next/tools/import.mdx
+++ b/apps/web/src/content/docs/docs/next/tools/import.mdx
@@ -3,6 +3,7 @@ title: Import
 description: Import transcripts and selected datasets into AgentV
 sidebar:
   order: 3
+slug: docs/tools/import
 ---
 
 The `import` command converts agent session transcripts and selected external datasets into AgentV formats. Transcript imports let you grade past runs offline without re-running the agent. Dataset imports help seed AgentV YAML from portable case sources.
diff --git a/apps/web/src/content/docs/docs/next/tools/inspect.mdx b/apps/web/src/content/docs/docs/next/tools/inspect.mdx
index ada156314..cc2a88bc6 100644
--- a/apps/web/src/content/docs/docs/next/tools/inspect.mdx
+++ b/apps/web/src/content/docs/docs/next/tools/inspect.mdx
@@ -3,6 +3,7 @@ title: Inspect
 description: Inspect and analyze evaluation results from the CLI
 sidebar:
   order: 5
+slug: docs/tools/inspect
 ---
 
 The `inspect` command provides headless trace inspection and analysis — no server or dashboard needed.
diff --git a/apps/web/src/content/docs/docs/next/tools/prepare.mdx b/apps/web/src/content/docs/docs/next/tools/prepare.mdx
index a42a63f25..d14b1871d 100644
--- a/apps/web/src/content/docs/docs/next/tools/prepare.mdx
+++ b/apps/web/src/content/docs/docs/next/tools/prepare.mdx
@@ -3,6 +3,7 @@ title: Prepare
 description: Prepare one eval case for a human or external agent, then grade the finished workspace.
 sidebar:
   order: 4
+slug: docs/tools/prepare
 ---
 
 `agentv prepare` materializes one eval case without launching the target provider. Use it when a human, a separate agent process, or another harness should attempt the task in the same workspace state AgentV would have provided immediately before target execution.
diff --git a/apps/web/src/content/docs/docs/next/tools/results.mdx b/apps/web/src/content/docs/docs/next/tools/results.mdx
index 8636f8cd6..445f299cb 100644
--- a/apps/web/src/content/docs/docs/next/tools/results.mdx
+++ b/apps/web/src/content/docs/docs/next/tools/results.mdx
@@ -3,6 +3,7 @@ title: Results
 description: Inspect, export, and share AgentV result workspaces from the CLI.
 sidebar:
   order: 6
+slug: docs/tools/results
 ---
 
 import { Image } from 'astro:assets';
diff --git a/apps/web/src/content/docs/docs/next/tools/trend.mdx b/apps/web/src/content/docs/docs/next/tools/trend.mdx
index 5f55f7aa4..106697326 100644
--- a/apps/web/src/content/docs/docs/next/tools/trend.mdx
+++ b/apps/web/src/content/docs/docs/next/tools/trend.mdx
@@ -3,6 +3,7 @@ title: Trend
 description: Analyze score drift across multiple historical eval runs
 sidebar:
   order: 2
+slug: docs/tools/trend
 ---
 
 The `trend` command analyzes score movement across multiple historical run manifests and reports whether quality is improving, degrading, or stable over time.
diff --git a/apps/web/src/content/docs/docs/next/tools/validate.mdx b/apps/web/src/content/docs/docs/next/tools/validate.mdx
index f9d89f848..bd60b6801 100644
--- a/apps/web/src/content/docs/docs/next/tools/validate.mdx
+++ b/apps/web/src/content/docs/docs/next/tools/validate.mdx
@@ -3,6 +3,7 @@ title: Validate
 description: Validate evaluation file definitions
 sidebar:
   order: 4
+slug: docs/tools/validate
 ---
 
 The `validate` command checks evaluation files for schema errors without running them.
diff --git a/apps/web/src/content/docs/docs/next/tools/wip-checkpoints.mdx b/apps/web/src/content/docs/docs/next/tools/wip-checkpoints.mdx
index 559241984..e430f5bd9 100644
--- a/apps/web/src/content/docs/docs/next/tools/wip-checkpoints.mdx
+++ b/apps/web/src/content/docs/docs/next/tools/wip-checkpoints.mdx
@@ -3,6 +3,7 @@ title: WIP checkpoints
 description: Recover in-progress eval runs from git-backed results repositories.
 sidebar:
   order: 7
+slug: docs/tools/wip-checkpoints
 ---
 
 WIP checkpoints are best-effort snapshots of an eval run while it is still executing. They are designed for long-running evals in CI, pods, or remote agents where losing the process would otherwise lose the completed test rows that were already written locally.
diff --git a/apps/web/src/content/docs/docs/v4.42.4/evaluation/eval-files.mdx b/apps/web/src/content/docs/docs/v4.42.4/evaluation/eval-files.mdx
index 8c521f972..8fe6335c8 100644
--- a/apps/web/src/content/docs/docs/v4.42.4/evaluation/eval-files.mdx
+++ b/apps/web/src/content/docs/docs/v4.42.4/evaluation/eval-files.mdx
@@ -3,6 +3,9 @@ title: Eval Files
 description: YAML and JSONL evaluation file formats
 sidebar:
   order: 1
+slug: docs/v4.42.4/evaluation/eval-files
+editUrl: false
+pagefind: false
 ---
 
 Evaluation files define the test cases, graders, workspace lifecycle, and run
diff --git a/apps/web/src/content/docs/docs/v4.42.4/evaluation/running-evals.mdx b/apps/web/src/content/docs/docs/v4.42.4/evaluation/running-evals.mdx
index 8148f884c..64504d34a 100644
--- a/apps/web/src/content/docs/docs/v4.42.4/evaluation/running-evals.mdx
+++ b/apps/web/src/content/docs/docs/v4.42.4/evaluation/running-evals.mdx
@@ -3,6 +3,9 @@ title: Running Evaluations
 description: CLI commands for running and managing evaluations
 sidebar:
   order: 4
+slug: docs/v4.42.4/evaluation/running-evals
+editUrl: false
+pagefind: false
 ---
 
 ## Run an Evaluation
diff --git a/apps/web/src/content/docs/docs/v4.42.4/targets/cli-provider.mdx b/apps/web/src/content/docs/docs/v4.42.4/targets/cli-provider.mdx
index 9248f576a..4d32842f6 100644
--- a/apps/web/src/content/docs/docs/v4.42.4/targets/cli-provider.mdx
+++ b/apps/web/src/content/docs/docs/v4.42.4/targets/cli-provider.mdx
@@ -3,6 +3,9 @@ title: CLI Provider
 description: Wrap any shell command as an evaluation target
 sidebar:
   order: 4
+slug: docs/v4.42.4/targets/cli-provider
+editUrl: false
+pagefind: false
 ---
 
 The `cli` provider runs an arbitrary shell command per test case and captures its output as the target's response. It's the escape hatch that lets you evaluate *anything* that exposes a command-line entry point — your own agent, a third-party CLI, a stub that prints a fixed answer, a script that calls an in-house microservice, etc.
diff --git a/apps/web/src/content/docs/docs/v4.42.4/targets/coding-agents.mdx b/apps/web/src/content/docs/docs/v4.42.4/targets/coding-agents.mdx
index cbbbcabe5..8be53e738 100644
--- a/apps/web/src/content/docs/docs/v4.42.4/targets/coding-agents.mdx
+++ b/apps/web/src/content/docs/docs/v4.42.4/targets/coding-agents.mdx
@@ -3,6 +3,9 @@ title: Coding Agents
 description: Evaluate coding agent targets
 sidebar:
   order: 3
+slug: docs/v4.42.4/targets/coding-agents
+editUrl: false
+pagefind: false
 ---
 
 Coding agent targets evaluate assistants that run against a real workspace. They
diff --git a/apps/web/src/content/docs/docs/v4.42.4/targets/configuration.mdx b/apps/web/src/content/docs/docs/v4.42.4/targets/configuration.mdx
index c66fc5a6c..5fe634545 100644
--- a/apps/web/src/content/docs/docs/v4.42.4/targets/configuration.mdx
+++ b/apps/web/src/content/docs/docs/v4.42.4/targets/configuration.mdx
@@ -3,6 +3,9 @@ title: Targets Configuration
 description: Configure execution targets for providers and agents
 sidebar:
   order: 1
+slug: docs/v4.42.4/targets/configuration
+editUrl: false
+pagefind: false
 ---
 
 Targets define which agent or LLM provider to evaluate. AgentV uses one
diff --git a/apps/web/src/content/docs/docs/v4.42.4/targets/custom-providers.mdx b/apps/web/src/content/docs/docs/v4.42.4/targets/custom-providers.mdx
index 7e810a233..40a6971bd 100644
--- a/apps/web/src/content/docs/docs/v4.42.4/targets/custom-providers.mdx
+++ b/apps/web/src/content/docs/docs/v4.42.4/targets/custom-providers.mdx
@@ -3,6 +3,9 @@ title: Custom Providers (SDK)
 description: Implement native TypeScript providers using the ProviderRegistry API
 sidebar:
   order: 6
+slug: docs/v4.42.4/targets/custom-providers
+editUrl: false
+pagefind: false
 ---
 
 Custom providers let you implement evaluation targets in TypeScript instead of shelling out to a CLI command. This is useful when you want to call an HTTP API, use an SDK, or implement custom logic that goes beyond what the CLI provider supports.
diff --git a/apps/web/src/content/docs/docs/v4.42.4/targets/llm-providers.mdx b/apps/web/src/content/docs/docs/v4.42.4/targets/llm-providers.mdx
index 0a0df092b..53dcfdae5 100644
--- a/apps/web/src/content/docs/docs/v4.42.4/targets/llm-providers.mdx
+++ b/apps/web/src/content/docs/docs/v4.42.4/targets/llm-providers.mdx
@@ -3,6 +3,9 @@ title: LLM Providers
 description: Direct LLM API provider targets
 sidebar:
   order: 2
+slug: docs/v4.42.4/targets/llm-providers
+editUrl: false
+pagefind: false
 ---
 
 LLM provider targets call language model APIs directly. These are used both as evaluation targets and as grader targets for scoring.
diff --git a/apps/web/src/content/docs/docs/v4.42.4/targets/retry.mdx b/apps/web/src/content/docs/docs/v4.42.4/targets/retry.mdx
index 725a5ded5..bb63b0509 100644
--- a/apps/web/src/content/docs/docs/v4.42.4/targets/retry.mdx
+++ b/apps/web/src/content/docs/docs/v4.42.4/targets/retry.mdx
@@ -3,6 +3,9 @@ title: Retry Configuration
 description: Configure automatic retry with exponential backoff
 sidebar:
   order: 5
+slug: docs/v4.42.4/targets/retry
+editUrl: false
+pagefind: false
 ---
 
 Configure automatic retry with exponential backoff for transient failures.
diff --git a/apps/web/src/content/docs/docs/v4.42.4/tools/dashboard.mdx b/apps/web/src/content/docs/docs/v4.42.4/tools/dashboard.mdx
index f76ddd593..aafa46db4 100644
--- a/apps/web/src/content/docs/docs/v4.42.4/tools/dashboard.mdx
+++ b/apps/web/src/content/docs/docs/v4.42.4/tools/dashboard.mdx
@@ -3,6 +3,9 @@ title: Dashboard
 description: Visual dashboard for reviewing evaluation results
 sidebar:
   order: 6
+slug: docs/v4.42.4/tools/dashboard
+editUrl: false
+pagefind: false
 ---
 
 import { Image } from 'astro:assets';