Restyle Iris/AI context-engine tiles and update self-managed messaging

content/develop/ai/agent-builder/agent-concepts.md

@@ -112,6 +112,30 @@ Create intelligent recommendation systems that:
 [Build a recommendation agent →](../)
 </div>
 
+<div class="bg-gray-50 p-4 rounded-lg border border-gray-200 mb-4">
+<h3 class="no-toc">Knowledge assistants (RAG)</h3>
+
+Build retrieval-augmented generation agents that:
+- Ingest documents and answer questions with citations
+- Combine vector search with semantic caching for fast, grounded responses
+- Reduce hallucinations by retrieving relevant context before generating answers
+- Scale to large document collections
+
+[Build a knowledge assistant →](../)
+</div>
+
+<div class="bg-gray-50 p-4 rounded-lg border border-gray-200 mb-4">
+<h3 class="no-toc">Redis Iris conversational assistants</h3>
+
+Build conversational agents backed by managed Redis Iris Agent Memory that:
+- Get session and long-term memory without building a vector index
+- Persist user preferences and context across conversations
+- Extract durable memories automatically in the background
+- Run on Redis Cloud as a fully managed service
+
+[Build a Redis Iris agent →](../)
+</div>
+
 <div class="bg-gray-50 p-4 rounded-lg border border-gray-200 mb-4">
 <h3 class="no-toc">Task automation agents</h3>
 

content/develop/ai/context-engine/_index.md

@@ -4,35 +4,34 @@ categories:
 - docs
 - develop
 - ai
-description: Redis Iris is a suite of fully-managed services.
+description: Redis Iris is a suite of managed and self-managed services for agent memory, semantic caching, and governed data access.
 hideListLinks: true
 linktitle: Redis Iris context engine
 title: Redis Iris context engine
 weight: 30
+bannerText: LangCache, Agent Memory, and Context Retriever are currently available in preview. Features and behavior are subject to change.
 ---
 
 Give your AI agents the context layer they need to reliably act on business data.
 
-Redis Iris eliminates the infrastructure burden of building context-aware AI agents — persistent memory, semantic caching, governed data access, and live data sync, all on Redis Cloud.
+Redis Iris eliminates the infrastructure burden of building context-aware AI agents: persistent memory, semantic caching, governed data access, and live data sync, fully managed on Redis Cloud or self-managed on your own infrastructure.
 
 <div class="grid grid-cols-1 md:grid-cols-4 gap-6 my-8">
-  {{< image-card image="images/ai-model.svg" alt="Concepts icon" title="Concepts — What happens when an agent asks Redis Iris for context" url="/develop/ai/context-engine/concepts" >}}
-  {{< image-card image="images/ai-brain.svg" alt="Agent Memory icon" title="Agent Memory — Persistent short-term and long-term memory across agent interactions" url="/develop/ai/context-engine/agent-memory" >}}
-  {{< image-card image="images/ai-LLM-memory.svg" alt="LangCache icon" title="LangCache — Semantic caching to reduce LLM costs and improve response times" url="/develop/ai/context-engine/langcache" >}}
-  {{< image-card image="images/ai-cube.svg" alt="Context Retriever icon" title="Context Retriever — Governed, schema-first data access tools for agents" url="/develop/ai/context-engine/context-retriever" >}}
+  {{< tile-card color="bg-blue-300" title="Concepts" description="What happens when an agent asks Redis Iris for context" url="/develop/ai/context-engine/concepts" >}}
+  {{< tile-card color="bg-violet-300" title="Agent Memory" description="Persistent short-term and long-term memory across agent interactions" url="/develop/ai/context-engine/agent-memory" >}}
+  {{< tile-card color="bg-teal-300" title="LangCache" description="Semantic caching to reduce LLM costs and improve response times" url="/develop/ai/context-engine/langcache" >}}
+  {{< tile-card color="bg-rose-300" title="Context Retriever" description="Governed, schema-first data access tools for agents" url="/develop/ai/context-engine/context-retriever" >}}
 </div>
 
 ## What is Redis Iris?
 
 Redis Iris is a production-ready context engine for AI agents that:
 
-<ul class="my-4 space-y-2">
-  <li class="flex gap-3"><span class="text-redis-red-500 font-bold mt-0.5">&#9679;</span><span><strong>Reduces LLM costs</strong> — Semantic caching returns cached responses for similar queries in milliseconds</span></li>
-  <li class="flex gap-3"><span class="text-redis-red-500 font-bold mt-0.5">&#9679;</span><span><strong>Adds persistent memory</strong> — Agents remember past interactions and user preferences across sessions</span></li>
-  <li class="flex gap-3"><span class="text-redis-red-500 font-bold mt-0.5">&#9679;</span><span><strong>Structures business data access</strong> — Context Retriever generates governed tools agents can safely call at runtime</span></li>
-  <li class="flex gap-3"><span class="text-redis-red-500 font-bold mt-0.5">&#9679;</span><span><strong>Keeps data fresh</strong> — Data Integration streams live changes from relational databases into Redis within seconds</span></li>
-  <li class="flex gap-3"><span class="text-redis-red-500 font-bold mt-0.5">&#9679;</span><span><strong>Requires no database management</strong> — All four services are fully managed on Redis Cloud via REST API</span></li>
-</ul>
+- **Reduces LLM costs**: Semantic caching returns cached responses for similar queries in milliseconds
+- **Adds persistent memory**: Agents remember past interactions and user preferences across sessions
+- **Structures business data access**: Context Retriever generates governed tools agents can safely call at runtime
+- **Keeps data fresh**: Data Integration streams live changes from relational databases into Redis within seconds
+- **Deploys your way**: All four services are available fully managed on Redis Cloud or self-managed on your own infrastructure, via REST API
 
 See [how Redis Iris works](/content/develop/ai/context-engine/concepts/_index.md) for the mental model before you start building.
 
@@ -45,23 +44,23 @@ See [how Redis Iris works](/content/develop/ai/context-engine/concepts/_index.md
       <li>Agents that remember context across sessions and users</li>
       <li>Faster responses and lower costs through semantic caching</li>
       <li>Reliable, structured access to live business data</li>
-      <li>No stale data — near real-time sync from your source databases</li>
+      <li>No stale data: near real-time sync from your source databases</li>
     </ul>
   </div>
   <div class="p-5 border border-redis-pen-300 rounded-lg">
     <h3 class="text-redis-ink-900 font-semibold mb-3">For developers</h3>
     <ul class="space-y-1 text-redis-pen-600">
-      <li>Four fully-managed services — no infrastructure to build or maintain</li>
+      <li>Four services, fully managed on Redis Cloud or self-managed on your own infrastructure</li>
       <li>Python and JavaScript SDKs and REST APIs for all services</li>
       <li>Define your data model once, reuse it across all agents</li>
-      <li>Available on Redis Cloud with no database setup required</li>
+      <li>No database setup required on Redis Cloud</li>
     </ul>
   </div>
 </div>
 
 ## Quick example
 
-Search LangCache before calling your LLM — return a cached response in milliseconds if a semantically similar prompt has been seen before:
+Search LangCache before calling your LLM; return a cached response in milliseconds if a semantically similar prompt has been seen before:
 
 ```json
 POST /v1/caches/{cacheId}/entries/search
@@ -89,7 +88,7 @@ Redis Iris context engine includes four services:
 - **[Context Retriever](/content/develop/ai/context-engine/context-retriever/_index.md)**: Turns your business data into structured tools that AI agents can safely and reliably use, defined once and reused across all agents.
 - **[Data integration](/content/develop/ai/context-engine/data-integration/_index.md)**: Syncs live data from your existing relational databases into Redis Cloud so agents always have access to fresh, accurate business data.
 
-All four services are available on [Redis Cloud](/content/operate/iris/_index.md) using the REST API, with no database setup or management required.
+All four services are available fully managed on [Redis Cloud](/content/operate/iris/_index.md) using the REST API, with no database setup or management required, or self-managed on your own infrastructure.
 
 ## LangCache
 

content/develop/ai/context-engine/agent-memory/_index.md

@@ -24,10 +24,10 @@ When enabled, automatic summarization compacts session memory by summarizing old
 Access Redis Agent Memory through the Python and TypeScript SDKs or its REST API. It works with any agent framework or LLM provider.
 
 <div class="grid grid-cols-1 md:grid-cols-4 gap-6 my-8">
-  {{< image-card image="images/ai-model.svg" alt="Overview icon" title="Overview — What's the same and what's different if you already know Redis" url="/develop/ai/context-engine/agent-memory/overview" >}}
-  {{< image-card image="images/python-sdk-mark.svg" alt="Python SDK mark" title="Python SDK quickstart — Explore Redis Agent Memory with Python" url="/develop/ai/context-engine/agent-memory/python-sdk-quickstart" >}}
-  {{< image-card image="images/typescript-sdk-mark.svg" alt="TypeScript SDK mark" title="TypeScript SDK quickstart — Explore Redis Agent Memory with TypeScript" url="/develop/ai/context-engine/agent-memory/typescript-sdk-quickstart" >}}
-  {{< image-card image="images/rest-api-mark.svg" alt="REST API mark" title="REST API quickstart — Explore Redis Agent Memory with curl" url="/develop/ai/context-engine/agent-memory/rest-api-quickstart" >}}
+  {{< tile-card color="bg-blue-300" title="Overview" description="What's the same and what's different if you already know Redis" url="/develop/ai/context-engine/agent-memory/overview" >}}
+  {{< tile-card color="bg-redis-yellow-500" title="Python SDK" description="Explore Redis Agent Memory with Python" url="/develop/ai/context-engine/agent-memory/python-sdk-quickstart" >}}
+  {{< tile-card color="bg-redis-yellow-500" title="TypeScript SDK" description="Explore Redis Agent Memory with TypeScript" url="/develop/ai/context-engine/agent-memory/typescript-sdk-quickstart" >}}
+  {{< tile-card color="bg-teal-300" title="REST API" description="Explore Redis Agent Memory with curl" url="/develop/ai/context-engine/agent-memory/rest-api-quickstart" >}}
 </div>
 
 ## Why use Redis Agent Memory?

content/develop/ai/context-engine/context-retriever/_index.md

@@ -13,28 +13,26 @@ bannerText: Redis Context Retriever is currently available in preview. Features
 bannerChildren: true
 ---
 
-Give your agents structured, governed access to business data — without building custom tools for every project.
+Give your agents structured, governed access to business data, without building custom tools for every project.
 
 Context Retriever lets you define your data model once. It automatically generates the retrieval tools agents call at runtime, so agents always work with accurate, live data through a controlled interface rather than guessing at SQL or calling databases directly.
 
 <div class="grid grid-cols-1 md:grid-cols-4 gap-6 my-8">
-  {{< image-card image="images/ai-model.svg" alt="Concepts icon" title="Concepts — Governed tool-calling instead of direct database access, and why it matters" url="/develop/ai/context-engine/context-retriever/concepts" >}}
-  {{< image-card image="images/ai-cube.svg" alt="Quick start icon" title="Quick Start — Create a Context Retriever service on Redis Cloud" url="/operate/iris/context-retriever/create-service" >}}
-  {{< image-card image="images/ai-lib.svg" alt="Python SDK icon" title="Python SDK and CLI — Model entities and deploy tools with the redis-context-retriever package" url="https://pypi.org/project/redis-context-retriever/" >}}
-  {{< image-card image="images/ai-brain.svg" alt="Admin keys icon" title="Manage Access — Create and manage agent keys to control what each agent can access" url="/operate/iris/context-retriever/view-admin-keys" >}}
+  {{< tile-card color="bg-blue-300" title="Concepts" description="Governed tool-calling instead of direct database access, and why it matters" url="/develop/ai/context-engine/context-retriever/concepts" >}}
+  {{< tile-card color="bg-redis-red-500" title="Quick Start" description="Create a Context Retriever service on Redis Cloud" url="/operate/iris/context-retriever/create-service" >}}
+  {{< tile-card color="bg-redis-yellow-500" title="Python SDK & CLI" description="Model entities and deploy tools with the redis-context-retriever package" url="https://pypi.org/project/redis-context-retriever/" >}}
+  {{< tile-card color="bg-teal-300" title="Manage Access" description="Create and manage agent keys to control what each agent can access" url="/operate/iris/context-retriever/view-admin-keys" >}}
 </div>
 
 ## What is Context Retriever?
 
 Redis Context Retriever is a schema-first context layer for AI agents that:
 
-<ul class="my-4 space-y-2">
-  <li class="flex gap-3"><span class="text-redis-red-500 font-bold mt-0.5">&#9679;</span><span><strong>Defines business context once</strong> — Model your entities, fields, and relationships in one place, reused across all agents</span></li>
-  <li class="flex gap-3"><span class="text-redis-red-500 font-bold mt-0.5">&#9679;</span><span><strong>Auto-generates retrieval tools</strong> — Tools are created from your data model, not hand-coded per agent</span></li>
-  <li class="flex gap-3"><span class="text-redis-red-500 font-bold mt-0.5">&#9679;</span><span><strong>Keeps agents out of your database</strong> — Agents call generated tools; the system handles data access safely</span></li>
-  <li class="flex gap-3"><span class="text-redis-red-500 font-bold mt-0.5">&#9679;</span><span><strong>Governs access by design</strong> — Each agent key has access tags that automatically filter what data it can see</span></li>
-  <li class="flex gap-3"><span class="text-redis-red-500 font-bold mt-0.5">&#9679;</span><span><strong>Exposes tools via MCP</strong> — Agents call tools through a standard Model Context Protocol (MCP) interface at runtime</span></li>
-</ul>
+- **Defines business context once**: Model your entities, fields, and relationships in one place, reused across all agents
+- **Auto-generates retrieval tools**: Tools are created from your data model, not hand-coded per agent
+- **Keeps agents out of your database**: Agents call generated tools; the system handles data access safely
+- **Governs access by design**: Each agent key has access tags that automatically filter what data it can see
+- **Exposes tools via MCP**: Agents call tools through a standard Model Context Protocol (MCP) interface at runtime
 
 ## Why use Context Retriever?
 
@@ -44,17 +42,17 @@ Redis Context Retriever is a schema-first context layer for AI agents that:
     <ul class="space-y-1 text-redis-pen-600">
       <li>Agents reliably follow defined data paths instead of guessing at SQL</li>
       <li>Live, structured context from your business data at every agent step</li>
-      <li>No tool zoo sprawl — one model definition, consistent tool surface</li>
-      <li>Access control built in — agents only see what they're allowed to see</li>
+      <li>No tool zoo sprawl: one model definition, consistent tool surface</li>
+      <li>Access control built in: agents only see what they're allowed to see</li>
     </ul>
   </div>
   <div class="p-5 border border-redis-pen-300 rounded-lg">
     <h3 class="text-redis-ink-900 font-semibold mb-3">For developers</h3>
     <ul class="space-y-1 text-redis-pen-600">
       <li>Python client and <code>ctxctl</code> CLI for modeling and deploying</li>
       <li>UI-based setup available in Redis Cloud console</li>
-      <li>No per-agent tool engineering — the platform handles tool generation</li>
-      <li>Fully managed on Redis Cloud, no infrastructure required</li>
+      <li>No per-agent tool engineering: the platform handles tool generation</li>
+      <li>Available fully managed on Redis Cloud or self-managed on your own infrastructure</li>
     </ul>
   </div>
 </div>
@@ -67,15 +65,15 @@ Install the Python client, which also includes the `ctxctl` CLI:
 pip install redis-context-retriever
 ```
 
-Use the `ctxctl` CLI, the Python client, or the Redis Cloud UI to model your entities and relationships. Context Retriever uses that model to automatically generate retrieval tools that agents call at runtime through its MCP interface — agents never access your database directly.
+Use the `ctxctl` CLI, the Python client, or the Redis Cloud UI to model your entities and relationships. Context Retriever uses that model to automatically generate retrieval tools that agents call at runtime through its MCP interface. Agents never access your database directly.
 
 See the [Redis Cloud setup guide](/content/operate/iris/context-retriever/create-service.md) to create your first Context Retriever service.
 
 Redis Context Retriever helps teams expose operational context to AI agents through schema-first retrieval. It models the entities, fields, keys, and relationships that matter to an agent workflow, then presents that context through a governed tool surface the agent can call at runtime. Context Retriever helps an AI Agent understand what business objects exist, how they connect, and which paths are safe to use.
 
 ## Overview
 
-Production agents fail not because the model is wrong, but because the context layer breaks. Enterprise data can be fragmented across multiple different databases, and can be disorganized. Teams try to patch this with text-to-SQL, OpenAPI-to-MCP wrappers, or hand-built tools — which works for demos but creates tool zoo sprawl, SQL risk, and agents that can't reliably choose the right path in production. Redis Context Retriever gives teams a governed, schema-first surface agents can traverse safely.
+Production agents fail not because the model is wrong, but because the context layer breaks. Enterprise data can be fragmented across multiple different databases, and can be disorganized. Teams try to patch this with text-to-SQL, OpenAPI-to-MCP wrappers, or hand-built tools, which works for demos but creates tool zoo sprawl, SQL risk, and agents that can't reliably choose the right path in production. Redis Context Retriever gives teams a governed, schema-first surface agents can traverse safely.
 
 When you set up Redis Context Retriever, you model the objects that matter to your agent workflow and connect the relationships between them. You can do this either through the UI, using the [Context Surfaces Python Client](https://pypi.org/project/redis-context-retriever/), or the `ctxctl` CLI (available when you install the python client). Context Retriever will use those relationships to automatically create and deploy retrieval tools from your entity model.  
 
@@ -95,7 +93,7 @@ Get started with Redis Context Retriever on Redis Cloud or join the private prev
 
 Redis Context Retriever is available for self-managed deployment on Kubernetes as a private preview. See [Install Context Retriever](/content/develop/ai/context-engine/context-retriever/install/_index.md).
 
-You need a license key to deploy — [contact Redis](https://redis.io/contact/) to request access.
+You need a license key to deploy: [contact Redis](https://redis.io/contact/) to request access.
 
 {{< /multitabs >}}