# Cognition Recipes Overview

Build intelligent agents from the ground up using [EmbodiedAgents](https://github.com/automatika-robotics/embodied-agents), the EMOS intelligence framework. These recipes introduce the core [Components](../../intelligence/ai-components.md) -- the modular building blocks that drive your physical agents.

Every capability -- hearing, speaking, seeing, thinking -- is a component you wire together in pure Python. No ROS XML, no boilerplate.

---

::::{grid} 1 2 3 3
:gutter: 3

:::{grid-item-card} {material-regular}`chat;1.2em;sd-text-primary` Conversational Agent
:link: conversational-agent
:link-type: doc

Your first agent -- wire STT, VLM, and TTS into a multimodal dialogue system.
:::

:::{grid-item-card} {material-regular}`edit_note;1.2em;sd-text-primary` Prompt Engineering
:link: prompt-engineering
:link-type: doc

Shape agent behavior with dynamic Jinja2 templates at the topic or component level.
:::

:::{grid-item-card} {material-regular}`map;1.2em;sd-text-primary` Semantic Map
:link: semantic-map
:link-type: doc

Give your robot spatio-temporal memory backed by a Vector DB.
:::

:::{grid-item-card} {material-regular}`near_me;1.2em;sd-text-primary` GoTo Navigation
:link: goto-navigation
:link-type: doc

Navigate to locations from natural language commands.
:::

:::{grid-item-card} {material-regular}`build;1.2em;sd-text-primary` Tool Calling
:link: tool-calling
:link-type: doc

Give the LLM access to executable functions so it can act on the world.
:::

:::{grid-item-card} {material-regular}`alt_route;1.2em;sd-text-primary` Semantic Routing
:link: semantic-routing
:link-type: doc

Route messages to different graph branches based on meaning, not topic names.
:::

:::{grid-item-card} {material-regular}`smart_toy;1.2em;sd-text-primary` Complete Agent
:link: complete-agent
:link-type: doc

Combine perception, memory, and reasoning into a fully embodied system.
:::

::::