The Tool Desk
Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Outbyte Driver Updater FREEScan for outdated or missing drivers - takes under a minuteDriver Scan →iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Home Assistant Assist is the user-facing voice or text interface and the pipeline that carries a request to a conversation agent. A script is a saved sequence of actions that runs only when something calls it. An LLM conversation agent uses a language model to interpret requests and may call tools—such as scripts—that you have made available to it. Assist does not require an LLM: its built-in conversation agent can match supported sentences locally.
The simplest way to choose is by role: use Assist for natural-language interaction, a script for reusable actions on demand, and an LLM agent when you want model-based interpretation. These pieces can work together, but they are not interchangeable.
What is the difference between Assist, a script, and an LLM agent?
They occupy different layers of a Home Assistant setup. Assist receives a person’s request and routes it through a pipeline; a conversation agent interprets the request; and a script performs a defined sequence when a caller starts it. The built-in conversation agent and an LLM agent are alternative ways to interpret a request, not alternate names for Assist.
| Component | Primary role | How it starts | Does it inherently need an LLM? |
|---|---|---|---|
| Assist | User-facing voice or typed assistant and request pipeline | A voice or typed request enters a pipeline | No. The built-in agent can match supported sentences locally. |
| Script | Saved sequence of actions | A caller explicitly runs it | No |
| LLM conversation agent | Interprets conversational input and may select available tools | A conversation request is sent to the agent | Yes |
Home Assistant introduced Assist in version 2023.2. Its LLM integration documentation dates to version 2026.7; that is the introduction date for the framework integration page, not a claim that every LLM conversation integration first became possible in that release.
#1 Best Overall
- Read Before You Buy — No Video Output: These adapters support charging and USB 2.0 data transfer, but cannot transmit video signals. Except for standard USB webcams (which use USB data only), they are not compatible with HDMI/DisplayPort cables, video-capable USB-C hubs, or docking stations with video output.
- Convert USB-A Ports to USB-C: Designed to connect USB-C earphones, cables, flash drives, card readers, and other USB-C accessories to standard USB-A ports. Plug-and-play with no drivers or software required.
- Aluminum Alloy Housing: Built with a sturdy aluminum alloy shell that aids in heat dissipation and protects against daily wear and scratches. Designed to maintain a stable and secure connection.
- Compact & Travel-Friendly: The ultra-compact design allows the adapter to stay plugged into your device without blocking adjacent ports or adding bulk, reducing wear and tear on your original USB ports.
- 12-Month Warranty: Backed by a 12-month manufacturer warranty for peace of mind. Designed to meet strict quality control standards for reliable everyday performance.
How do the three parts work together?
In a voice interaction, the request can pass through wake-word detection and speech-to-text before conversation processing. A response may then pass through text-to-speech. Those stages can run locally, through integrations, or in the cloud depending on how the pipeline is configured. A typed request can enter the conversation pipeline without the voice-processing stages.
At the conversation stage, the selected agent interprets the text. The built-in agent matches supported sentence patterns to intents. An LLM agent instead uses a language model and can select from the tools made available to it. If the selected tool is an eligible script, Home Assistant runs that script; the script itself remains a defined action sequence rather than turning into a conversational agent.
That separation helps diagnose where a problem lies. A request may fail to be transcribed, may not match the built-in agent’s supported patterns, may be interpreted incorrectly by an LLM, or may reach a script whose action does not produce the intended result. Treating these as separate stages makes troubleshooting more precise than changing scripts when the request was never understood.
When should I use a script instead of an automation or scene?
Use a script for an action sequence that should be reusable or started on demand. Use an automation when a trigger or state change should start the sequence, and use a scene to apply a saved group of device states together rather than to run sequential steps or branching logic.
Choose a script when a caller should decide when to run it
A dashboard control, Assist request, automation, or another caller can start a script. A script has no trigger of its own, so saving one does not make it run when a device changes. The caller supplies that starting point.
Rank #2
- 5-in-1 USB-C Hub: Experience comprehensive connectivity featuring a Power Delivery input, two USB-A 2.0 ports, a USB-A 3.0 port, and an HDMI port. (Note: The USB-C power delivery input port is only for connecting an external wall charger to power your laptop and cannot power peripheral devices.)
- 90W Pass-Through Charging: Achieve optimal charging with 90W pass-through power to your laptop, supported by a total input of 100W, with the hub reserving 10W for operational efficiency. (Note: Wall charger not included.)
- Quick Data Transfers: Accelerate your productivity with rapid data transfers using a high-speed 5Gbps USB 3.0 port and two 480Mbps USB 2.0 ports.
- 4K HDMI Display: Enhance your visual experience with a hub capable of delivering 4K resolution at 30Hz in both mirror and extend modes. Please note that this hub is compatible with MacBook (macOS 12 and newer), Windows 10 and 11, ChromeOS, and laptops equipped with DP Alt Mode and Power Delivery. Note: This device is not compatible with Linux.
- What You Get: Anker USB-C Hub (5-in-1, 4K HDMI), welcome guide, 18-month warranty, and our friendly customer service.
This makes scripts useful for a routine that multiple callers may need. For example, an automation can start a script after a condition is met, while a person can start the same sequence on demand. The sequence is defined once; the callers determine when it runs.
Choose an automation when an event should start the work
If the requirement is “when this state changes, do these actions,” the trigger belongs in an automation. A script can still hold reusable actions called by that automation, but it does not replace the trigger logic.
Choose a scene when the goal is a group of states
A scene is the better fit for applying a saved set of device states together. Use a script when the work depends on an ordered sequence or branching behavior. The distinction is about the shape of the task, not whether the task is launched by voice.
Does Assist need an LLM?
No. Assist is the interface and pipeline; it can use Home Assistant’s built-in conversation agent, which matches supported sentence patterns locally. An LLM conversation agent is an optional alternative for requests that benefit from more flexible conversational interpretation.
The built-in agent and an LLM solve different interpretation problems. The built-in path works with the sentence patterns and intents it supports. An LLM can interpret more open-ended wording, but its available home-control tools and exposed entities need to be configured deliberately. Choosing an LLM does not automatically make every entity or script available to it.
Rank #3
- Sleek 7-in-1 USB-C Hub: Features an HDMI port, two USB-A 3.0 ports, and a USB-C data port, each providing 5Gbps transfer speeds. It also includes a USB-C PD input port for charging up to 100W and dual SD and TF card slots, all in a compact design.
- Flawless 4K@60Hz Video with HDMI: Delivers exceptional clarity and smoothness with its 4K@60Hz HDMI port, making it ideal for high-definition presentations and entertainment. (Note: Only the HDMI port supports video projection; the USB-C port is for data transfer only.)
- Double Up on Efficiency: The two USB-A 3.0 ports and a USB-C port support a fast 5Gbps data rate, significantly boosting your transfer speeds and improving productivity.
- Fast and Reliable 85W Charging: Offers high-capacity, speedy charging for laptops up to 85W, so you spend less time tethered to an outlet and more time being productive.
- What You Get: Anker USB-C Hub (7-in-1), welcome guide, 18-month warranty, and our friendly customer service.
Voice processing is another separate choice. Wake-word detection, speech-to-text, conversation, and text-to-speech may use different local, integration-based, or cloud components. Therefore, “Assist is local” or “Assist is cloud-based” is too broad without knowing the configured pipeline stages and agent.
Do these 3 things before closing this tab:
1Fix the driver behind crashes, sound loss and screen glitches2Clear out junk files and repair common Windows errors3Scan for outdated or missing drivers - takes under a minuteHow do I let an LLM agent call a script?
Configure a supported conversation integration for Assist mode with home control enabled, then enable the individual script for Assist. Give the script a clear name and a concise description explaining what it does and when the agent should use it. If the script accepts inputs, describe what each input means and the expected format so the model can select and call it appropriately.
- Configure the conversation integration and choose the Assist mode that enables home control.
- Open the script’s settings and enable that script for Assist.
- Write a specific description that distinguishes the script from other available actions and says when it is appropriate.
- Add descriptions to input fields, including the meaning and expected format of each input.
- Test a request through the relevant Assist pipeline and inspect whether the agent selected and called the intended tool.
Expose only the scripts and entities needed for the use case. An LLM’s choices depend on the tools and information it can see; unnecessary options can make tool selection less focused and increase the context it must process. A script exposed to the agent remains a callable action, not an ordinary static entity.
For scripts that need to report an outcome, a Stop action can return a success or error message for the agent to relay. This gives the conversation a useful result to communicate instead of treating the script as a silent action.
How can I test whether the problem is the sentence matcher or the LLM?
Use the developer Assist tab to test the built-in sentence matcher, and use Assist Debug for a pipeline that uses another conversation agent. The first tool tests matching; it does not execute actions.
Recommended Free Tools
Rank #4
- Dual Converters, Infinite Potential：Includes 2× USB C male to USB A female adapters and 2× USB A male to USB C female adapters. Perfect for a wide range of uses—tablets with Bluetooth keyboards, expand USB ports on macbook, and more. Two different converters for all your daily needs
- Next-Level 10Gbps & 3A Charging: No more slow 480Mbps, this usb to usb c adapter has a transfer speed of up to 10Gbps, allowing you to do more transferring in less time. This usb adapter fits both USB A and USB C charger, supporting up to 3A fast charging
- Upgraded Exquisite Craftsmanship: With an aluminum alloy housing and metal connector, the usbc to usb adapter is extremely durable and sturdy. Rigorously tested to withstand more than 10,000 times of plugging and unplugging, ensuring long-lasting performance
- Broad Compatible: The usb c to usb adapter widely supports all USB C/ USB A devices like laptops, tablets, cellphones, car chargers, and phone chargers. Such as compatible with MacBook Pro/Air 2023/2022, Thunderbolt 4/3 Devices,Apple MagSafe Watch 9/8/7/SE/Ultra, iPad Pro 2022/2021, Samsung Galaxy S23/S20/S10, and iPhone 17/16/15 Pro. Plug and play
- Please Note: To reach 10Gbps speed, keep the cable under 3.3 ft. For USB A Male to USB C adapters, try flipping the USB C connector. USB C Male to USB A adapters support bidirectional 10Gbps transfer within 3.3 ft
Test built-in sentence matching
- Open Settings > Tools > Assist.
- Enter the sentence you want to check and review whether the built-in agent matches it.
- Do not treat a successful match in this tab as proof that a script or device action ran: the tab tests the matcher without executing actions.
Inspect a different conversation agent
When the pipeline uses an LLM or another conversation agent, use the Assist Debug view instead. Check the conversation and tool calls to see whether the agent interpreted the request as intended and selected an available action. Since scripts are registered as tools, inspect those calls rather than expecting a script to appear as a static entity.
If the agent did not choose the script, review whether the script is enabled for Assist and whether its description and inputs make its purpose clear. If it chose the script but the result was wrong, examine the script’s own actions and the input values it received. These checks separate an exposure or interpretation issue from an execution issue.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.What should I expose to Assist and an LLM?
Entity exposure is opt-in, and the useful scope depends on the task. Give an assistant access to only the entities and scripts needed for the requests you want it to handle. This limits the available control surface and avoids presenting irrelevant choices to the conversation agent.
For a built-in sentence-matching use case, expose the entities needed for the supported intents. For an LLM workflow, also expose only the scripts that make sense as callable tools, with descriptions that help distinguish them. A broad list is not automatically better: additional exposed entities can increase matching work and LLM context, while unclear or overlapping script descriptions make it harder to select the right action.
Think of exposure as a configuration decision, not a guarantee of behavior. Making a script available allows an agent to call it when appropriate; it does not mean every conversational request will trigger that script. The agent still has to interpret the request and select the tool.
Best Value
- 5-in-1 Connectivity: Equipped with a 4K HDMI port, a 5 Gbps USB-C data port, two 5 Gbps USB-A ports, and a USB C 100W PD-IN port. Note: The USB C 100W PD-IN port supports only charging and does not support data transfer devices such as headphones or speakers.
- Powerful Pass-Through Charging: Supports up to 85W pass-through charging so you can power up your laptop while you use the hub. Note: Pass-through charging requires a charger (not included). Note: To achieve full power for iPad, we recommend using a 45W wall charger.
- Transfer Files in Seconds: Move files to and from your laptop at speeds of up to 5 Gbps via the USB-C and USB-A data ports. Note: The USB C 5Gbps Data port does not support video output.
- HD Display: Connect to the HDMI port to stream or mirror content to an external monitor in resolutions of up to 4K@30Hz. Note: The USB-C ports do not support video output.
- What You Get: Anker 332 USB-C Hub (5-in-1), welcome guide, our worry-free 18-month warranty, and friendly customer service.
Which option should I choose for a common home-control task?
Start with the caller and the kind of work: decide whether a person is making a request, an event should trigger an action, or a saved state should be applied. Then choose the interpretation and action mechanisms that fit.
- A person asks to control the home by voice or text: use Assist as the request interface.
- The request matches a supported sentence pattern: the built-in conversation agent may handle it without an LLM.
- The request needs more flexible conversational interpretation: use an LLM conversation agent, with a limited and well-described set of tools and entities.
- A reusable sequence should start when called: create a script and decide which callers should be able to start it.
- A state change should initiate a sequence: create an automation, optionally calling a reusable script.
- Several devices should take saved states together: use a scene.
These choices can be combined. For example, Assist can carry a person’s request to an LLM agent, which can choose an exposed script to perform a multi-step action. Or an automation can run a script without any conversation agent being involved. The component that accepts the request, the component that interprets it, and the component that performs actions remain distinct.
Frequently Asked Questions
Can a script appear as a normal entity to an LLM?
Home Assistant says scripts do not appear in the static entity list an LLM sees; they appear as callable tools. That is why enabling a script for Assist and describing its purpose are separate from exposing ordinary entities.
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Repair Windows errors before they cause bigger problemsFix Now →How many scripts or tools can I expose to an LLM?
Home Assistant documents a maximum of 128 scripts and tools in total. Exceeding that total can result in a hard-limit error, so keep the set focused rather than exposing every available action.
Can an automation or script send text to a conversation agent without voice?
Yes. The conversation.process action can send text to a selected or default conversation agent and capture its response. This is useful when another part of a setup generates text that should be interpreted as a request.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
