# Agent Models

> Pick the agent model that fits your use case, from fast high-volume chat to HIPAA-compliant healthcare.

Source: https://docs.getlinkai.com/agents/models

Link AI uses **agent models**: combinations of LLMs from several providers, tuned for specific use cases. Each agent model routes every request to the best underlying LLM for the task, balancing quality, speed, and cost.

![Agent Models](https://docs.getlinkai.com/screenshots/v2/agent-brain.png)

## Available agent models

| Model | Optimized for | Quality | Speed |
|-------|---------------|---------|-------|
| **Link Core Smart** | Complex reasoning and accuracy. Handles nuanced questions. | Highest | Moderate |
| **Link Core Fast** | Speed and efficiency for high-volume, real-time conversations | Good | Fastest |
| **Link Health Smart** | HIPAA-compliant, accurate, thoughtful answers for healthcare | High | Moderate |
| **Link Health Fast** | HIPAA-compliant, fast answers for high-volume healthcare conversations | Good | Fast |

The Health models use a selected mix of LLMs that meet healthcare compliance requirements.

## Choose a model

| Choose | When |
|--------|------|
| **Link Core Smart** | Accuracy is critical, you need complex reasoning, or quality matters more than speed |
| **Link Core Fast** | You need fast replies, handle high volume, and standard accuracy is enough |
| **Link Health Smart** | You're in healthcare, need HIPAA compliance, and quality matters more than speed |
| **Link Health Fast** | You're in healthcare, need HIPAA compliance, and handle high volume |

**Tip:**
Start with Link Core Fast for most use cases. It gives good quality at the best cost and speed. Move to Link Core Smart only if you need better accuracy and reasoning.

## Select a model

### Open the Brain tab

Open the agent from **My Agents** and go to the **Brain** tab.

### Pick the model

Select the agent model from the dropdown.

### Save

Save your changes. The model routes each request to the right mix of LLMs from then on.

## Settings

### Temperature

Temperature controls how random responses are.

| Range | Behavior | Use it for |
|-------|----------|------------|
| **0.1 to 0.3** | Focused and deterministic | Factual information |
| **0.5 to 0.7** | Balanced creativity and consistency | Most cases (recommended) |
| **0.8 to 1.0** | More creative and varied | Only when creativity is needed |

### Token limits

| Limit | What it controls | Typical range |
|-------|------------------|---------------|
| **Prompt tokens** | How much context the agent considers | 4,000 to 8,000 |
| **Completion tokens** | Maximum response length | 1,000 to 2,000 |

Higher limits allow more context and longer replies, but cost more. Agent models already optimize token usage. Monitor usage in analytics and adjust limits to match.

## Get better results

- **Write clear instructions.** Be specific, give examples, set boundaries, and include relevant context. Better **Instructions** improve results more than switching models. See [Prompting Tips](https://docs.getlinkai.com/getting-started/prompting-tips).
- **Fill your knowledge base.** A complete [Knowledge Base](https://docs.getlinkai.com/agents/knowledge-base) means the model generates less from scratch, which improves accuracy and lowers cost.
- **Compare models.** Run the same set of real customer questions against each model. Compare quality, speed, and cost, then pick the best fit.
- **Test before you switch.** Test a new model in the live test chat before you use it with customers.
- **Iterate on data.** Track answer quality, response time, token usage, and error rates. Switch models if quality falls short, adjust temperature if replies are too random or too rigid, and tune token limits to real usage.

## Troubleshooting

**Answer quality is poor**
1. Try a different model, such as Link Core Smart instead of Link Core Fast.
2. Improve the **Instructions**.
3. Add more content to the knowledge base.
4. Adjust temperature.

**Replies are slow**
1. Switch to a faster model, such as Link Core Fast or Link Health Fast.
2. Lower the completion token limit.
3. Make the **Instructions** more concise.
4. Check for network or API issues.

## Next steps

**[Configure Agent](https://docs.getlinkai.com/agents/configure-agent)**:
Set instructions, persona, and every agent tab.

**[Knowledge Base](https://docs.getlinkai.com/agents/knowledge-base)**:
Give the model accurate content to answer from.

**[Prompting Tips](https://docs.getlinkai.com/getting-started/prompting-tips)**:
Write instructions that get better answers.

**[Actions](https://docs.getlinkai.com/agents/actions)**:
Let your agent take real steps for customers.