HalosHalosDocs

Training Your Agents

Training is what makes your agents yours. A freshly deployed agent knows its specialty and has a default personality, but training lets you teach it your specific knowledge, rules, and communication style.

How Training Works

When you add training data to an agent, that data gets injected into the agent's system prompt every time it responds. The agent doesn't just memorize facts — it uses your training data as context to shape every response.

This means:

  • An email agent trained on your company's support docs will write replies using your terminology
  • An agent with custom instructions to "always respond in bullet points" will do exactly that
  • An agent trained with example conversations will mirror the tone and style you demonstrate

Three Types of Training Data

You can add three types of training data, each serving a different purpose:

Knowledge

What it is: Facts, documents, reference material, or any text your agent should know about.

Use it for:

  • Company documentation, FAQs, or wikis
  • Product specs and feature lists
  • Personal notes and preferences
  • Research papers or article summaries
  • Any reference material the agent should draw from

Example:

Title: Company Return Policy

Content: Our return policy allows returns within 30 days of purchase. Items must be unused and in original packaging. Refunds are processed within 5-7 business days. Digital products are non-refundable. For damaged items, we offer free replacements regardless of the return window.

Instructions

What it is: Custom rules and behavioral guidelines that tell the agent how to behave.

Use it for:

  • Communication style rules ("Always be formal", "Use bullet points")
  • Guardrails ("Never recommend competitor products")
  • Process rules ("Always ask for the order number first")
  • Role-specific behavior ("You are a senior frontend engineer reviewing code")

Example:

Title: Response format

Content: Always structure responses with a one-sentence summary first, then detailed explanation. Use headers for sections longer than 3 paragraphs. End with a "Next steps" section when applicable.

Examples

What it is: Example conversations showing the agent exactly how to respond in specific scenarios.

Use it for:

  • Demonstrating your preferred tone and style
  • Teaching domain-specific Q&A patterns
  • Showing how to handle edge cases
  • Few-shot learning for specific tasks

Example:

Title: Handling refund requests

Content: User: I want a refund for my order Assistant: I'd be happy to help with your refund. Could you share your order number so I can pull up the details? In the meantime — our policy covers returns within 30 days of purchase for unused items in original packaging.

Adding Training Data

  1. Navigate to the agent's profile page (tap their avatar in The Yard)
  2. Scroll to the Training section and tap Train [agent name]
  3. Click Add Training Data
  4. Select the type (Knowledge, Instruction, or Example)
  5. Add a title and the content
  6. Click Add

The training data takes effect immediately — the next time you chat with the agent, it will use the new context.

Managing Training Data

On the training page, you can see all entries for an agent at a glance:

  • Toggle on/off — Temporarily disable an entry without deleting it. Useful for A/B testing different instructions.
  • Expand — Long entries are truncated by default. Click "More" to see the full content.
  • Delete — Permanently remove an entry.

The stats at the top show how many knowledge entries, instructions, and examples the agent has.

Best Practices

Start Small

Add a few key pieces of knowledge and one or two instructions. Chat with the agent to see how it behaves, then iterate. It's easier to refine than to dump everything at once.

Be Specific in Instructions

Instead of "be helpful," try "when the user asks about pricing, always mention the free tier first, then compare the Pro and Enterprise plans side by side."

Use Examples for Tone

If you want a specific communication style, examples are the most effective way to teach it. The agent will pattern-match against your examples more reliably than following abstract instructions.

Title Entries Clearly

Good titles make it easy to manage training data as it grows. Use descriptive names like "Q3 product changelog" or "Escalation handling rules" rather than "Info 1."

Disable Instead of Delete

If you're not sure whether an entry is helping, toggle it off instead of deleting it. You can always re-enable it later.

Limits

Training data is included in the agent's context window, which means there's a practical limit to how much you can add before responses start to degrade. As a rough guide:

  • Knowledge: Up to ~20 entries works well. For very large knowledge bases, keep individual entries focused and concise.
  • Instructions: 5-10 well-written instructions are more effective than 50 vague ones.
  • Examples: 3-5 high-quality examples per scenario are usually sufficient.

Next Steps

Your agent is trained — now put it to work.