> ## Documentation Index
> Fetch the complete documentation index at: https://docs.trugen.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Presentations

> Give your agent a deck. When the user asks a relevant question, the agent presents the right slide alongside its spoken answer.

**Visual Presentations** turn your agent into a presenter. Upload a PDF or PowerPoint deck to your library, attach the presentation to an agent, and when a user asks a question that matches the content, the agent shows the relevant slide while it speaks its answer.

This turns typical "explain how X works" answers into an actual walkthrough — the agent shows the pricing slide when asked about pricing, the architecture diagram when asked how the system works, and so on.

## Supported media

| Media          | Formats         | Size limit | Notes                                                             |
| -------------- | --------------- | ---------- | ----------------------------------------------------------------- |
| **PDF**        | `.pdf`          | 100 MB     | Upload a file or provide a public URL. Each page becomes a slide. |
| **PowerPoint** | `.ppt`, `.pptx` | 100 MB     | Upload a file or provide a public URL. Each slide is indexed.     |

Each slide is indexed after upload — the agent uses semantic search to find the right slide based on the user's question, similar to how [Knowledge Base](/docs/agents/knowledge/overview) retrieval works.

## Creating a presentation

<Steps>
  <Step title="Open the Presentations tab in Studio">
    In the Studio's agent creation flow, open the **Visual Presentations** tab.
  </Step>

  <Step title="Upload your media">
    Pick a media kind (PDF or PowerPoint), upload the file, and give the presentation a name and optional tags.
  </Step>

  <Step title="Wait for processing">
    Uploads process asynchronously — PDFs are page-split and PowerPoints are slide-indexed. Status moves through `pending` → `processing` → `completed`.
  </Step>

  <Step title="Attach to the agent">
    Once processing is complete, select the presentation in the tab and save the agent. It's now available for the agent to use in every session.
  </Step>
</Steps>

## How the agent uses it

During a live session:

1. The user asks a question.
2. Before answering, the agent semantically searches the attached presentations for the most relevant slide.
3. If a strong match is found, the agent both **speaks the answer** and **presents the slide** — the widget shows the slide alongside the avatar.
4. If no strong match is found, the agent falls back to answering from its system prompt and knowledge base as normal — no presentation is shown.

The agent decides when to present. You don't have to script it.

## Custom instruction

Each presentation has a **custom instruction** that tells the LLM how to answer using the retrieved slide. The default is a strict, grounded template:

```
QUESTION
{query}

RESULTS
{results}

Using the provided RESULTS, answer the QUESTION. Select the most relevant result
and present it as a slide. Keep your response strictly grounded in the RESULTS.
If the answer is not clearly supported by the RESULTS, respond with "I don't know"
and close the presentation. Do not make assumptions.
```

You can customize this per presentation from the upload modal. Common reasons to change it:

* **Loosen groundedness** — allow the agent to elaborate beyond what's on the slide
* **Change presentation style** — force the agent to summarize rather than quote
* **Adjust fallback behavior** — change what the agent says when no slide matches

The `{query}` and `{results}` placeholders are filled in at runtime.

## Attaching to an agent

Presentations are attached via the `visual_presentations` array on the agent config:

```json theme={null}
{
  "agent_name": "Sales Agent",
  "visual_presentations": [
    { "id": "presentation-uuid-1" },
    { "id": "presentation-uuid-2" }
  ]
}
```

Attach as many presentations as makes sense. The agent searches across all of them and picks the best match.

## Best practices

* **Split large decks by topic.** A 100-slide master deck retrieves worse than 5 focused 20-slide decks. The agent picks the right presentation before it picks the right slide.
* **Use clear slide titles.** Slide titles are heavily weighted in retrieval. "Q3 Pricing Update" is more findable than "Slide 12."
* **Prefer PDF over PowerPoint** when the source allows. PDFs process faster and produce cleaner slide extractions.
* **Test with real user questions.** After attaching, join a test session and ask 5–10 questions the way your users would. Watch which slides come up and which don't.

## Presentations vs Knowledge Base

Both are retrieval-based, but they serve different purposes.

| Use Knowledge Base for             | Use Visual Presentations for                     |
| ---------------------------------- | ------------------------------------------------ |
| Text answers grounded in documents | Answers that need to *show* something visually   |
| FAQs, policies, product docs       | Pitch decks, tutorials, product screenshots      |
| Long-form written content          | Slide-per-idea material designed to be presented |

You can — and often should — use both on the same agent.

## Next steps

<CardGroup cols={2}>
  <Card title="Knowledge Base" icon="database" href="/docs/agents/knowledge/overview">
    Attach text-based sources for grounded written answers.
  </Card>

  <Card title="Prompting" icon="pen" href="/docs/agents/prompting-strategies">
    Write a system prompt that plays well with a presenting agent.
  </Card>
</CardGroup>