knovis_icon_square
Knovis

AI Agent

The Knovis agent helps you populate, enrich, and build environments using plain English. Tell it what you want, review what it plans to do, and let it handle the repetitive work: filling in metadata, finding images, setting up DataTags across hundreds of items at once.

What the agent can do

  • Fill in DataTag fields: titles, descriptions, keywords, dates, links
  • Find and set thumbnail images from the web
  • Apply templates across a whole environment
  • Batch-update settings across all items matching a filter
  • Propose waypoints and routes based on how your content is organized
  • Create items and environments from scratch given a description
  • Scan a folder on your computer and generate item stubs from what it finds

The agent always shows you what it plans to do before it does anything. You review the proposed changes and approve, skip, or adjust; nothing is applied without confirmation.

Three tiers

Knovis uses three different modes depending on what you're asking for and what you have set up. They're not separate features; the same agent panel handles all three. The difference is what's running behind the scenes.

Tier 1: Built-in rules

No AI model required. Tier 1 handles precise, mechanical operations using built-in logic, for things where you know exactly what you want and can describe it clearly.

Examples:

  • Fetch favicons for all website items in an environment
  • Set all video items to open with the Knovis player
  • Apply a specific setting to every item matching a tag or type

Tier 1 also powers the image fetch and DataTag buttons you'll find in the item panel; those actions run without any external model. If you're a power user comfortable writing structured commands, Tier 1 also accepts direct JSON instructions for full control over batch operations.

Who it's for: Anyone who wants to automate repetitive settings changes or bulk actions across many items. No AI setup needed.

Tier 2: Local AI model

Tier 2 uses a small AI model that runs entirely on your machine. It reads your existing items, infers what's missing, and fills it in. No data leaves your computer, no API key required.

This is what powers the Fill Metadata and Find Image buttons in the item panel. The model looks at what you already have (the item label, existing tags, the target file or URL) and completes the gaps: a description, relevant keywords, a collection role.

Tier 2 works best for structured enrichment tasks where the answers come from the content itself. It reads and completes existing content rather than inventing anything new.

Examples:

  • Fill in missing descriptions and keywords across a whole environment
  • Find thumbnail images for items that don't have one yet
  • Complete DataTag fields for a batch of items in one pass
Setup: Download a compatible local model (llama.cpp format) and point Knovis to it in Preferences. The model file is around 1 GB. Once set up, Tier 2 runs offline with no ongoing cost.

Tier 3: Frontier AI model

Tier 3 connects to an external AI service such as Anthropic (Claude) or OpenAI (GPT-4). This is the most capable tier and handles tasks that require real judgment: creative layout decisions, generating environments from a description, understanding relationships between content, and producing natural-sounding metadata at scale.

Examples:

  • "Build a Star Trek TNG environment organized by season, with waypoints for each one"
  • "Create items for these 12 research papers and arrange them by topic"
  • "Flag the most essential items in this environment and suggest a presentation route"

Tier 3 uses tokens from your API account, so each operation has a small cost. For most enrichment tasks the cost is a few cents. Complex environment generation with many items costs more.

Setup: Add your API key in Preferences under Agent. You can use an Anthropic key, an OpenAI key, or both; Knovis lets you choose which model to use per session.

How a typical session works

  1. Open the Agent panel from the View menu
  2. Type what you want in plain English, such as "fill in metadata for all items in this environment" or "find images for items without one"
  3. The agent asks any clarifying questions it needs, then shows you a preview of the changes it plans to make
  4. Review the list: approve all, skip individual items, or cancel
  5. Approved changes are applied and saved

Approving changes

For each item the agent wants to modify, you'll see what it currently has and what it's proposing to change. You can:

  • Accept: apply this change
  • Skip: leave this item as is
  • Automate rest: accept all remaining items without reviewing each one

The agent never applies changes silently. If it can't figure out what you're asking, it asks rather than guesses.

← Back Gamepad & TV