Quick answers to the most common questions about the Discovery Agent, from how it works to what it can't do yet. Use it to check a specific detail, or read start to finish for a full overview.
What is the Moments Lab Discovery Agent?
The Discovery Agent is your AI-powered research assistant for video. Instead of relying on keyword-based search, it understands natural language, context and intent to surface the exact clips, quotes or moments you need, down to timecodes. It's like having your smartest researcher embedded in your catalog, available at any time, delivering answers in seconds instead of hours.
How is it different from current search workflows?
Traditional search depends on exact keywords, metadata or the one person who knows the system. The Discovery Agent takes a different approach:
Understands what you mean, not just what you type.
Finds results even with poor or missing metadata.
Surfaces moments, not just files.
Lets you refine results in conversation instead of running endless queries.
It turns hours of scrubbing into seconds of discovery.
Who benefits the most from this feature?
Digital and social teams: find highlights quickly without waiting on archivists.
Archivists and system experts: spend less time on requests and focus on higher-value work.
External partners, like sponsors or broadcasters: get self-serve access to the clips they need.
Every group in your workflow saves time and produces better content, faster.
Does it work only for short-form, social-style content?
Not at all. The Discovery Agent is just as powerful for long-form storytelling. Whether you're cutting a recap, a documentary or a feature promo, it surfaces supporting footage, forgotten catalog material and thematic moments to enrich your stories.
Does it require my teams to learn new workflows?
No training is needed. The Agent uses a simple chat-style interface: you describe what you're looking for in natural language. Even freelancers or new hires can be productive on day one, as easy as asking a teammate rather than learning a new tool.
Can it answer general knowledge questions?
Yes. Beyond searching your library, the Agent can also answer contextual questions, like who won a specific event. This saves your team from switching between tools while researching and producing content.
How do I access the Discovery Agent?
The Discovery Agent is built directly into the Moments Lab platform and available at any time, from anywhere in your workspace. Click the Discovery Agent icon in the top-right corner to start searching without leaving your current view.
Can I use the Agent to search within specific collections?
Not at this time. The Agent can use context at the media level though: when you're viewing a media item, it automatically uses that media as context for more relevant results.
Does the Agent understand what media I'm viewing?
Yes. The Agent is context-aware. When you open it from a media page, it automatically detects what you're viewing and tailors its responses. Remove the media context anytime if you want to search more broadly.
What languages are supported?
English, French, Arabic, Dutch and Spanish. Both the interface and the Agent's responses are delivered in your chosen language, so global teams can collaborate more easily.
What roles have access to the Discovery Agent?
All roles can access and use the Agent.
Can the Agent read and understand documents or articles linked in a prompt?
Yes. If you include a link, the Agent can read it and incorporate that context into its response.
Can I upload images or videos in my prompt?
Not directly. The Agent can only analyze videos already processed by MXT3 (Moments Lab's video understanding AI) within Moments Lab.
How long does it take the Agent to respond to a query?
On average, about 30 seconds. Simple text-based requests are faster, while complex requests, like returning several diverse clips, take a little longer.
Can I make follow-up prompts?
Yes. The Agent is conversational, so you can refine results, ask for similar content, or pivot to a new request without starting from scratch, just like an ongoing conversation with a researcher.
Does the Agent replace global search in the platform?
No, it complements it. Power users can still run precise searches with the search bar, while the Agent makes discovery more intuitive for everyone else.
Can I provide feedback on Agent answers?
Yes, with a thumbs up or thumbs down. This feedback is currently used to monitor performance and identify pain points, and will eventually improve the Agent's responses over time.
What are best practices for prompting the Discovery Agent?
The more context you provide, the better the results. Framing what you're looking for, and why, helps the Agent plan and return more relevant results. Learn how to write a great prompt.
Does the Agent return files that aren't indexed by MXT3?
Yes, but only at the file level, based on the title or basic metadata. To return moment-level clips, the file needs to be indexed by MXT3.
Can the Discovery Agent be branded or renamed?
Not today, but custom branding and naming are being considered for the future.
What customization options are available?
You can configure the Agent with a workspace description covering the types of content in your library, your typical outputs, and any date or content restrictions. This helps tailor responses for your organization.
Can individual users provide custom instructions?
Not yet, but it's on the roadmap.
Does the Discovery Agent use semantic search?
Yes, combining lexical search (exact word matches), text semantic search (intent-based matches, like "dog" matching "puppy") and visual semantic search (frame-level matches based on what's in the footage), for higher recall and precision than keyword-only search.
Does the Agent use embeddings?
Yes. Embeddings power semantic understanding by mapping words, phrases and visuals into a shared vector space, letting the Agent find related concepts, not just exact terms.
What is "Reasoning" and how does the Agent use it?
Reasoning is how the Agent breaks down complex prompts into multiple steps: interpreting your intent, cross-referencing external knowledge if needed, like event outcomes, then mapping that against your library. The Discovery Agent uses OpenAI's GPT-4.1 to perform these reasoning steps, simulating how a skilled researcher would approach the task.
What is MCP/A2A and does the Agent support it?
MCP (Multi-Context Protocol) lets an agent use external tools and environments. A2A (Agent-to-Agent) lets multiple agents collaborate. The Discovery Agent isn't yet fully MCP/A2A enabled: early demonstrations are underway, but production-ready deployments are still in development.
Can I access the Discovery Agent via Adobe Premiere?
Not currently, but integrations with editing tools are being explored for future releases.
Is the Discovery Agent available via API?
Not today, but API access is on the roadmap.
What's next
Need more help? Reach out to our Support team, we're happy to help.
UI not matching? Your platform may not be updated yet, let us know and we'll help.