Marketing ops · Production

Accenture Spotlight scales video highlight generation with Amazon Nova and Amazon Bedrock Agents

The problem

Traditional video highlight creation workflows are slow and labor-intensive, requiring editors to manually review footage, identify significant moments, cut clips, add transitions, and perform quality checks—creating bottlenecks that do not scale efficiently.

Workflow diagram · grounded in source
1
User submits natural language request
trigger
“users access a frontend UI where they provide natural language input to specify their objective”
2
Orchestrator agent coordinates task
ai_action
“The orchestrator agent manages task breakdown, data flow, and inter-agent communication”
3
Video processing agent generates metadata
ai_action
“The video processing agent powered by Amazon Nova Pro analyzes video and generates fine-grained metadata (for example, identifying patterns from viral videos)”
4
Short video generation agent constructs highlight
ai_action
“The short video generation agent powered by Amazon Nova Pro constructs a video highlight using segment recommendations”
5
Reviewer agent validates quality
validation
“The reviewer agent powered by Amazon Nova Premier makes sure the constructed highlight aligns with quality, brand, and contextual expectations”
6
Video postprocessing and output
output
“AWS Elemental Media Convert and open source tooling enable video highlight construction and postprocessing (such as subtitle layover, aspect ratio change, and transitions)”
Reported outcome

Spotlight reduces video highlight generation from hours or days to minutes, and Amazon Nova-powered agents deliver over 10 times better cost savings compared to traditional highlight creation methods.

Reported metrics
Video highlight generation timein minutes, reducing from hours or days
Cost savings vs traditional methodsover 10 times better cost savings
Highlight review cost reduction10 times lower with Amazon Nova
Overall highlight generation cost reduction10 times lower using serverless and on-demand LLM deployment
Reported stack
Amazon NovaAmazon Bedrock AgentsAmazon Nova ProAmazon Nova PremierAWS Step Functions
Source
https://aws.amazon.com/blogs/machine-learning/accenture-scales-video-analysis-with-amazon-nova-and-amazon-bedrock-agents?tag=soumet-20
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Spotlight reduces video highlight generation from hours or days to minutes, and Amazon Nova-powered agents deliver over 10 times better cost savings compared to traditional highlight creation methods.

What tools did this team use?

Amazon Nova, Amazon Bedrock Agents, Amazon Nova Pro, Amazon Nova Premier, AWS Step Functions.

What results were reported?

Video highlight generation time: in minutes, reducing from hours or days; Cost savings vs traditional methods: over 10 times better cost savings; Highlight review cost reduction: 10 times lower with Amazon Nova; Overall highlight generation cost reduction: 10 times lower using serverless and on-demand LLM deployment (source-reported, not independently verified).

How is this marketing ops AI workflow structured?

User submits natural language request → Orchestrator agent coordinates task → Video processing agent generates metadata → Short video generation agent constructs highlight → Reviewer agent validates quality → Video postprocessing and output.

Related marketing ops cases