Example brief
The target GenAI platform is designed for a European insurer with a reference architecture that includes experience channels such as adviser cockpit and mobile self-service, agent orchestration with components like agent router and policy guardrails, model services with Azure OpenAI and domain adapters, knowledge and data with customer 360 and feature store, and integration with API gateway and core policy, all built on a cloud foundation with a landing zone and network segmentation, to achieve scale through a governed platform layer, not rebuilding AI inside every channel, with key components including workflow engine, tool registry, and human approval.
Render it
Brief path
curl -X POST https://api.slideforge.dev/v1/render/auto \
-H "Authorization: Bearer sf_live_..." \
-H "Content-Type: application/json" \
-d '{ "brief": "The target GenAI platform is designed for a European insurer with a reference architecture that includes experience chan" }'Structured intent (this template)
{
"pattern": "layer_stack",
"title": "The target GenAI platform: governed services, not AI rebuilt in every channel",
"subtitle": "Reference architecture for a European insurer",
"variant": "platform_layer_stack",
"layers": [
{
"label": "Experience channels",
"icon": "monitor",
"role": "Where users engage",
"components": [
{
"label": "Adviser cockpit"
},
{
"label": "Claims assistant"
},
{
"label": "Service console"
},
{
"label": "Mobile self-service"
}
]
},
{
"label": "Agent orchestration",
"icon": "workflow",
"role": "The control point",
"emphasis": "primary",
"components": [
{
"label": "Agent router"
},
{
"label": "Workflow engine"
},
{
"label": "Tool registry"
},
{
"label": "Policy guardrails"
},
{
"label": "Human approval"
}
]
},
{
"label": "Model services",
"icon": "cpu",
"role": "Models + evaluation",
"components": [
{
"label": "Azure OpenAI"
},
{
"label": "Domain adapters"
},
{
"label": "Eval harness"
},
{
"label": "Prompt registry"
}
]
},
{
"label": "Knowledge & data",
"icon": "database",
"role": "Grounding data products",
"components": [
{
"label": "Customer 360"
},
{
"label": "Vector index"
},
{
"label": "Feature store"
},
{
"label": "Doc intelligence"
}
]
},
{
"label": "Integration",
"icon": "plug",
"role": "Systems of record",
"components": [
{
"label": "API gateway"
},
{
"label": "Event bus"
},
{
"label": "Core policy"
},
{
"label": "CRM"
},
{
"label": "Claims platform"
}
]
}
],
"foundation": {
"label": "Cloud foundation",
"components": [
{
"label": "Landing zone"
},
{
"label": "Network segmentation"
},
{
"label": "Secrets"
},
{
"label": "Observability"
},
{
"label": "FinOps"
}
]
},
"takeaway": "Scale comes from a governed platform layer, not rebuilding AI inside every channel."
}Related templates
Bars vs target marker
Margin recovery is visible but three units are below target
Diverging variance bars
Cloud hosting and contractor spend offset hiring delay savings
Grouped comparison bars
Pipeline coverage is ahead of last year but below target in two regions
Ranked magnitude bars
Three offer families drive 68% of FY25 growth
Frequently asked questions
How do I render the Platform layer stack template?
Send a POST to /v1/render/auto with a brief, or call create_slide via MCP with the structured intent shown below. The response includes an editable .pptx, a PDF, and a PNG. $0.05 per slide.
Does an AI write the slide?
No. SlideForge renders deterministically from a structured intent — no LLM draws the slide, so text is never mangled or fabricated. The optional brief path uses a router to pick the pattern, then renders deterministically.
Can I customize the colors and fonts?
Yes. Pass a theme_id to apply a built-in or custom brand theme; the layout stays the same.
Try this template
Render Platform layer stack deterministically — editable PowerPoint in under a second.