Example brief
The automation project improved exception handling by reducing resolution time from 4.8 days to 2.9 days, a 40% decrease, and also decreased supervisor clarification needs from 38% to 21%, and audit prep time from 6 hours to 90 minutes, a 75% reduction, overall enhancing the workflow's efficiency and scalability.
Render it
Structured intent — create_slide payload
Copy-paste-ready. Renders deterministically (verbatim, no LLM). Add a theme_id for any of the built-in themes — the layout stays identical.
{
"form": "editorial_split",
"variant": "quantified_delta",
"headline": "Automation cut exception handling time while improving auditability",
"context": "Baseline vs post-implementation",
"takeaway": "The first wave proves the workflow scales; next target claims and returns.",
"data": {
"deltas": [
{
"metric": "Resolution time",
"before_value": "4.8d",
"after_value": "2.9d",
"delta_value": "-40%",
"direction": "down",
"tone": "good"
},
{
"metric": "Supervisor clarification",
"before_value": "38%",
"after_value": "21%",
"delta_value": "-17pp",
"direction": "down",
"tone": "good"
},
{
"metric": "Audit prep / sample",
"before_value": "6 hrs",
"after_value": "90 min",
"delta_value": "-75%",
"direction": "down",
"tone": "good"
}
],
"panels": [
{
"label": "Baseline",
"sub": "Mostly manual exception handling",
"detail": [
"Manual triage",
"Evidence assembled by hand",
"Ad-hoc customer updates"
],
"tone": "warn"
},
{
"label": "Post-implementation",
"sub": "AI-assisted triage in the workflow",
"detail": [
"Suggested next actions inline",
"Evidence attached automatically",
"Milestone updates to customers"
],
"emphasis": "primary",
"tone": "good"
}
]
}
}cURL (REST)
curl -X POST https://dev-api.slideforge.dev/v1/render/intent \
-H "Authorization: Bearer sf_live_..." \
-H "Content-Type: application/json" \
-d '{"form":"editorial_split","variant":"quantified_delta","headline":"Automation cut exception handling time while improving auditability","context":"Baseline vs post-implementation","takeaway":"The first wave proves the workflow scales; next target claims and returns.","data":{"deltas":[{"metric":"Resolution time","before_value":"4.8d","after_value":"2.9d","delta_value":"-40%","direction":"down","tone":"good"},{"metric":"Supervisor clarification","before_value":"38%","after_value":"21%","delta_value":"-17pp","direction":"down","tone":"good"},{"metric":"Audit prep / sample","before_value":"6 hrs","after_value":"90 min","delta_value":"-75%","direction":"down","tone":"good"}],"panels":[{"label":"Baseline","sub":"Mostly manual exception handling","detail":["Manual triage","Evidence assembled by hand","Ad-hoc customer updates"],"tone":"warn"},{"label":"Post-implementation","sub":"AI-assisted triage in the workflow","detail":["Suggested next actions inline","Evidence attached automatically","Milestone updates to customers"],"emphasis":"primary","tone":"good"}]}}'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
Ranked magnitude bars
Three offer families drive 68% of FY25 growth
Pricing packages
Three packages for sales teams
Frequently asked questions
How do I render the Impact before / after 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 Impact before / after deterministically — editable PowerPoint in under a second.