Brand-Aligned Presentations
Turns a topic into a production-ready, BRAND-ALIGNED slide deck (presentation / pitch / .pptx / slides) for sales, marketing & consulting. Blends deep web research with the CALLER'S OWN brand identity (pass brand fields, or a brand.source_url to extract identity from) plus optional internal_context. ROUTE HERE whenever the user wants a slide deck or presentation built from a topic — especially when it must follow corporate brand guidelines, or combines research + a deck deliverable. HUMAN-IN-THE-LOOP: returns status:needs_input / stage:review (a research brief + slide outline) for approval BEFORE building slides; on approval, re-call with approved:true and pass the research_anchor back VERBATIM so Phase-1 research carries across the handoff (session continuity). Input: {topic, audience?, objective?, slide_count?, depth?, brand{...}, internal_context?, clarifications?, approved?, revisions?, research_anchor?}. Output: deck spec (slides with title, bullets, speaker_notes, image_prompt + sources). Rendering to .pptx and internal Vertex AI Search are pluggable (render_status 'spec_only' today). Gemini 3.5 Flash + google_search.
Example input
{"topic":"The 2026 state of AI agents in B2B customer support, and why mid-market SaaS should adopt now","audience":"VP of Customer Experience at a 200-500 person B2B SaaS company","objective":"Book a pilot of our AI support copilot","slide_count":12,"depth":"standard","brand":{"company_name":"Octupie","source_url":"https://www.octupie.com","tagline":"AI copilots for support teams","primary_color":"#ff5722","tone":"confident, plain-spoken, data-driven"},"internal_context":"Octupie pilots cut first-response time 36hr->9hr at PhoneClinic India; deflection 41% in 8 weeks."}Example output
{"status":"needs_input","stage":"review","deliverable_type":"presentation_brief","ask":{"question":"Here's the research brief and a proposed 12-slide outline. Approve to build the deck, or tell me what to change.","why":"Approving locks the research and outline before I generate slides.","suggestions":["Approve and build the deck","Revise the outline","Adjust the brand styling"]},"brand":{"company_name":"Octupie","primary_color":"#ff5722","secondary_color":"#1a1a2e","tone":"confident, plain-spoken, data-driven","_inferred":["secondary_color"]},"research_brief":{"summary":"AI support agents moved from deflection bots to copilots in 2025-2026; mid-market SaaS sees the fastest ROI as ticket volume outpaces headcount. Deployments report 30-45% deflection and 50-70% faster first-response within a quarter; blockers are data readiness and trust.","key_findings":["30-45% deflection in the first 8-12 weeks is the typical mid-market range.","Copilots commonly cut first-response time 50-70%.","Data readiness predicts pilot success more than model choice."],"sources":[{"url":"https://www.zendesk.com/cx-trends-2026","title":"Zendesk CX Trends 2026","relevance":"Deflection + FRT benchmarks"},{"url":"https://www.gartner.com/en/customer-service-support","title":"Gartner CS&S outlook","relevance":"Mid-market adoption curve"}]},"outline":[{"title":"From bots to copilots: support in 2026","bullets":["Why now","What changed"]},{"title":"The mid-market squeeze","bullets":["Ticket volume vs headcount","SLA pressure"]},{"title":"What good looks like: the numbers","bullets":["30-45% deflection","50-70% faster FRT"]},{"title":"Octupie pilot results","bullets":["36hr->9hr FRT","41% deflection in 8 weeks"]},{"title":"Pilot in 6 weeks: the plan","bullets":["Weeks 1-2 data","Weeks 3-6 live"]},{"title":"Book your pilot","bullets":["Next step","Contact"]}]}