Live
Our generative product-photo and video studio · Gemini on Google Cloud
- Generative AI
- Gemini
- Google Cloud
Media and entertainment · Content and media
Booking concierge and promo content engine
A concierge for showtime, seat and food questions that sends booking links, plus a Gemini pipeline for posters, thumbnails and short promos per title and city.
- ClaudeAnthropic
- GeminiGoogle
- Typical timeline: 4–10 weeks
The problem
Cinemas and venues field the same showtime, seat, food and offer questions all day, while marketing needs posters, thumbnails and short promos for every title and city.
- Showtime and offer questions swamp phones and social inboxes.
- Every release needs fresh creative in several formats and languages.
- Food and beverage upsells are missed online.
How we solve it
A concierge on web and WhatsApp that reads showtimes, sends booking links and suggests combos, alongside a content engine that turns approved trailers and stills into localised posters, thumbnails and short cut-downs.
It plugs into Ticketing / POS system, WhatsApp Business, Website (WordPress or Wix), Google Drive and Ad accounts, so nothing you rely on today is replaced. The architecture below shows each step and which model does the work.
Architecture
From your stack, through the AI layer, to numbers you can track
Each step names the model or system doing the work. Writes to your systems wait for a person to approve them.
Your stack
- Ticketing / POS system
- WhatsApp Business
- Website (WordPress or Wix)
- Google Drive
- Ad accounts
AI layer
Softpiper AI layer
- Claude
- Gemini
- Guests ask, using Claude Haiku / Sonnet
Guests ask on web or WhatsApp; showtimes and availability come from your ticketing system.
- Book and upsell, using Ticketing API · booking links
The concierge sends booking links and suggests food and beverage combos.
- Creative inputs, using Google Drive
Approved trailers, stills and key art are pulled from Drive, with rights noted.
- Generate assets, using Nano Banana · Veo · Lyria
Thumbnails, posters with localised text, short promos and music beds.
- Copy and brand QA, using Claude Sonnet
Captions and descriptions are written per city and language, and every asset is checked against brand rules.
- Approve and publish, using Approval queue
Your team approves assets before they reach the site and ad accounts.
Outcomes you measure
- Booking conversion from chat
- Food and beverage attach rate
- Query deflection
- Asset turnaround time per title
Why this model
Claude and Gemini, each where it leads
We choose per task on capability, cost and where your data must stay. Final versions are picked at kickoff.
ClaudeAnthropic
Claude runs the concierge with tools on your ticketing data, writes captions and localised descriptions, and checks every asset against your brand rules.
GeminiGoogle
Gemini handles the media: video-to-image generation for thumbnails and posters, Nano Banana image models for localised poster text, Veo and Gemini Omni Flash for short promo cut-downs, and Lyria for background music.
Delivery
What you get, how long it takes, and how we keep it safe
Guardrails
- Only footage and stills you hold rights to are used as inputs.
- Studio and brand approvals before anything is published.
- AI-generated content is disclosed where required.
- Showtimes and prices come from the ticketing system, never the model.
Plus the guardrails on every build: facts from your systems, approvals for writes and money, a human one step away, audit logs and evals. See all
Deliverables
- Concierge on web and WhatsApp
- Ticketing integration and booking links
- Content pipeline for posters, thumbnails and promos
- Brand QA rules
- Asset approval queue
Typical timeline
- Concierge4–6 weeks
- Content pipeline2–4 weeks
A planning range for a first production release. We confirm scope, price and dates in a tailored proposal.
KPIs to track
- Booking conversion from chat
- Food and beverage attach rate
- Query deflection
- Asset turnaround time per title
- Creative variants per campaign
Goals we agree with you and measure from a baseline. They are what we track, not results we promise.
Related services
The services behind this playbook
AI agents
Agents that answer, act and hand off, on Claude and Gemini, inside the tools you already run.
View serviceAI product engineering
From prototype to production: RAG, copilots, multimodal features and the evals that keep them honest.
View serviceWix Studio
Premium business sites your own team can edit, delivered on Wix Studio, with Velo when you need custom code.
View service
Our work in this space
Related work
Products we've built that show the approach. They are our own products, not deployments of this playbook.
More playbooks
Related playbooks
Retail and e-commerce
Catalogue and content factory
Thousands of SKUs with thin descriptions, missing attributes, no translations and inconsistent imagery hold back search visibility and conversion.
- Claude
- Gemini
- Typical timeline
- 2–4 weeks
- Plugs into
- Shopify · WordPress / WooCommerce · Google Drive +1 more
Retail and e-commerce
AI shopping concierge for web and WhatsApp
Shoppers leave when they can't get a fast answer on sizing, stock, delivery or returns, and your team answers the same questions across chat, email and WhatsApp.
- Claude
- Gemini
- Typical timeline
- 3–10 weeks
- Plugs into
- Shopify · WhatsApp Business · HubSpot or Zoho CRM +1 more
Real estate
Lead qualification and property-matching concierge
Portals and ads bring high lead volumes, follow-up is slow, and agents spend their time on enquiries that were never going to buy.
- Claude
- Gemini
- Typical timeline
- 4–10 weeks
- Plugs into
- HubSpot or Zoho CRM · Salesforce · Listings database +2 more
Pip · Softpiper's AI
Ask Pip about this playbook
Ask Pip how this would work for you
Pip is Softpiper's AI. Tell it what you run today and it will walk through how this playbook fits, what we would build first and a tailored price range. Or book a call with the team.