Google Cloud Software / SaaS Argentina

WeSpeak

Application Refactoring · IT Operations Automation · Real-time Analytics

Building that product required infrastructure that would never go down. Early on, WeSpeak ran on a virtual private server that could fail without warning, taking the entire platform offline. For a hotel waiting on a guest's booking decision, every minute the platform was down was a direct revenue loss. WeSpeak needed infrastructure that matched the stakes of the business it was serving.

Read the original story Explore all use cases

70% of hotel guest inquiries automated end to end

Direct booking conversion rates raised up to 167%

Support tickets cut by 70% after switching to agentic Gemini

Reported impact

Business outcome

70% of hotel guest inquiries automated end to end; Zero downtime since migrating from VPS to Cloud Run; Support tickets cut by 70% after switching to agentic Gemini; Direct booking conversion rates raised up to 167%.

Solution

Moving to Google Cloud solved the infrastructure problem. eliminated the fixed server entirely, deploying serverless containers that scale automatically to handle guest inquiries across WhatsApp, Instagram, Facebook, and TikTok. To power these omnichannel conversations, WeSpeak leverages Gemini Pro and Gemini Flash using Gemini platform and Google AI Studio. WeSpeak ran more than a thousand automated tests on every model considered, measuring hallucination rates across real hotel scenarios. Gemini platform routes each conversation to the right model: Gemini Pro for the most complex hotels and Gemini Flash for the majority of properties where speed is the priority. Google AI Studio runs in the background as a fallback, ensuring that if Gemini platform ever has an issue, the guest still receives a response built with the same Gemini models.

Data flow

processed with Gemini Pro, orchestrated via Gemini platform, and surfaced through Gemini Flash, Gemini, Cloud Run

Solution architecture

5 components · 3 layers

Compute
- Gemini Pro Performs higher-depth reasoning and content generation for the workflow.
Serving
- Gemini Flash Handles high-volume generative AI tasks with lower latency and lower serving cost.
- Gemini Powers natural-language reasoning, summarization, generation, or assistance inside the workflow.
- Cloud Run Runs application services and proprietary code in a managed container environment.
Orchestration
- Gemini platform Coordinates the solution's agentic and generative AI workflows on Google Cloud.

Architecture clues

"Gemini was the only model that consistently passed those tests," says Albiero. "We tried the alternatives. None of them gave us what we needed at a price that made our business viable."
# WeSpeak delivers 24/7 hotel sales automation across Latin America with Gemini
Gemini is the engine that moves WeSpeak. Every conversation we respond to, we respond with Gemini. We tested all the competitors and literally Google has what works best for us in terms of quality and price.
Support tickets cut by 70% after switching to agentic Gemini
WeSpeak built an AI hotel receptionist on Gemini to handle guest inquiries, from first message to payment, across Latin America.
Zero downtime since migrating from VPS to Cloud Run

Evidence from the source

70% of hotel guest inquiries automated end to end

Direct booking conversion rates raised up to 167%

Support tickets cut by 70% after switching to agentic Gemini

WeSpeak built an AI hotel receptionist on Gemini to handle guest inquiries, from first message to payment, across Latin America.

Zero downtime since migrating from VPS to Cloud Run

Transparency Evidence & methodology 95/100 reference value · 82% confidence · 2 sources

Review how this reference was scored and trace each normalized claim back to its documented source.

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value95/100

Problem clarity20/20
Measures whether the customer's operational problem is specific enough to compare.
Implementation depth20/25
Rewards named components, data flow, integrations, and architecture detail.
Outcome specificity20/20
Measures whether the reported benefit is concrete rather than a generic claim.
Quantified impact25/25
3 metrics describe measurable impact.
Deployment scale10/10
Rewards evidence of a live or scaled deployment and meaningful integration scope.

Evidence confidence82%

Source authority20/25
The main evidence is an official vendor-published customer story.
Claim traceability23/25
11 of 12 key fields link to a named source.
Direct evidence20/20
5 direct source quotes retained.
Date provenance0/10
The publication date has no documented provenance.
Source transparency9/10
2 source references document publisher, URL, authority, retrieval, and supported fields.
Implementation specificity10/10
Rewards source-backed components, data flow, quantified impact, and a specific outcome.

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

Google Cloud
WeSpeak customer story

First-party
https://cloud.google.com/customers/wespeak

Source type
Vendor-published customer story
Supports
- Customer
- Business problem
- Solution
- Products
- Solution components
- Data flow
- Integrations
- technical area
- use case category
- Business outcome
- outcome category
- Metrics
- Architecture
- evidence quotes
WeSpeak
Who We Are | The Team Behind the AI Assistant for Hotels | WeSpeak

First-party
https://www.wespeak.pro/en/about/
The page's JSON-LD lists addressLocality Buenos Aires and addressCountry AR.

Source type
Official company website
Supports
- Region

Date evidence

First archived Aug 29, 2026 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
Open date source
Sitemap last modified Oct 9, 2026 · Google Cloud · Publisher metadata Publisher-reported modification timestamp; not a publication date.
Open date source

Not separately sourced Industry, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Similar use cases

See all like this

Google Cloud Archived · Mar 4, 2026 ChatAndBuild Software / SaaS Singapore Enabling 140,000+ users to turn natural language into working apps with sub-second latency. But this vision was hindered by the company’s previous infrastructure. Builders faced 30–70% higher latency, disrupting the… Accelerates feature delivery 2x with unified DevOps tools including Cloud Build Application RefactoringIT Operations Automation BigQuery · Cloud Build · Cloud CDN

Google Cloud Archived · Aug 29, 2026 PayPal Financial Services United States After unifying its core data estate, PayPal needed an AI platform that could power global commerce use cases, let developers choose the best model for each workload, and elastically handle training and inference without… 25,000 pipelines every day Application RefactoringIT Operations Automation BigQuery · Cloud GPUs · Gemini Enterprise Agent Platform

Google Cloud Archived · Jun 6, 2026 Foodpairing Consumer Goods Belgium In the food and beverage industry, launching new products successfully is a challenge. More than 80% of product launches fail, due in large part to the sector’s traditional reliance on slow, expensive consumer testing. Achieves more than 75% correlation with real consumer panels Application RefactoringIT Operations Automation BigQuery · Cloud Run · Cloud SQL