Share Your Requirements
Launch RASA Chatbot
LANCER
Lancer :
Ideal for quick, focused engagements
Team: ≤ 2 resources
Duration: ≤ 3 weeks
Indicative Budget: ≤ $3,000 USD*
Use Cases: MVPs, prototypes, simple websites, bug-fix sprints
Indicative Pricing: ~$15–$25/hr per resource*
Growth :
Best suited for growing products or structured builds
Team: 2–5 resources
Duration: Up to 4 months
Indicative Budget: Up to $30,000 USD*
Use Cases: Feature-rich web apps, integrations, custom dashboards
Indicative Pricing: ~$15–$35/hr per resource*
Enterprise :
Tailored for high-scale, complex or long-term initiatives
Team: 5+ resources
Duration: More than 4 months
Indicative Budget: Starts from $30,000+ USD*
Use Cases: End-to-end platforms, SaaS products, compliance-heavy systems
Indicative Pricing: ~$25–$50/hr depending on roles*
(Development)
Project Description
A Germany-based SaaS provider specializing in AI-driven automation approached Oodles to deploy a scalable chatbot server using Rasa. With growing demand from enterprise clients, the company needed a solution that could host multiple client-specific bots under a single infrastructure. The engagement focused on multi-bot architecture, cloud deployment, and real-time channel integrations.
Scope Of Work
The client sought Oodles to deploy a Rasa chatbot server from a local environment to the cloud with support for managing multiple bots for different clients. The project involved server provisioning, Rasa framework deployment, bot instance separation, and integration with communication platforms like WhatsApp and Facebook Messenger.
Our Solution
Oodles implemented a production-grade chatbot deployment strategy tailored for multi-client SaaS use.
Key Features Implemented:
- Rasa Chatbot Server Setup: Deployed the chatbot system on a secure cloud server (AWS), moving from local to production.
- Multi-Bot Architecture: Enabled client-wise isolation using individual NLU pipelines and domain configurations for each bot.
- Conversational AI Customization: Configured Rasa Core and Rasa NLU for contextual flow, intent classification, and entity recognition.
- Third-Party Channel Integration: Connected bots to WhatsApp, Telegram, and Facebook Messenger using Rasa Connectors.
- Containerization with Docker: Ensured environment consistency and simplified bot updates and scaling.
