GupShup
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 digital media company, Gupshup focused on conversational AI wanted to automate user interactions through a flexible chatbot. With increasing complexity in user flows and entity handling, they needed a powerful, customizable NLP engine. The project involved building an advanced Rasa-based chatbot solution to handle multilingual input, custom workflows, and automated testing modules.
Scope Of Work
The client needed a scalable Rasa chatbot with the help of Oodles that is capable of managing complex conversations, reusable story flows, and entity recognition. The project involved automated testing setups, dialog customization, and integration with MySQL and Elasticsearch. Areas of work included NLU training, entity handling, Rasa Forms, story design, and custom action development.
Our Solution
To fulfill the client’s goals, a structured and reliable chatbot framework was implemented using the Rasa Platform with customized NLP workflows.
Key Features and Implementation Highlights:
- Custom NLP Pipeline: Integrated Spacy, Regex, Lookup, Synonym-based entity recognition for deep language understanding.
- Automated Test Framework: Enabled consistent validation using NLU-only tests and test stories.
- Dialog Control: Managed complex story flows, slots, conditions, checkpoints, and fallback actions.
- Modular Actions: Developed Python-based custom actions for dynamic responses and backend logic.
- Form Handling: Built multi-turn interactions using Rasa Forms for guided data collection.
Share Your Requirements