> Markdown version of [/videos/249-integrate-your-cognitive-assistant-with-3rd-party-dbs-and-software?t=2164](https://www.wearedevelopers.com/videos/249-integrate-your-cognitive-assistant-with-3rd-party-dbs-and-software?t=2164). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Integrate your Cognitive Assistant with 3rd-party DBs and software

Basic chatbots read scripts; cognitive assistants execute real business workflows. Learn how to securely connect Watson Assistant to Jira, HubSpot, and third-party databases using serverless middleware.

- **Speakers:** Felix Augenstein
- **Event:** WeAreDevelopers LIVE
- **Published:** September 22, 2021
- **Duration:** 48:27
- **URL:** https://www.wearedevelopers.com/videos/249-integrate-your-cognitive-assistant-with-3rd-party-dbs-and-software

## Summary

Building effective conversational artificial intelligence requires moving beyond basic generic scripts to create cognitive assistants that actively interface with existing business infrastructure. Utilizing platforms like IBM Watson Assistant paired with flexible deployment options via Red Hat OpenShift, engineering teams can design highly contextual dialogues capable of gathering active user data and executing complex backend commands. Conversational intelligence relies on clearly mapping customer goals through distinct intents while leveraging entities to capture explicit parameters, allowing the assistant to respond accurately natively rather than returning large generic information blocks. By implementing conversational input slots, the software sequentially gathers all requisite data points from a user before successfully triggering an external process or workflow. The true power of these cognitive assistants lies in their integration capability. Utilizing native webhooks tied to serverless middleware, such as IBM Cloud Functions, developers establish secure REST API bridges connecting the interface to critical third-party databases and enterprise workflow tools. Practical applications of this architecture include automatically inserting IT support tickets into a Cloudant NoSQL database, assigning dynamic software bugs directly into Jira sprint backlogs, and capturing potential lead details immediately inside a HubSpot CRM platform. Connecting these robust logic models to user-facing applications demands minimal frontend effort, typically relying on embedded customizable web chat widgets deployed inside standard Node.js applications. Post-deployment, teams can continually refine system accuracy and data privacy using active chatbot analytics to monitor unhandled queries, track path drop-offs, and precisely identify intent usage securely within public cloud, private cloud, or fully on-premises environments.

**Keywords:** ibm watson assistant, conversational AI integration, chatbot webhook configuration, ibm cloud functions, serverless API integration, REST API chatbot bridging, dialogue node sequencing, intent and entity recognition, conversational context variables, cloudant database connection, agile jira automation, hubspot CRM data capture, red hat openshift deployment, hybrid cloud AI architecture, embedded web chat widget, chatbot usage analytics

## Chapters

1. **Introduction to Watson cognitive assistance and deployment flexibility** (00:03) — An introduction to cognitive assistants and the session outline covering Watson services and practical tutorials.
1. **Deploying Watson services across hybrid cloud environments** (01:45) — How Cloud Pak for Data running on Red Hat OpenShift allows deploying Watson on any infrastructure.
1. **Real-world example of Watson Assistant in space** (02:51) — How the Simon interactive companion assists astronauts on the international space station to save time and reduce costs.
1. **Core capabilities and features of Watson Assistant** (04:39) — Building intelligent conversational interfaces that integrate with multiple channels, searchable databases, and external APIs.
1. **Creating a new Watson Assistant service instance** (08:08) — Navigating the IBM Cloud dashboard to provision a service and select usage plans for development.
1. **Starting a new dialog skill for conversational AI** (11:08) — Navigating the Watson Assistant dashboard to create or import dialog skills for conversational applications.
1. **Identifying user goals with intent classification** (13:08) — Training the assistant to recognize user aims by providing examples of natural language input.
1. **Extracting specific variables via system and custom entities** (15:18) — Using entities to recognize contextual values like product types for customized and human-like interactions.
1. **Structuring conversational flow using dialog nodes** (17:21) — Configuring dialog nodes with specific conditions to handle user requests throughout the conversation path.
1. **Testing and debugging intents in the try it panel** (20:47) — Verifying how custom dialog flows process conversational inputs and assign context variables during interactions.
1. **Integrating the web chat interface into a frontend application** (22:49) — Customizing the web chat user interface and embedding the generated code snippet into a Node.js project.
1. **Connecting Watson Assistant to external databases using webhooks** (26:38) — Triggering webhooks during a dialog to pass collected context variables to external api endpoints.
1. **Creating cloud functions to handle webhook requests** (31:11) — Writing serverless code to process parameters from Watson Assistant and interact with database services.
1. **Integrating an assistant application with Jira software** (32:58) — Configuring Watson Assistant to automatically create issue tickets in Jira using REST API calls.
1. **Automating lead generation with HubSpot CRM integration** (36:04) — Collecting potential customer details through a chat flow and piping the data straight into your CRM tool.
1. **Audience Q&A on architecture and deployment use cases** (40:25) — Addressing questions about typical organizational scales, encryption settings, on-premise deployments, and sub-node complexity.

## Related Moments

- [Powering workflows with connected and agentic AI](https://www.wearedevelopers.com/videos/100259-what-if-your-hr-software-adapted-to-you-not-the-other-way-around) (from "What if your HR software adapted to you, not the other way around?")
- [Summarizing developer experience and artificial intelligence companions](https://www.wearedevelopers.com/videos/884-forget-developer-platforms-think-developer-productivity) (from "Forget Developer Platforms, Think Developer Productivity!")
- [Leveraging the comprehensive generative artificial intelligence stack](https://www.wearedevelopers.com/videos/969-make-it-simple-using-generative-ai-to-accelerate-learning) (from "Make it simple, using generative AI to accelerate learning")
- [Applying context engineering across the full software lifecycle](https://www.wearedevelopers.com/videos/100256-can-this-elephant-dance-ibm-bob-and-the-future-of-ai-first-software-development) (from "Can This Elephant Dance? IBM Bob and the Future of AI-First Software Development")
- [Live demo of AI chat interactions with ClickHouse](https://www.wearedevelopers.com/videos/100240-analytics-in-the-age-of-agentic-ai-a-tour-of-clickhouse-and-langfuse) (from "Analytics in the Age of Agentic AI: A tour of ClickHouse and Langfuse")
- [Building a personal assistant interface using web speech](https://www.wearedevelopers.com/videos/1142-is-the-web-ready-for-voice-user-interfaces) (from "Is the web ready for voice user interfaces?")

## Related Articles

- [WWC24 Talk - Scott Hanselman - AI: Superhero or Supervillain?](https://www.wearedevelopers.com/magazine/469-wwc24-talk-scott-hanselman-ai-superhero-or-supervillain)
- [Exploring AI: Opportunities and Risks for Developers](https://www.wearedevelopers.com/magazine/522-exploring-ai-opportunities-and-risks-for-developers)
- [Dev Digest 132 - Binging WADFlix?](https://www.wearedevelopers.com/magazine/473-dev-digest-132-binging-wadflix)
- [Stephan Gillich - Bringing AI Everywhere](https://www.wearedevelopers.com/magazine/489-stephan-gillich-bringing-ai-everywhere)

## Related Jobs

- [Principal Field Architect - AI Agents](https://www.wearedevelopers.com/jobs/ext/1442858-principal-field-architect-ai-agents) at **Twilio**
- [Twilio's next Senior Principal Field Architect - AI Agents](https://www.wearedevelopers.com/jobs/ext/1487390-twilio-s-next-senior-principal-field-architect-ai-agents) at **Twilio**
- [AI Full Stack Engineer](https://www.wearedevelopers.com/jobs/ext/1354435-ai-full-stack-engineer) at **Almedia**
- [Senior Engineer, Infrastructure Platform](https://www.wearedevelopers.com/jobs/ext/328836-senior-engineer-infrastructure-platform) at **Intercom, Inc.**
- [salesforce artificial intelligence architecture leadership documentation](https://www.wearedevelopers.com/jobs/ext/2000219-salesforce-artificial-intelligence-architecture-leadership-documentation) at **Twilio**
- [AI Software Engineer (Germany)](https://www.wearedevelopers.com/jobs/48317-ai-software-engineer-germany) at **Sunhat**