Discover information you didn't even know you were looking for.
November 09, 2022

Discover information you didn't even know you were looking for.

Sandro Silva | TrustRadius Reviewer
Score 8 out of 10
Vetted Review
Verified User

Overall Satisfaction with IBM Watson Discovery

In the technical area, it took us about six months to train a new analyst in the systems developed by the company so that after this training period, he/she would be able to provide assistance to customers autonomously; even so, the support and monitoring of a full analyst is necessary. As doubts about features, parameterization, and even error correction are frequent, they need to resort to the support of another analyst or even escalate the level of service. As we have a library of documents and manuals on the use of the systems, as well as technical documentation, we were able to create a chatbot with Watson Assistant and integrate it with the Watson Discovery service to include in the answers sent to technicians, the documentation associated with the item it was researching, this ensured that we maintained a standard of knowledge in the company, reduced the need for support from a full or senior analyst in the assistance of the junior analyst, and disseminated all the new features and procedures of our systems in a centralized and accessible way.

Pros

  • Ease of including documents for research.
  • Support for multiple file formats.
  • Multi Language Support for documents.
  • Easy implementation.

Cons

  • Web scrapers is so hard to use.
  • High Cost.
  • Poor UI/UX, it's not easy to novice users.
  • Positive: Facilitating document search using natural language reduces the time needed to find what you are looking for.
  • Positive: Used as a central point of the knowledge base, it is possible to retain the knowledge acquired by employees through feedback in forms or even emails.
  • Positive: Centralized way to disseminate new concepts, manuals, or procedures throughout the company.
  • Negative: High price.
If we consider only the core function, Watson Discovery does not differ much from alternative systems, as they all have a web interface, the possibility of different indexing types and file formats, and an API for automatic integration with third-party systems, and even fewer resources such as Per-user permission control, as there are situations where not all documents can be accessed by all users, or to use on-premise on local servers or in a private cloud. Its differential lies in the improvement in the use of Natural Language (NLU) and in the easy integration with other IBM products, such as Watson Assistant, allowing a chatbot, in addition to pre-programmed responses, to return to the user material contained in documents indexed by Discovery.
Definitely yes. IBM's engine for NLU (Natural Language Understanding) is, if not the best on the market; this in itself reduces the time needed to find what you are looking for, the insights offered by Discovery also help in reducing the search time, as it returns subjects correlated to the searched context.
Discovery differs from its competitors due to the better ease of implementation and the high level of natural language recognition, it is equal in integration resources such as API and workflow or process pipeline, but it loses in the price for a high volume of documents and/or research. If you own or plan to use other services from the IBM Watson family, there is no doubt that Watson discovery is your best option. Another important point is if you plan to use a cloud or on-premise service (local server or private cloud).

Do you think IBM Watson Discovery delivers good value for the price?

Not sure

Are you happy with IBM Watson Discovery's feature set?

Yes

Did IBM Watson Discovery live up to sales and marketing promises?

Yes

Did implementation of IBM Watson Discovery go as expected?

Yes

Would you buy IBM Watson Discovery again?

Yes

Whether using it as a standalone search tool, integrating with other IBM Watson products, or using the API to integrate with proprietary or third-party systems and applications, Watson Discovery addresses these and many other scenarios where document search is required -- understand- if here documents can be pdf, doc, txt files, websites, among other formats --, don't confuse Watson Discovery with EDRMS (Electronic document and records management system) software, Discovery goes further, allowing text search to be done within a context using natural language (NLU) and returning not only the search term but also insights and related issues. File indexing works very well, and training Discovery so that documents and technical terms are learned a bit of work, but it can be reduced by using some of the learning models already trained and available for use.

Comments

More Reviews of IBM Watson Discovery