Have you been able to successfully integrate AI/ML into your enterprise search? What were your greatest challenges or failures in doing so?

Strategy & ArchitectureEnd-User Services & Collaboration
9.3k viewscircle icon3 Upvotescircle icon4 Comments
Sort by:
IT Manager in Construction2 years ago

Lack of governance for data and AI too.
There is an adoption frame everybody follows but before that your team and employees should be ready for the new cultural transformation.

Director of IT2 years ago

Agree with Pradeep on this. Data Quality and Prompt engineering really important to have Gen AI and other search options using Chat GPT.

VP / CIO in Healthcare and Biotech2 years ago

Challenges on data quality, model selection, and the need for ongoing maintenance and user trust. It's essential to address these issues for a successful implementation.

Lightbulb on1
Director of Other in Software2 years ago

I see a lot of interest in this area and we are doing quite a bit there. Great if you want to move beyond the "static" FAQ chatbot and now have a more dynamic and human-like search experience. Challenges sometimes in the type of doc or content inside a doc, i.e. highly technical information/drawings etc. 

Lightbulb on1

Content you might like

What are the biggest technical challenges preventing organizations from being able to use their existing data to enable digital transformation?

Finding data and putting it to good use13%

Controlling the security and privacy of data45%

Understanding how data is currently being used20%

All of the above19%

None of the above1%

View Results

As technology leaders, where are you seeing the most challenges or gaps?

Executive Support10%

Projects vs. Operations68%

Building a culture of Security15%

Team Completeness5%

View Results

Thoughts on self-healing applications? Any approaches or tools that look promising to you?

We use Microsoft PowerBI extensively at the company. Over 15,000 reports.
For our "corporate" reports, like financials or HR, we centralize those requests and attend them with my team.
We currently "extract" information from multiple systems (ie. SAP, SuccessFactors, CRM, etc...) and put in into a SQL Analysis Services. For interpreting the data we have a Semantics model in PBI.
The problem I see is we can't scale enough to comply with the reporting demands as the semantic model is "unique" and we end up having only one or two developers that can work at a time. 
Anyone has an idea how to scale their PBI teams without having to redevelop the semantic model per report?

How do you tell if AI tools are genuinely helping your engineers, instead of just adding extra steps or confusion?

Read More Comments