Beyond the Obvious: Revisiting AI Enterprise Search for Consultants

Many conversations I have with consulting leaders about their knowledge management practice have a common theme: AI-powered search tools—when they work—surface the obvious but don’t help discover new insights about their institutions.

What’s Missing?

If firms want to leverage their institutional knowledge, they demand more than a simple search over PDFs. They’ve realized they need to understand the fuller context around the final reports, which isn’t spelled out in any one place in their data environment.

Imagine you’re assembling a team for an M&A due diligence RFP, and a new consultant needs to get up to speed quickly on who at the firm would be great to speak with. They search internally for someone with expertise on deals of this structure and size, and your hypothetical system responds with the four partners at the firm who lead your financial practice.

The response wasn’t wrong because they are indeed top-down identified leaders of that practice. But the question is…

Did you need AI to tell you that?

If you had Googled the same search query on the public internet about your firm, you’d get the same answer. Where is the alpha in having access to your institutional knowledge on the inside?

That hypothetical result failed to tell you who within your firm has been growing their expertise in this area.

• Who has worked on multiple M&A due diligence projects over the past year and developed a strong understanding of key risks?
• Who has been actively involved in structuring post-merger integration strategies in recent engagements?

Traditional knowledge retrieval systems won’t surface them because their contributions are hidden in the file contribution logs across fragmented systems. Their expertise isn't declared in a canonical source of truth. This is where learning from your metadata comes in.

Your knowledge is in your data—and about your data

It’s natural to expect that all of a firm’s knowledge is what is documented in the CRMs, PSAs, and file stores. These only tell half the story—what’s missing is the context and processes that shaped the outcomes captured in those systems.

For an AI Enterprise Search platform to give you insights only you could know, it needs to:

• Map knowledge beyond final reports — deconstructing final reports into their parts and attributing each insight to its source.
• Analyze contributions, not just authorship —reconstructing decision-making hierarchies from the bottom-up.

As such, we need a comprehensive approach to reconstructing a firm's true knowledge graph by integrating everything, from CRM entries (tracking client engagements) to resourcing schedulers (who worked on what) and their respective metadata (how decisions were shaped). Of course, we also need a semantic understanding of the insights (what exactly is inside the documents?).

After seeing firms struggle with these gaps firsthand, we adapted Kenley to meet practices where they are today. By starting with a robust data integration layer to connect with source systems and help build a rich knowledge foundation, we begin to enable all the downstream value creation we’ve been promised with AI. But more on this soon.

Till next time,

Bolu

Request a demo to learn how leading consulting firms are winning today with Gen AI powered by their institutional knowledge.