AI analytics layer
AI Analytics Layer as a Core Ad-Hoc Assistant
A mid-size SaaS company wanted AI on top of its analytics instead of a bigger BI team. Deploying and calibrating data.Ask took three weeks. It involved building the accuracy and trust, reconciling the definitions and logic, and building the further governance plan.
- B2B SaaS
- AI analytics layer
- 2 days to 6 min
Challenge
A ~400-person SaaS business was about to grow its BI team again. The team was constantly fighting ad-hoc requests and firefighting the system. Paying more people to answer "what-is-the-number" & "where-is-this-dashboard" questions was the expensive option. Pointing an assistant at the warehouse was not safe though. The poor governance and documentation along a trapped business logic created AI hallucinations and inconsistencies. The trust wasn't there.
Solution
Deployed d.Ask across four sources: Tableau Cloud for live dashboard metadata and calculated field formulas, Snowflake and Postgres for the numbers and data verification, and GitHub documentation and DDL for definitions and context. HubSpot and Asana were deliberately left out, because a layer is only as credible as its least trustworthy source. Not to mention the complexity and costs of crawling those. Most of the engagement was calibration rather than installation. We reconciled the competing definitions of each core metric and agreed which one was authoritative, corrected the logic, and set processes and monitoring for further improvements.
Results
Questions that used to take about two days came back in about 6 minutes, with their sources attached. Analysts stopped running a lookup service and went back to analysis and tech-debt removal. Three weeks start to finish, and we had a working layer, a documented set of authoritative metric definitions that outlives it, and a clear path for the next AI project.
What the people we worked with say
Consistently brought strategic thinking on architecture, data mesh, governance, and cost optimization, reducing our dashboard delivery from weeks to days.
Proactively solved issues, bridged tech and business communication, and strengthened our internal capability to scale independently. I’d confidently recommend Igor to any pharma leader looking for strategically aligned, sustainable data solutions.
Simon Skurikhin
Data Engineer, Pfizer
Before I worked with Igor, I said dashboard was “the D word.” He often anticipates what I would need.
I review and think “but what about… “ and he’s already thought of it. I focus on giving him the priorities; the questions we need to answer; and for what audience.
And he delivers every time. I feel overall more capable and effective due to Igor’s work.
He’s a joy to work with. I’m very happy to recommend him.
Heather McNamee
Service Manager, Techoir
Igor worked with us at Manual as an independent Tableau contractor. He clearly knows Tableau inside out and built us some great dashboards.
He was pragmatic, understood the balance of £ vs speed, and was willing to adapt his designs and approach appropriately. He was able to work independently and great at managing his own workload - a pleasure to work with.
Mark Madge
Head of Data, Manual
Next step
Recognise this pattern?
It is rarely the report. It is usually what feeds it. That is a fixable problem.
Thirty minutes, straight to the problem. No deck, no pitch, and a written summary afterwards either way.