/ Parts and operations · PUBLISHED CASE
TirupatiAir Intelligence
Parts cross-referencing made faster and less error-prone
An industrial compressor service company reported faster part identification and fewer dispatch errors after centralising operating knowledge.
/ THE SHORT VERSION
An industrial compressor service company reported faster part identification and fewer dispatch errors after centralising operating knowledge.
01 / BUSINESS CONTEXT
The work before the tool.
TirupatiAir manages industrial compressor service, parts and dispatch work. Identifying compatible parts required searching manuals and OEM information across fragmented sources.
02 / THE INTERVENTION
What changed in the workflow.
The business used Gemini and a custom workflow to search, compare and organise part information, while extending AI support into broader operational management.
The case describes active use for cross-referencing and management support. Broader system integration is still an expansion opportunity.
03 / REPORTED OUTCOMES
The numbers, with their labels attached.
| Workflow area | Before | After |
|---|---|---|
| Part identification | Manual search across manuals and OEM references | A structured AI-assisted cross-reference shortens the search |
| Dispatch risk | Incorrect matching could create direct losses | The team reviews a clearer compatibility result before dispatch |
| Knowledge access | Answers depended on experienced individuals | Operational information becomes easier for the team to retrieve |
Capability matters when people stay in control.
The team remained responsible for confirming compatibility and approving dispatches. The system reduced search effort without removing the final operational check.
05 / WHAT A SIMILAR BUSINESS SHOULD TEST
Transfer the pattern, not the conclusion.
- 01
Start with a constrained reference set and known part relationships.
- 02
Keep dispatch approval with a person who understands compatibility risk.
- 03
Measure avoided errors as well as faster retrieval.
06 / SOURCE AND LIMITS
What this page can and cannot establish.
This analysis summarises outcomes published in MCCIA’s AI: Compilation of case studies (2026), printed pages 30–31. The work was conducted through the MCCIA Applied AI Studio. The report credits the Studio team managed by Neeraj Thakur, with Gauri Kale and Ismail Patel. The featured organisation is not presented as a dotSuper client.
- 01The publication does not provide the number of searches, error rate or financial value of avoided dispatch mistakes.
- 02Compatibility answers require current source material and a clearly defined escalation path.
Does this pattern look familiar?
Bring the comparable workflow in your business. We will test the fit, name the missing evidence and identify one practical next move.
Explore this use case