# How a SaaS team shipped three internal AI tools in two weeks

A VP of Engineering at a SaaS company had engineers spending 10+ hours a week on internal tooling instead of product. We took three of those projects off his plate: an AI research assistant, automated data enrichment and a support ticket router. All three were live within 2 weeks, with code his team owns.

By the WorkflowPal team. Published 2026-10-05.

## At a glance

- **Client:** A B2B SaaS company, working with the VP of Engineering (anonymized)
- **Problem:** Engineers spent 10+ hours a week on internal tooling instead of product
- **What we built:** An AI research assistant, automated data enrichment and a support ticket router
- **Results:** All three live within 2 weeks
- **Time to live:** Within 2 weeks

> The client is anonymized. The figures are the real before-and-after numbers from the project, reported as-is and not rounded up.

## What was the problem?

Engineers were spending 10+ hours a week on internal tooling instead of product. The projects weren’t big enough to justify pulling a dedicated engineer off the roadmap, but they were too valuable to keep ignoring.

## What did we build?

- **AI research assistant:** gathers and summarizes information so people start from a brief.
- **Automated data enrichment:** fills and checks records without manual lookups.
- **Support ticket router:** classifies incoming tickets and sends them to the right queue with context.

All three were built in the company’s own repository and accounts and handed over with documentation.

## What changed?

Before and after:

| Measure | Before | After |
| --- | --- | --- |
| Engineering time on internal tooling | 10+ hours a week | Off the team’s plate |
| Internal tools live | Stuck in the backlog | three, within 2 weeks |

- **3 tools, 2 weeks**: research assistant, data enrichment and ticket router, all live (SaaS) ([case study](https://workflowpal.com/case-studies/saas-three-internal-tools-two-weeks/))

## What should you know before building something similar?

- Batch small internal projects together. One scoping pass across all of them is faster than three separate ones.
- Agree the hand-over standard (tests, docs, owner) at the start, so tools land in a state your team will accept.
- Start the ticket router in suggest-only mode, then let it route on its own once its choices match your team’s.

## Could this work for you?

If your team does similar work by hand, probably. [Request a free workflow audit](https://workflowpal.com/free-workflow-audit/) and you get a one-page plan: the 3 tasks worth automating first, hours saved, and what a build would cost. See also [AI automation for SaaS](https://workflowpal.com/industries/saas/) and [Custom AI agents](https://workflowpal.com/services/ai-agents/).

## Related

- [AI automation for SaaS](https://workflowpal.com/industries/saas/)
- [Custom AI agents](https://workflowpal.com/services/ai-agents/)
- [All case studies](https://workflowpal.com/case-studies/)

---

Last updated: 2026-10-05

Next step: request a free workflow audit at https://workflowpal.com/free-workflow-audit/ or book a call at https://calendly.com/dan-workflowpal/30min.

Canonical HTML: https://workflowpal.com/case-studies/saas-three-internal-tools-two-weeks/

WorkflowPal · PO Box 704, Brandon, SD 57005