Case study · PropTech · AI Engineering← All work

An AI assistant that gives property managers back one to two hours a day

Matera's property managers searched 6M+ documents by hand to answer their clients. I built the assistant that finds the answer in five minutes instead of thirty, used every day by ~100 people.

Fig. 1Matera · time to find an answer

By hand30 min

With the assistant5 min

Fig. 2Matera · questions asked per month since launch
×60
saved across property managers, 1-2h each
100h/day
to get an answer, instead of searching by hand
30 → 5 min
people use it every day
~100
usage growth in nine months
×60

“I highly recommend Bryce, who completed a one-year engagement at Matera, for both his technical skills and his human qualities.

He independently led an AI project from A to Z, now used daily by about a hundred people. This project turned out to be crucial for the company's future and convinced us to invest more in it.

He also delivered several side projects and introduced us to new technologies and best practices through his knowledge.”

Hugo Lime

Hugo Lime

VP Data & AI at Matera

The problem

Matera started as property-management software and now runs property management itself. Its property managers answer their clients’ questions all day, and every answer sits somewhere in 6M+ documents.

Finding it by hand took about thirty minutes a question. That time, more than anything else, capped how many clients each manager could take on.

What I built

I was the lead GenAI engineer and owned the whole chain behind the assistant: roadmap & strategy, alignment with stakeholders, cloud infrastructure, ingestion, search, evaluation and production.

An ingestion pipeline sized to the budget. Fully processing the whole corpus would have cost about six times more. Instead, a lighter pipeline makes every document reachable, and the assistant searches them agentically: it finds and reads what each question needs. That costs a sixth as much, without losing accuracy.

Knowledge search with an assistant on top. Managers ask in plain language; the assistant searches the documents and emails and answers with what it found.

Agents connected to the application’s data, through MCP. With the tech team, I gave the agents access to the application’s own data, read-only for a start, so an answer can combine a document with the live record it refers to. I built part of the MCP tools myself, search among them, and integrated the MCP server the tech team runs in the Rails app for wider data access.

Evaluations of the agents’ tool calls. I evaluated how the agents call the application’s data with a 200-question Langfuse test dataset, plus manual analysis of their traces in Langfuse.

AI spend under control. I routinely ran FinOps on the Vertex AI projects I owned and cut their spend by half.

Owned by the team. Matera’s product runs on Ruby on Rails; the GenAI layer is Python, beside it. I worked with the managers on what they needed and with the engineering team on how it fit, and the product’s Rails developers contributed to the Python codebase.

Results

  • Managers find an answer in 5 minutes instead of 30, and save 1 to 2 hours a day each: about 100 hours a day across the team.
  • Each property manager can now take on more clients, so Matera can scale its managed property service. Its VP Data & AI calls the project “crucial for the company’s future”.
  • ~100 people use it every day, and usage grew 60-fold in nine months.

More work.

E-commerce · ML & Data

ManoMano: E⁠-⁠commerce optimization

Worked on the Google Shopping bidding algorithm and built the keyword-campaign system, alongside a delivery-time model, for a European e-commerce unicorn.

Fig. 3ManoMano · Shopping bidding model, randomized A/B test

Controlbaseline

New model · +$30M/yr+7%

+$40M/yradditional business volume from the bidding & marketing ML

Fintech · Data Platform

Alma: Data platform

Led the build of Alma's data platform from scratch. From cloud infra to business dashboards.

Fig. 4Alma · what the platform connects

Sources

What it feeds

  • Postgres
  • HubSpot
  • Zendesk
  • Stripe
  • Adyen
  • Google Sheets
BigQuery · dbt
  • Dashboards
  • Fraud model
  • HubSpot
  • Zendesk
  • Customer.io

Postgres via CDC: freshness 24 h → 5 min

$50M/yrfraud savings enabled by the platform

Have a similar problem?

Bring the workflow and what's blocking it. In 20 minutes, you'll know whether AI can solve it, what to build first, and whether I'm the right person for it.

20 minutes · you leave with a clear next step

Book a free call