Every number traces to a model
The workflow doesn't generate reports — it builds the Excel model behind them, and the report explains what the model shows. Every figure in the deliverable cites the model cell or source document it came from.
More room in the week for the work your team was hired to do.
Automated workflows for Vancouver real estate operators that handle the assembly behind your team's deliverables, so their time goes to analysis. Built by an engineer who's been building agentic AI systems for real estate analytical work since 2022.
How an installed workflow runs
The workflow handles the assembly; your team's time goes to the judgment.
Your systems
AUTOMATED ASSEMBLY
builds
01
Capture
structured, tagged to source
02 · BUILD
Orchestration
deterministic
AI reasoning
directed
structured · grounded · repeatable
03
Draft
assembles into your template
The model
HUMAN JUDGMENT
Review
experience · interpretation · decisions
Finished deliverable
in your format, ready to send
every figure traces back
Why this practice
Built by an engineer who's done the work
Most AI for this work comes from one of two places: engineers without the domain, or consultancies without the engineering. This practice has both: four years building agentic AI systems, and the finance background to produce the analysis to institutional standard.
Installed over your stack, owned by you
The workflow installs over the systems you already run and operates on your infrastructure. When the engagement ends, you own every system, model, and process built, with an internal AI champion on your team trained to operate and extend it. No ongoing dependency.
Proven on institutional REIT diligence
A diligence workflow for publicly-traded REITs, installed for a senior buy-side reviewer in 2025. Built over six weeks, calibrated to institutional buy-side standard. The workflow produces deep diligence analysis on any target REIT, and runs on subsequent REITs without rebuilding.
Workflows
Monthly close and variance reporting
The monthly cycle — pulling data from the property management system, building variance tables, formatting the monthly deliverable. The workflow handles the production; your team's time stays on the judgment that sits on top.
Typical install: 6-10 weeks.
Portfolio performance review
The recurring analysis on the portfolio — performance against budget, comp benchmarking, surfacing the properties that need attention.
Typical install: 6-10 weeks.
Acquisition diligence
The data and modeling work behind evaluating an acquisition — submarket research, comp pulls, pro forma scenarios.
Typical install: 6-10 weeks.
Capital partner reporting
The recurring package for institutional LPs, co-investors, or capital partners — quarterly performance, capital account statements, fund-level summary. Built against your existing partner-reporting templates, not a vendor's.
Typical install: 6-10 weeks.
Pricing
$5,000
Installation scoping
A written plan for what gets built and how it integrates with your existing systems. Two to three weeks. Credited toward installation if you proceed.
$30,000–$60,000
Single workflow installation
Build and install one of the workflows above. Six to ten weeks. Price depends on scope and systems involved.
What to expect
- First conversation — 30 to 45 minutes.
- Installation scoping — two to three weeks.
- Installation — six to ten weeks.
- Handover — an internal AI champion on your team operates the workflow, you own everything built.
FAQ
How is this different from just using Claude for Small Business or prompting Claude directly?
Off-the-shelf tools handle general productivity — drafting emails, summarizing meetings, research summaries, the everyday work day. Reviewer-ready analytical output is different work. The workflow this practice installs produces consistent output with every figure traceable to the model cell or source it came from, calibrated to your team's conventions and reviewers. Prompting Claude directly produces narrative output that doesn't carry those properties. Many operators use Claude for the productivity work alongside it.
What happens to my data?
Most of the workflow runs locally on your infrastructure — the orchestration, your data, and the model all stay in your environment. Only the steps that need AI reasoning call Anthropic's models, and only with the specific data that step requires. Those calls run under terms that prohibit training on your data or retaining it, in a Canadian region where required.
Will this work with my existing systems?
Yes. The workflow installs over your current stack — Yardi, Buildium, AppFolio, MRI, custom systems, or any combination. Platform AI features (Yardi Virtuoso, etc.) keep working alongside it. No migration or replacement required.
How much of my team's time does installation require?
Roughly 15-25 hours total across the 6-10 weeks. Initial deep-dive on your current workflow, calibration reviews at milestones, and team training at handover. Most of the work happens without your team's involvement.
What happens after the engagement ends?
Your team operates the workflow going forward through an internal AI champion identified and trained during installation. The systems, models, and processes built are yours to extend as your operations evolve. There's no ongoing dependency on this practice.
Background
I built the first version of what runs this practice in 2022, to automate the analytical work real estate operators produce: diligence, performance analysis, partner reporting. That first system took a property address and produced a post-acquisition value analysis.
The early output fell short of the standard the work requires. The four years since have been spent reaching it.
Get in touch
A first conversation, 30 to 45 minutes, to walk through the workflow you're considering and whether the engagement is the right fit.