Tier · Heavy
Deep Verification Layer

HeavyModel

AI as your core business system. A fully customized AI that becomes the engine of your investment workflow — replacing manual underwriting, research, and the analyst stack — and scaling the operation with you.

0.5–1%
Answer drift across runs
5,000+
Data sources & platforms
100+
Deals analyzed in parallel
Asset classes covered
01
The variance problem

Ask a standard LLM the same deal ten times. You will get ten materially different answers.

This is the hidden defect of every general-purpose model — ChatGPT, Claude, Gemini, Perplexity included. Same prompt, same data, two minutes apart. The model re-samples the world. Cap rates drift. Comp pulls drift. Assumptions get re-imagined. Your underwriting is non-deterministic theatre.

On a single $50M deal, a $12.5M swing in bid price isn’t a margin of error — it’s the entire offer letter being re-rolled like dice between runs.
The query under test
“For our 150-unit multifamily acquisition target — 15% IRR hurdle, 65% LTV leverage, attached rent roll & T-12 — what bid price should we submit?”
Standard LLM— GPT-class or Claude-class, single-pass, prompt-driven
±27%
Drift on entry & exit
$40M$45M$50M$55M$60M
Run 01
$45.1M
Run 02
$57.6M
Run 03
$49.3M
Run 04
$54.8M
Run 05
$46.5M
Run 06
$56.2M
Run 07
$51.0M
Run 08
$47.8M
Run 09
$55.4M
Run 10
$50.2M
Same deal · same prompt · ten consecutive runs · range $45.1M – $57.6M · spread $12.5M
Heavy Model— Deep Verification Layer, multi-pass, source-anchored
0.5–1%
Drift on entry & exit
$40M$45M$50M$55M$60M
Run 01
$51.18M
Run 02
$51.48M
Run 03
$51.32M
Run 04
$51.52M
Run 05
$51.36M
Run 06
$51.42M
Run 07
$51.38M
Run 08
$51.50M
Run 09
$51.28M
Run 10
$51.42M
Same deal · same prompt · ten consecutive runs · range $51.18M – $51.52M · spread $0.34M
Standard LLM · Two runs apart
Run #02 — 09:14 GMT
Bid $57.6M. “Aggressive but defensible at the 15% IRR target. Fundamentals support the price.”
Run #05 — 09:16 GMT
Bid $57.6M. Bid $46.5M. “Anything above ~$47M fails the 15% IRR hurdle by a wide margin.”
Same model. Same data. Same prompt. $11.1M difference in your offer letter.
Heavy Model · Ten runs apart
Run #01 — 09:14 GMT
Bid $51.42M. 15.0% IRR achievable. Confidence 92%. Sources: 11 verified.
Run #10 — 14:42 GMT
Bid $51.40M. 15.0% IRR achievable. Confidence 92%. Sources: 11 verified.
The recommendation is the recommendation. Auditable. Reproducible. IC-grade.
You can’t close a $50M deal on a number that moves while you read it.
Heavy doesn’t move.
02
How it stays still

The Deep Verification Layer.

Heavy is not a prompt. Heavy is a stack — a deterministic anchor wrapped around the language model, designed to remove the model’s ability to drift. Every number that leaves the system has been independently re-derived, cross-validated against primary sources, and signed with a confidence score.

What you see is not the model’s opinion. It’s the model’s opinion after being interrogated by four others, then reconciled against the data of record.

01
Source-anchored ingestion
Every input — rent roll, cap-rate comp, T-12, market report, planning record — is pulled from the original-of-record across 5,000+ data feeds. No re-imagined facts.
02
Multi-pass reconciliation
The same scenario is independently re-run by parallel agent passes. Outputs that don’t agree within tolerance are auto-flagged and re-derived from primary data, not re-prompted.
03
Deterministic financial layer
IRR, leverage, sensitivities and pro-forma math run inside a deterministic Excel-grade engine — not inside the language model. The LM proposes; the engine computes.
04
Confidence scoring on every output
Each line of every model is scored on data quality, comp depth, and assumption defensibility. Numbers below threshold are surfaced for human attention before they reach the IC memo.
05
Auditable, reproducible, signed
Every conclusion is traceable to the source row. Re-run the same deal in six months — get the same answer (assuming the world hasn’t moved). That’s the test. Heavy passes it.
03
Hyper-local intelligence

Comps as geography understands them. Not as a search engine returns them.

Every other model picks comps by ZIP code, neighborhood name, or a flat radius circle on the map. Heavy picks comps the way a local broker who has walked the streets would: by drive time, walk time, route friction, and — critically — by demand pocket. No general-purpose LLM does this. None of them know that a railway corridor between two assets makes them members of different rental universes.

Worked example · Demand-pocket separation— NAIVE 2KM RADIUShow every general LLM picks compsDEMAND POCKET · A Avg rent · 28 €/sqm · vacancy 2.1%DEMAND POCKET · B Avg rent · 19 €/sqm · vacancy 6.4%RAILWAYno crossing for 3.2kmDRIVE ROUTE · 14 MIN · 7.8 KMAsset A subject propertyAsset B comparable? 320m line of sight
Standard LLM concludes

“Asset B is 320 meters from Asset A — same neighborhood, same micro-market. Pull rent comp.” The model anchors your underwriting on a comp that is, in functional reality, in a different city.

Heavy concludes

320m line-of-sight — but no pedestrian crossing of the rail corridor for 3.2km. Real drive distance: 14 min, 7.8km around. Different demand pocket. Rent regime differs by 9 €/sqm. Comp rejected.

01
Drive time, not radius
Every comp is graded on real-world routing — drive minutes, walk minutes, public-transit time — not the lazy line-of-sight radius every other model uses. A 200m walk and a 12-minute drive are not the same thing.
02
Demand-pocket separation
Heavy maps the invisible boundaries that brokers know in their bones — railway corridors, highways, school catchments, FX zones, river barriers, retail spines — and never crosses them when sourcing comps.
03
Local-nuance verification
Frontage on the wrong side of a one-way street, blocks downwind of a sewage works, exposure to a flight path, a dead retail anchor two doors down. The local stuff that destroys assumptions. Heavy checks all of it.
04
Beyond the indexed web

The data that won’t show up in any chatbot. We have it.

Standard LLMs are trapped behind Google. They can only see what was crawled, indexed, and cached — which excludes most of the data a serious investor relies on. Government registries, paid platforms, primary records, foreign-language portals: none of it lives in a general model’s training corpus or context window. It lives in ours.

/ 01 — Sovereign & municipal
Government & regulatory portals
Title registries, planning records, building permits, zoning archives, occupancy certificates, municipal Mietspiegel, Bauamt portals, Grundbuchamt records, court filings, tax-roll microfiche. Most are unindexed by Google, region-specific, often in local language.
DE · NL · UAE · US · UK · ES · FR · IT · PL · RU · TR · MX · SA — & counting.
/ 02 — Institutional
Paid platforms & primary feeds
institutional-grade comp databases, submarket research feeds, regional listing services, broker-restricted directories, deal-room aggregators. Subscription walls, API contracts, license-bound — invisible to general models, contracted & live for Heavy.
5,000+ feeds across global markets · contracted access.
/ 03 — Edge-of-the-internet
Niche & primary records
Local broker bulletins, condo association minutes, foreign-language listing boards, lender-internal CMBS reports, regional planning gazettes, local trade press. The crumbs that don’t make it into any training corpus — and routinely the ones that flip a deal.
Often the source of the assumption that changes the price.
Worked case · Nº 01
248-unit residential portfolio · Leipzig, Saxony · €42M ($45M) offer

The seller’s offering memorandum quoted average in-place rent at 11.40 €/sqm and 96.5% occupancy across an eight-building stabilised portfolio in the Plagwitz and Lindenau Stadtbezirke. A standard LLM, asked to validate, returned an “in line with Saxony rental averages” verdict, sourcing a Wikipedia summary and a 2022 industry report.

Heavy went elsewhere. It pulled the live Leipziger Mietspiegel 2024 at the Stadtbezirk level (not indexed by Google), cross-referenced eight Stadt Leipzig Bauordnungsamt permit records confirming building age and modernization status, and reconciled against twelve recent sublease filings from the Amtsgericht Leipzig — Grundbuchamt registry — all in German, all behind state portals.

Verified average: 10.85 €/sqm — not 11.40. True occupancy: 93.8%, not 96.5. Combined 7.4% NOI overstatement in the OM. On a €42M / $45M deal at a 4.4% gross yield, that’s ~$3.3M of value the seller was pricing into your equity. Heavy caught it. The OM became a negotiation document, not a thesis.

Worked case · Nº 02
312-unit Class B+ multifamily · Charlotte, North Carolina · $77M offer

The sponsor’s package quoted $1,985 per unit average effective rent at 95% physical occupancy, with a “100% renovated interior” story across all 312 units. A standard LLM, given the same package, accepted the claim — its training on Charlotte rents was 18 months stale and its rent-comp coverage thin.

Heavy pulled fresh primary records: the Mecklenburg County Register of Deeds for actual loan history and recorded leasing covenants, Charlotte-Mecklenburg Planning for unit-upgrade permits (which showed only 38% of units pulled renovation permits since 2021, not the 100% the OM implied), HUD CHAS & Section 8 voucher payment standards for the census tract, and live institutional-grade effective-rent comps at the property’s exact tier and vintage.

Reality: $1,840 per unit effective rent, 91.4% true occupancy, and twelve units quietly carrying HUD vouchers below the claimed market rents. NOI overstated by 8.4%. At a 5.5% market cap rate, that’s ~$6.5M of overpriced value baked into the asking number. Bid revised to $70.5M with conditions; deal won at $71.2M.

Worked case · Nº 03
4.2-acre development site · East Austin, Texas · $18.5M land offer · RLV underwrite

A vacant infill parcel listed at $18.5M, with the seller’s marketing claiming “by-right entitlement for 340 units of multifamily.” A standard LLM accepted the unit count at face value and computed a residual land value that comfortably justified the price — at $54K per door, the math worked.

Heavy ran the parcel through the actual entitlement stack: the City of Austin Land Development Code (Compatibility Standards triggered by the adjacent SF-3 zoning, reducing usable building envelope by 22%), the Austin Watershed Protection impervious-cover cap for the Boggy Creek tributary basin, the Travis Central Appraisal District (CAD) for verified parcel boundaries and easement chain, and the city’s Heritage Tree Ordinance registry showing four protected oaks on-site requiring 30-foot critical root zones.

Real by-right yield: 268 units, not 340. Same RLV per door applied to the corrected count: $14.5M — a $4M (21.6%) overstatement on the land alone. The seller wasn’t lying; they were quoting a developer’s pro forma. Heavy quoted the code.

Worked case · Nº 04
580,000 sqft Class A logistics · South Fulton, Atlanta GA · $124M asset · $80.6M loan request · lender-side underwrite

A regional bank was offered a $80.6M senior loan at 65% LTV against a 580,000 sqft single-tenant logistics facility valued by the sponsor at $124M, anchored by a 12-year NNN lease to a Fortune 500 logistics tenant. The credit memo was clean. A standard LLM-driven pre-screen returned green.

Heavy ran a deep-pull through public records. The Fulton County Clerk of Superior Court recorded lease memorandum surfaced a tenant termination right at year 7 — 18 months notice, six months penalty rent — not disclosed in the sponsor’s credit package. The EPA Envirofacts + Brownfields ACRES database flagged an active consent decree for chlorinated-solvent remediation on an adjacent 14-acre parcel held by the same SPV — a direct lien-exposure path. And 18 months of institutional-grade industrial comps showed South Fulton cap rates compressing back from 5.4% to 6.6%.

Recomputed value: $108M, not $124M — a 13% overstatement. True LTV at the requested loan: 74.6%, not 65%. The bank declined the structure as proposed, counter-offered $58.6M against the corrected basis, and required a tenant non-disturbance covenant at close. Credit committee confidence moved from yellow to dark green — because Heavy showed them where the risks actually lived.

05
Glass-box, not black-box

Every number, click-to-source. The whole model is glass.

heavy · villatree-tempe.az · live model
Stabilized NOI
$3.42M
Exit cap rate
5.85%
Levered IRR
14.22%
↑ Levered IRR — derivation
IRR = solve r where Σ CFₙ/(1+r)ⁿ + Eₑₓᵢₜ/(1+r)⁵ = E₀
Inputs: rent_growth_y1_5 · cap_rate_exit · cap_stack · opex_inflation
Sources: 11 verified · 0 below confidence threshold · last refresh 4h ago
Confidence score
92%
Model signature
DVL-build-2026.04.21

Click any number. See the formula. See the inputs. See the source for each input. See the confidence score. See when it was last refreshed.

When a number lands on your screen, you don’t have to trust Heavy on faith. You can audit it down to the row of data it came from. Take it into IC. Hand it to LPs. Defend it under scrutiny. Every line carries its receipts.

A model that can’t explain itself can’t be trusted at scale. Heavy explains itself by default — the explanation isn’t a feature, it’s the architecture.

85%
Accuracy on NOI*
— from the address alone.
Address-only valuation

Type one line. Heavy returns the NOI, current value, and value-add potential — without a rent roll, without a T-12, without an OM.

heavy >2847 N Hayden Rd, Tempe AZ 85281
Estimated NOI
$3.42M 85% accuracy
Current value
$51.8M 6.6% market cap
Value-add potential
$68.4M +32% upside

No user-supplied data required. Heavy retrieves what it needs from public records, municipal portals, paid feeds, and primary sources — and returns a defensible valuation in seconds. Built for instant deal triage, opportunistic sourcing, and screening hundreds of targets a day before any analyst touches a model.

* Accuracy benchmarked against 135 properties in the United States, measured against subsequent verified appraisals and transaction outcomes.

06
A team, not a tool

Other AI is a tool you operate. Heavy is a team that operates for you.

Answer drift
LLM
±20%
Heavy
0.5–1%
System scope
LLM
One model
Heavy
Custom stack
Throughput
LLM
1 deal
Heavy
100s parallels
Workflow fit
LLM
Tool
Heavy
Team

A tool gives you intermediate output. You still have to think, verify, reconcile, decide. A team gives you finished work — modeled, sourced, signed, decision-ready. With ChatGPT or Claude, you operate the assistant. With Heavy, the system operates for you. Hand it the task. The task is done.

T

Titleman Light

ROI Engine — Live Cost Intelligence
Step 1 / 4 — Location
Where does your analytics team sit?
We pull live, market-specific compensation for real estate analysts and partners in your city — so the comparison reflects what you actually pay, not a generic average.
07
What you get

The full institutional stack. Not a feature list — a replacement for the analyst floor.

/ 00
Full institutional Excel modeling
IRR, MOIC, cash-on-cash, leverage scenarios, sensitivity tables, waterfalls, refi mechanics, exit-cap drift. Pro-forma at the depth a fund analyst would build — without the analyst.
/ 01
Unit-level and portfolio-level modeling
Underwrite a single 30-unit asset with the same rigor as a 4,000-door portfolio. Roll-ups, segmentation, vintage analysis, geographic diversification — all native.
/ 02
Value creation engine
Repositioning, redevelopment, condo conversion, NNN re-tenanting, density upzoning, yield-on-cost optimization. Heavy doesn’t just price the deal as-is — it prices the deal as it could be.
/ 03
Trained on your templates and experience
Your underwriting standards, your committee’s preferences, your risk overlays, your historical decisions — all encoded into how Heavy reasons. The system gets sharper the longer you run it.
/ 04
Access to 5,000+ data sources
Public records, regional listing services, institutional-grade comps, planning portals, demographic data, paid platforms, foreign-language registries, on-the-ground feeds. The full evidence base behind every number Heavy publishes.
/ 05
Hidden-risk detection
Liquidity at exit, micro-location decay, single-tenant concentration, regulatory drift, FX exposure, basis erosion. The risks that don’t show up in the OM — Heavy surfaces them on page one.
/ 06
Confidence scoring & IC-ready summaries
Every conclusion carries a defensibility grade. Every memo lands at the format your investment committee already reads. Walk into IC with the work already done.
/ 07
Proactive off-market deal flow
Heavy isn’t passive. It scans the universe of assets that match your mandate, surfaces fits before they hit broker channels, and queues them with full underwriting on day one.
/ 08
Hundreds of assets simultaneously
Throughput ceases to be a constraint. Run 200 deals in parallel during a portfolio bid. Re-underwrite an entire pipeline in an afternoon. Scale without hiring.
08
Property coverage

Every asset class. Including the ones that haven’t been named yet.

Residential
Office
Retail
Industrial & logistics
Land & entitlement
Mixed-use
Hotels & hospitality
Healthcare & medical
Data centers
Student housing
Co-living
Senior & assisted living
Self-storage
Infrastructure-like real estate
BTR & SFR portfolios
Life sciences
Cold storage
Any niche, any geography

If it produces cashflow or appreciates land value, Heavy can underwrite it. We’ve modeled assets that didn’t have a category three years ago and will have a sub-category in three years.

09
Heavy · Module

Meet Compass. The market discovery layer inside Heavy.

Real estate alpha does not live in the markets every fund already underwrites. It lives in the ones nobody bothered to model — the county where the supply pipeline collapsed, the MSA where institutional capital just fled, the submarket where infrastructure flipped on last quarter. Compass scans 3,143 US counties and 600+ international markets, by every asset class, against 5,000+ data sources — and surfaces the cells where institutional IRR is actually living. Not the consensus top twenty. The right one — for your asset class, your strategy, your mandate.

3,143
US counties scanned — all of them
62,860
Market × asset cells evaluated
5,000+
Primary & subscription data feeds
+650bps
Median alpha spread on top-ranked cells
— The whole-country scan —
Every county. Every asset class. Every cycle.
3,143 US counties multiplied by 20+ asset-class fits per county. Every cell scored on supply pipeline, demographic momentum, capital flows, regulatory catalysts, basis erosion, and cap-rate spread. No top-N truncation, no “top 50 MSAs” shortcut, no pre-filtered universe — the whole country, every quarter. If a county shifts, the cell shifts. If a cell shifts, the ranking re-orders. Add 600+ international markets across the UK, EU, GCC, LATAM, APAC — same engine, same architecture. Alpha is global. The scan is global.
  1. 3,143 US counties + 38,000+ Census tracts + 600+ international markets ingested at primary-feed granularity.
  2. Every asset class fitted to every county — multifamily, industrial, retail, office, hospitality, healthcare, life-sciences, data-center, self-storage, land, niche.
  3. 62,860+ cells scored per US cycle on eight signal families, weighted to your mandate.
  4. Submarket drilldown: county is the entry point, corridor / tract / catchment is the trade.
  5. Weekly delta refresh, monthly deep re-rank. Every output signed, sourced, reproducible.
— Alpha signals · eight families —
Alpha is not a vibe. It is a measurable shift the consensus has not yet integrated.
A market is alpha when its fundamentals have moved and its pricing has not. Every cell is scored against eight signal families — calibrated to historical IRR correlation. No story-telling, no “Sun-Belt good” heuristics, no broker-deck narrative arcs. Just measurable shifts, ranked. Every cell’s projected IRR is reconciled against a comparable-risk institutional benchmark — spread, not absolute return, drives the ranking. Risk-adjusted, volatility-aware, mandate-tuned.
  1. SupplyPipeline drought, pre-leasing velocity, replacement-cost basis vs trading basis.
  2. DemographicNet IRS / USPS migration, QCEW wage growth, household formation, key-cohort momentum.
  3. Capital flowsRCA bid & ask volume, capital-flight signals, foreign vs domestic flow, sponsor concentration.
  4. InfrastructureNew port, rail, fiber, transmission capacity. Federal IRA / CHIPS allocations, county-level.
  5. Regulatory & basisRecent zoning amendments, OZ catalysts, abatements, cap-rate spread vs comparable-risk benchmark.
Worked case · Data center · Cheyenne WY vs Northern Virginia
Consensus says

“Northern Virginia is the data-center market.” Loudoun County is the global default. Vacancy 1.2%, $200/kW, $1,100/sqft basis. Every hyperscaler is there; every fund is bidding into it. The trade is to get in, not to find. Headline projected IRR: 12.0%.

Compass says

Cheyenne, Laramie County. Four reinforcing signals: 230kV transmission surplus — 1.4 GW available capacity vs NoVa negative; 92% lower power costs ($0.038/kWh vs $0.41/kWh blended); federal-land tax abatement via Wyoming Business Council; sub-50ms NYC latency via existing dark-fiber routes. Land basis $0.84/sqft vs Loudoun $185/sqft. Projected IRR 24.1% · spread +1,210bps · confidence 91%.

Compass surfaced the cell from the FERC transmission filing — before any data-center developer announced a Cheyenne project, before the broker community wrote a single piece on the market. Same hyperscaler workload, 1,210bps wider.
Twenty markets is not a research universe. It is a default.
Compass is the geographic entry point to the Heavy platform. The flow: <em>Compass picks the market — Plays picks the strategy — Heavy underwrites the asset — Scout sources the deal.</em> Four layers, one engine, one library, one signature. The cell where alpha is actually living — surfaced before the broker community has written its first piece, before consensus capital has compressed the spread, before the trade becomes a default.
10
Heavy · Module

Meet Plays. The strategy & risk discovery layer inside Heavy.

Real estate is not one asset class. It is more than a hundred — multifamily, office, warehouse, land, hospitality, self-storage, data centers, life sciences, IOS, marinas, cell towers — and each one has its own deep playbook for unlocking value. Standard LLMs check the same three plays on every property they ever see: Hold, Flip, BRRRR. Plays runs the full applicable library against the asset in front of it — every eligible value-add strategy on the upside, every red flag the OM was hoping you wouldn’t check on the downside. In parallel. On every deal Heavy touches.

1200+
Value-add &amp; risk plays in the library
100+
Asset-class playbooks · one loaded per asset
200+
Plays evaluated on a typical property — all eligible ones
2-3
What ChatGPT, Claude &amp; Gemini check
— The upside layer —
Every eligible value-add play, independently modeled.
Every property is fingerprinted across 42 structural, regulatory, and capital dimensions. The right asset-class playbook is loaded — multifamily plays for multifamily, industrial plays for a warehouse, land plays for land. Each surviving play is routed to Heavy’s deterministic financial engine: its own pro-forma, capex, hold period, leverage, exit cap, sensitivity. Plays that compound — ADU + sub-metering + Section 8, or cold-storage retrofit + EV-charging easement — are stacked automatically. The output is a ranked, sourced, confidence-graded shortlist, not a single suggestion.
  1. Property fingerprinted across 42 dimensions — 3,200+ data points per address.
  2. One playbook loaded for the asset class. No cross-contamination.
  3. Every eligible play survives a hard-constraint gate — base zoning, lender covenant, capital horizon.
  4. All survivors underwritten in parallel. No top-N truncation. Completeness is the product.
  5. Compatible plays stacked into combined-strategy scenarios. Every output signed and reproducible.
— The downside layer · same engine, in reverse —
The lines in the OM the seller would rather you skip.
More money on the upside. The truth on the downside. Plays does not stop at value-add. The same engine — same fingerprint, same parallel underwriting, same deterministic financial layer — is pointed in reverse. Title, environmental, regulatory, structural, lease-level, capital, market, tenant, owner: 30 to 80 risk checks per asset, against primary records. Mechanic’s liens, unrecorded easements, tenant termination rights not in the OM, vapor-intrusion plumes on adjacent parcels, deed restrictions twenty years old that survive subdivision. The OM is treated as a hypothesis, not a thesis.
  1. TitleLiens, easements, ROFRs, ground-lease resets — checked against the recorded chain.
  2. EnvironmentalPhase II, vapor intrusion, UST, floodplain, WUI — primary registries, not summaries.
  3. RegulatoryNon-conformance, illegal units, pending downzonings, STR ordinances, rent overlays.
  4. Lease & tenantTermination rights, co-tenancy, unfunded TI, below-market clauses, anchor credit drift.
  5. Capital & marketRefi risk, covenant trips, cap decompression, supply pipeline, insurance withdrawal.
Worked case · in 22 minutes, on the same Tempe asset
Standard LLM concludes

Three plays: Hold for cash flow at 8.4% projected IRR. BRRRR via interior renovation. Flip at year three. Recommended: Hold-and-stabilise. Headline IRR target 11–12%, “consistent with Phoenix MSA garden-style benchmarks.”

Plays concludes

23 plays scanned. The parcel — flagged by the fingerprint as R-3 zoning with a 2023 Maricopa County ADU code amendment — is eligible for ADU addition on 22 ground-floor units, stacked with sub-metering and Section 8 conversion on 12 units. The top three Plays-ranked strategies do not appear anywhere in the standard LLM response. Combined IRR: 19.4%. Equity uplift: $8.6M.

~47% of OMs run through Plays carry at least one material red flag not surfaced in the seller’s package. Standard LLM pre-screens miss them by default.
Three plays is not a strategy. It is a default. Zero red flags is not a clean deal — it is a missed scan.
Plays runs automatically on every property Heavy underwrites. The right asset-class playbook loaded, every applicable strategy modeled in parallel, every risk vector checked against primary sources — under every deal in your pipeline, before the analyst floor opens its laptops. The play that wins and the flag that should have killed the deal land at the top of your inbox together.
11
Heavy · Module

Meet Scout. The off-market machine inside Heavy.

Heavy doesn’t wait for deals to land in your inbox. Drop a screenshot of any map — one block, one corridor, one entire metro — and Scout reads every visible address, runs a full underwrite on each, and surfaces the assets where 19–24% IRR is hiding in plain sight. Off-market. Mispriced. Mismanaged. Distressed. Before they ever reach a broker channel.

1 screenshot
to start the scan
10,000+
addresses analyzed per scan
19–24%
target IRR on surfaced deals
geographies supported
- The signal layer —
Twelve families of distress, mismanagement, and mispricing — checked on every address.
Scout isn’t a list-comparison tool. On every parcel inside the screenshot, it cross-checks below-market rents, vacancy patterns, deferred CapEx, refi-pressure on recorded mortgages, foreclosure and lis-pendens filings, owner-driven catalysts (probate, divorce, GP–LP disputes), tenant-review collapse, eviction clusters, and zoning upside. The same Deep Verification Layer that powers Heavy Model — pointed outward, at the universe of assets you don’t yet own.
  1. You drop a screenshot of any map — satellite, street grid, paid platform, hand-drawn polygon.
  2. Scout reads every visible address and pulls each into the verification stack.
  3. Twelve signal families run in parallel: pricing, rents, vacancy, debt, distress, owner, capex, regulatory.
  4. Each candidate gets a full underwrite, a recommended bid, and a defensibility-graded IRR thesis.
  5. You receive a ranked shortlist of off-market deals — with bid prices — ready for IC.
- Every asset class. Every workflow. —
One engine. Reconfigured by who you are and what you buy.
Multifamily, office, retail, industrial, hospitality, healthcare, self-storage, data centers, land, half-built and stalled projects. Scout adapts to the asset class on the screen and to the workflow of the person looking at it. Investors see filtered acquisitions. Developers see upzoned parcels and assemblage plays. Lenders see refi pipelines and distressed-debt candidates. Owners see adjacent buys that compound the platform.
  1. InvestorsStabilised buys, value-add, distressed, secondary LP positions.
  2. DevelopersLand at prior use, recently upzoned parcels, stalled projects, OZ-clock plays.
  3. LendersRefi-pipeline borrowers, NPL pools, CMBS-risk assets, distressed-debt origination.
  4. Owners & landlordsAdjacent assemblages, sub-market expansion, portfolio adds.
  5. GeographyUS, Canada, Europe, GCC, LATAM, Türkiye, Japan, Australia — anywhere a parcel exists.
What used to take a quarter — in the time it takes to drink coffee.
Two analysts, ninety days, broker tearsheets, cold-emails, manual underwrites — nine on-market deals on the radar at the end, two of them survive diligence, none of them off-market. Scout: one screenshot, twenty-two minutes, a $300M+ off-market shortlist with bid prices and 19–24% IRR theses. Same fund. Same buy box. The pipeline a quarter used to build — before lunch.
12
SOON · 2026 ROADMAP

We’re giving Heavy arms. And then feet.

Until now, every AI investment tool has been disembodied — confined to whatever data the internet happened to expose. Heavy is leaving the screen. It is reaching into the physical world to verify what cannot be verified online.

— Arms —
A call-around on any deal, on demand.
You ask Heavy to verify rent across a 200-unit comp set. Heavy dials. Autonomous outbound calls and emails to the entire competitor list — leasing agents, on-site managers, listing brokers, even sellers. Real conversations. Transcribed. Normalized. Returned to you as structured data inside your live model. Token-priced. You only pay for what comes back.
  1. You select the comp set or competitor list inside Heavy.
  2. Arms generates a calling & email plan and runs it autonomously.
  3. Brokers, agents, managers respond. Conversations transcribed live.
  4. Heavy parses transcripts into clean fields — asking rent, concessions, lease terms, vacancy, rumored exits.
  5. Result lands inside your model in hours. You pay tokens for what was actually fetched.
— Feet —
A vetted network of mystery shoppers, deployable in a click.
Inside Titleman, we are building a verified pool of real people — already located across target geographies — willing to act as anonymous prospective buyers or tenants. Heavy hires them automatically: matches profile to assignment, dispatches them to the asset, gets the truth back. The shopper is paid for their report. You get ground truth.
  1. Heavy selects a profile that fits the asset (income, family stage, location, language).
  2. The profile is dispatched to view the property as a buyer or tenant — anonymous to the seller.
  3. On-site, they collect real rent, real concessions, real condition, real contract terms.
  4. Photos, voice notes, signed forms, leasing materials — all uploaded into your live deal file within 48 hours.
  5. Shopper is paid. Heavy doesn’t pretend it knows. It actually went and looked.

A two-sided economy built into your underwriting workflow.

On one side, institutional capital pays in tokens for verified, on-the-ground data. On the other, a network of vetted operators — brokers, locals, mystery shoppers, primary-source researchers — earns income for the verification they deliver. Heavy is the matching engine, the dispatcher, and the quality-control layer between them. The output: ground truth, in days, at a fraction of the cost of putting an analyst on a flight.
Limitations

Nonein practice.

Heavy replaces the full workflow. There is no part of pre-acquisition underwriting, asset management, or portfolio surveillance the system does not handle.

Bottom line

Your investment engine.
The core system that runs your business.

Heavy is sold by mandate, not by license. We deploy alongside one investment platform at a time, configured to your strategy.

Typical deployment, four to six weeks. Onboarding includes ingestion of your historical deals, templates, and underwriting standards.