roger3000 · demo — the intelligence layer between your data and your CRM · meridian advisory (fictional)

The intelligence layer between your data and your CRM.

roger3000 reads what you already own — CRM, documents, database — runs investor intelligence over it, and writes the enriched result back where you work. And it tells you when it's guessing: every claim is audited against a source before you see it. Six moments from the machine.

verified unverifiable fabricated every claim it makes wears one of these — on the record
scroll ↓
meridian advisory · onboarding structuring your corpus
yours
your CRM your documents your database
market
fund announcements deal & exit news team moves
meridian brain
your entities
1,900 relationships — firm ↔ partner ↔ deal
your criteria, queryable — not buried in docs
market layer
fund closes & deals — refreshed weekly
joined to your entities, not headlines
the joined view
who just raised, that fits a live mandate of yours
warm paths: your relationships × their new deals
01 · read

It starts with what you already own.

Your CRM, your documents, your database — read in place, not an integration project. The engine reads them into one typed graph: firms, funds, partners, deals, and how they connect.

External market signal — fund closes, deals, team moves — arrives already joined to your entities. Not a feed of headlines to triage; a fact attached to a firm you know, scored against a mandate you wrote.

reads your data in place · external sources are additive — this is your data structured, not a scrape of it · generated demo data · client fictional
meridian advisory · match pitch → investors
Voltfield — pitch.pdf grid analytics · Series A
routed →  intelligence agent
matching the deck against every firm it knows
1
Hartline Capital
generalist growth, moved hard into industrial software — closed Fund III (€180m) in march
3 deals · 12 mo · led 2 · cheque €4–12m
92
2
Norrfjord Capital
industrial software is the stated core of Fund IV
2 deals · led 1 · slower pace this year
84
3
Aster Bridge Partners
infra-software thesis, edges earlier than your mandate
4 follow-ons · co-led · seed–A
71
a deep report generated for each match
02 · intelligence

Drop in a pitch deck. Get the investors that fit.

Every deck becomes a saved artefact — its own workspace, kept per pitch. The engine reads it, matches it against the firms it knows, and returns a ranked report: the investors that fit, each with the signal that put them there.

Not a list of names — a report you can stand behind, because every claim in it is checked before you see it.

one artefact per pitch, persisted · ranked on fit, with evidence · firms fictional · generated demo data
meridian advisory · report audit claim auditor
match report — voltfield × hartline capital excerpt · 4 of 23 claims
2 verified 1 unverifiable — flagged 1 fabricated — withheld
the auditor itself is measured
0.0%
fabricated
false-positive rate
100%
recall on planted
fabrications
57
labeled fixtures
in the set
measured on a fixed labeled set — a baseline, not a green-light.
03 · trust

Before a report reaches you, it audits every claim in it.

Every sentence the engine writes is checked against the sources it holds. Verified claims carry their evidence. Unverifiable ones are kept — and flagged as such, so you know exactly where the ground is. Fabricated ones never reach you.

And the auditor itself is measured. On a fixed labeled set it currently calls nothing grounded that isn't — 0.0% fabricated false-positives — and catches every planted fabrication. Most AI asks for your trust; this one shows you its score.

the 0.0% · 100% · 57 are the only real numbers on this page — measured on a fixed labeled set; a baseline, not a green-light · claims shown illustrative
meridian advisory · ask brain — grounded
source · fund-filing.pdf source · deal-log
pushes back
One correction: Hartline led your last two rounds — the deal log shows it co-invested, never led. Want the firms that actually led?
04 · brain

Ask anything — it answers only from your sources.

Ask in plain language. The brain answers from your own documents, and every claim cites the source it came from. If the documents don't hold the answer, it says so and abstains — it never fills the gap with a guess.

So when your premise isn't in the sources, it won't play along — it shows you what the documents actually say. The same grounding standard the claim auditor holds your reports to in 03.

answers cite their source · abstains rather than guess · one grounding standard, shared with the 03 claim auditor · generated demo data · client fictional
meridian advisory · sync layer ⇄ Folk
enriched match
Voltfield × Hartline · fit 92
warm path · 2 tracked signals
audited · grounded
your CRM · Folk · Hartline Capital
stagequalified
owneryou
sectorgrid analytics
from Folk · into the layer
stage → meeting booked
+ new contact on the deal
dry-run preview dedupe-safe you approve the sync
05 · write-back

It syncs both ways with your CRM.

The engine writes the enriched result — the fit, the warm path, the tracked signals — straight back into your CRM record, so the tool your team already lives in starts surfacing deals it couldn't see. And it reads their moves back: a stage change, a new contact — the layer stays in step.

Every write is previewed, dedupe-safe, and yours to approve — it never touches your pipeline on its own.

two-way sync with your CRM · dry-run first · nothing writes without you · generated demo data · client fictional · roadmap
meridian advisory · outcomes labeled outcomes · 214
the loop one outcome
pipeline — voltfield · in your CRM (Folk)
intro 14 may partner meeting 2 jun term sheet 26 jun
outcome passed meeting won
✓ filed — outcome: won · series A · industrial software · label #215
match write-back outcome label
outcome in your CRM → label in the layer → sharper match
Next time a Voltfield-shaped company walks in, Hartline-shaped firms rank higher — because of your outcome, not anyone's scrape.
06 · flywheel

Every outcome makes the next match sharper.

The outcome happens in your CRM — a pass, a meeting, a term sheet. The layer reads it back and turns it into a labeled example: this startup, this firm, this result.

The matcher trains on those labels. That's the part no generic model can copy — it isn't in anyone's training data. It lives in the layer, on your outcomes, and it compounds.

outcomes live in your CRM · the layer turns them into labels that retrain the ranking · generated demo data
roger3000 · investor-intelligence demo · everything on this page is generated demo data — the client (meridian advisory), the startup (voltfield), and all firms, people, deals and figures are fictional · one exception: the three calibration figures in 03 (0.0% · 100% · 57) are real measurements from our labeled set.