AI-native LP communication platform

Your quarterly letter,
written the way you would write it.

LPRP ingests your portfolio data, learns your voice from prior letters, and drafts an institutional-quality LP update — with full citation provenance and two approval gates before anything reaches a limited partner.

Request Early AccessSee how it works
Scroll to explore
Two GP approval gates before any LP receives a word
Full provenance — every number traced to its source
Built for emerging managers — Fund I to Fund III
SOC 2-ready infrastructure, tenant-isolated data
// The Problem

LP reporting is the worst part of the job.
And no tool has fixed it.

Every GP we talked to said the same thing. The existing software category has spent twenty years building dashboards that LPs don't use and GPs didn't ask for.

01 — Manual Assembly

8–15 hours per letter, every quarter

Finance copies numbers from spreadsheets into Word. One wrong cell reference means an LP receives bad data. Formatting inconsistencies across every letter. No audit trail for any of it.

02 — No GP Voice

Dashboards that strip out all the judgment

Existing tools produce data tables and metric portals — not narratives. LPs receive charts they didn't ask for and miss the context, interpretation, and conviction that actually builds the GP-LP relationship.

03 — Always Late

Average letter arrives 45–90 days post-quarter

Late reporting signals poor fund operations. In a market where LPs are scrutinizing managers more carefully than at any point since 2009, delayed communication damages trust at exactly the wrong moment.

04 — Doesn't Scale

Fund I manager: 20 companies, no ops staff

Emerging managers carry the highest reporting burden and have the fewest resources to absorb it. Every hour spent on LP letters is an hour stolen from sourcing, portfolio work, and the next fundraise.

“Every GP we interviewed said the same thing: LP reporting is the worst part of the job. It's not a process problem — it's a tool gap. The process works fine. It's just done entirely by hand.”

// LPRP user research, Q4 2025, n=24 fund managers
// How It Works

Five stages. Two hard gates.
One letter your LPs will actually read.

The pipeline runs asynchronously in the background. You interact at the decision points — not the plumbing.

1
Data Ingest

Connect your portfolio sources

Upload portfolio updates, connect Airtable or Notion, forward founder emails, or sync your cap table exports. LPRP ingests heterogeneous inputs and builds a unified, provenance-tagged data layer for every company in your portfolio.

Airtable · Notion · Email parsing · Cap table exports · Fund model
2
AI Extraction

Every data point traced to its source

Claude Haiku 3.5 parses each document into structured JSON, tagging every extracted value with its originating source, date, and confidence score. Nothing enters the reporting layer without a provenance chain.

Claude Haiku 3.5 · Schema validation · Confidence scoring · Source attribution
3
Anomaly Detection + Gate 1

The system surfaces what you need to see before the draft runs

Claude Sonnet 4 cross-references your portfolio data against your fund model and prior reporting. Variances above configured thresholds surface as alerts — with the specific numbers that triggered them. You review and clear before generation begins.

HARD STOP — Generation is blocked until you clear Gate 1
4
Letter Generation

A draft that reads like you wrote it

Claude Opus 4 drafts the letter in your voice — calibrated from your prior accepted letters — in three sequential passes: narrative skeleton, full section drafting, then citation verification. Every quantitative claim is inline-cited to a source document. Every number is traceable.

Claude Opus 4 · 3-pass generation · GP voice calibration · Inline citations
5
GP Review + Gate 2

You author it. We draft it.

Review the draft in a tracked-changes editor. Edit inline. Every quantitative claim shows its source on hover. Approve the final version and the platform sends to your LPs — addressed, formatted, and delivered. No one receives anything without your explicit sign-off.

HARD STOP — LP distribution requires explicit GP approval
// Why LPRP

Not a dashboard. Not a portal.
A drafting engine with institutional discipline.

The features that matter are the ones that protect your LP relationships — not the ones that look impressive in a demo.

GP Voice Calibration

After two accepted letters, LPRP extracts a structured style brief from your writing — tone, sentence rhythm, citation format, hedge word frequency. Every draft after that reads like you wrote it, because the model knows how you write.

🔗

Full Provenance Chain

Every number in the letter traces to a source document — with the document name, extraction date, and confidence score. When your LP asks where a number came from, you can answer in 30 seconds, not 30 minutes of digging.

Anomaly Detection Before You See the Draft

The system flags variances between portfolio company reports and your fund model before generation runs — not after. Specific numbers, specific thresholds. You dismiss or confirm each alert at Gate 1. Nothing sneaks through to the letter.

🔒

Two Hard Gates. No Bypass.

Nothing reaches your LPs without you explicitly approving it at Gate 2. The send button is disabled. There is no override. You're legally and reputationally responsible for every word in those letters — this is how the product treats that responsibility.

📊

Completeness Scoring

Before generation runs, you see which portfolio companies are missing required metrics, which have stale data (>90 days), and which cap table entries haven't been verified. Generation is blocked on incomplete data — not silently degraded.

Scales from Fund I to Fund V

Built for emerging managers who have 20 companies and no ops staff. Grows with you to multi-fund platforms managing 60+ portfolio companies across parallel vehicles. One platform, one data layer, one workflow.

// Pricing

Simple, transparent pricing.
No per-letter fees. No per-LP charges.

We deliberately avoided pricing models that create adversarial incentives. You shouldn't pay more for communicating well with more LPs.

Starter
$200/mo
$2,400 billed annually
  • Up to 15 portfolio companies
  • 4 quarterly letters per year
  • 1 fund
  • Email delivery to LPs
  • Standard support
Get Started
Most Popular
Professional
$400/mo
$4,800 billed annually
  • Up to 30 portfolio companies
  • 4 quarterly letters per year
  • Up to 2 funds
  • Priority support
  • GP voice calibration after 2 letters
  • Advanced anomaly detection
Get Started
Growth
$800/mo
$9,600 billed annually
  • Up to 60 portfolio companies
  • Unlimited letters
  • Up to 5 funds
  • LP portal access (Q3 2026)
  • Carta & Pulley integration
  • Priority support + onboarding
Get Started
Enterprise
Custom
Starting at $18,000/yr
  • Unlimited companies & funds
  • White-label deployment
  • API access
  • SLA guarantee
  • Dedicated account management
  • Custom integrations
Contact Us

All plans include: full data provenance · two GP review gates · anomaly detection · LP email delivery · audit trail

// Early Access

Stop writing your LP letters by hand.

We're onboarding a small cohort of emerging managers in Q2 2026. Join the waitlist and we'll reach out with onboarding details within 48 hours.

No credit card required · Onboarding in 48 hours · Cancel anytime