A98 is the machine that builds them: it reads your data estate, learns how your firm actually works, and assembles agents specialized to your workflows: covenant checks, waterfalls, cap tables, full diligence, your quarterly reporting. Numbers computed by code, every figure traced to its page, decisions made by you.
Live demos of the real process: the ask, the steps, the numbers computed by code, what gets flagged instead of guessed, and the report it fills at the end. Click a type to switch.
Six engines today: private lending, private equity, venture capital, family office, real estate, hedge funds. The set is open, and no engine limits your metrics: if your firm uses it, your instance computes it.
A98 is not a tool you configure from a blank menu. It is a machine that builds your fund's own product: your definitions, your templates, your teams, your instance.
Your data room, your agreements, your closed quarters. It deduces your fund type, vehicles, sectors, and how your teams divide the work, and shows the evidence behind every deduction.
Before go-live, the system re-derives quarters you already closed: the covenant check, the fund IRR, a distribution waterfall. It ships only when its numbers match the ones you already trust.
Agents and pipelines built around your workflow, organized by your teams, writing to your own warehouse of results. Another fund gets a different machine, because it is a different fund.
Two building blocks, in plain terms, and what they do to your team's week.
An agent reads the exact documents for one task, computes with deterministic code, and returns the answer with its sources. It can be recurring (the quarterly covenant check) or a one-off you'll never run again ("what's our exposure to this supplier that just went under?"). Same machine either way, and a new agent is assembled from your firm's pieces in minutes, not a dev project. You can also point one at a single detail you care about, and it watches that detail every cycle.
A pipeline chains agents and runs itself, monthly or quarterly, without anyone asking. Every run is versioned into your firm's warehouse, and the last step doesn't produce a chat answer: it fills the reports you already use. The credit memo, the LP letter, the board pack, your template, your numbers, pre-populated with every figure traced.
The whole flow, in one chart: what we read, what gets built, what lands on your desk, and how it gets sharper every month. Your first months are free while this happens; you pay when it is already working.
The repetitive grind (spreading, covenant checks, report assembly) runs itself. We calibrate your instance to take 60 to 80% of those recurring hours; your team reviews flagged exceptions instead of rebuilding spreadsheets.
Every number is recomputed, never copied: a changed EBITDA definition, a missing certificate, a stale mark gets caught and flagged. And you can point an agent at one specific detail you worry about; it watches it every cycle.
Calibrated against your closed quarters before go-live, and every correction is remembered for your firm. Non-recurring questions become agents in minutes, on the same machine, with the same sourced output.
Your definitions, your covenant language, your report formats, your teams. The machine assembles your instance from your data and confirms it with you before it ships.
Private lending, private equity, venture, family office, real estate, hedge funds, and no engine limits your metrics. A new fund type is a new engine, not a new product.
Sign in with your own subscription. We never hold keys, we never mark up tokens, and nothing is sent to a model your compliance team didn't approve.
Every ratio is computed by deterministic code and clicks through to its source clause. It is the trail your auditors, and your LPs, wish every manager had.
We won't pretend the agents are perfect. Here's the real promise: they read, cross-reference, and compute across your whole book in minutes, show you where every number came from, compute with exact code, and flag clearly what they couldn't confirm. Your team decides, with the evidence in front of them.
Built for the way a fund's IT, compliance, and LP due diligence teams actually evaluate a vendor.
Agents read your data. They can't change, move, or delete anything.
Our cloud, your own cloud, or fully on your machine. Your documents can stay inside your perimeter.
Sign in with your own AI subscription. We never hold keys, and nothing goes to a model you didn't authorize.
Your data and documents are never used to train any model, ours or anyone else's.
Encrypted in transit and at rest, isolated per firm, with scoped access you can revoke at any time.
A full trail of what each agent did, and every figure traces back to its source page.
Penetration testing and SOC 2 are on the near-term roadmap, before scale. Before any data touches the system, we sign an NDA and walk your security and IT teams through the architecture.
A98 is built by a credit and data professional who underwrites and monitors lower-middle-market deals every day, and writes the code behind it. The founding beta is deliberately small: five funds whose workflows shape what the machine becomes.
For GPs, fund managers, and the LPs who push them. Tell us what kind of fund you run; we'll show you what your instance would look like, on your own numbers.