Last verified 2026-07-12

Side-letter obligation extraction

Can AI extract side-letter obligations into a register? Yes — this is a genuine AI-shaped job, turning prose promises into a structured register and lining up equivalent clauses for a most-favoured-nation comparison. No for the election itself: whether two differently-worded clauses are "the same term" is a legal call with money attached.

The pain	A fund closes with dozens of side letters, each granting a different investor different rights — fee terms, reporting frequencies, most-favoured-nation elections, notification triggers, co-invest rights. Those promises then have to be honoured for the life of the fund, but they live as prose in separate signed PDFs. Someone has to read every letter, extract every obligation into a register with deadlines, and re-run the most-favoured-nation comparison each time a new letter is signed to check whether an earlier investor now qualifies for the better term.
What AI does today	Extract the obligations from each letter into a structured register — clause, investor, obligation type, trigger, deadline — and support the most-favoured-nation comparison by lining up equivalent clauses across letters for a human to decide who elects what. The extracted register can then feed a deadline calendar. The boundary: AI reads prose into structure; the interpretation of what a clause means, and the election, are legal work.
Proof it's real	Vendor-claimed. Specialist tooling built for exactly the most-favoured-nation election workflow is marketed as in production across managers by Ontra, whose contract-automation business is established in private markets. The claim and the client numbers are the vendor's own; law firms' internal use of legal AI on side letters is widely reported but rarely named per matter. Newest evidence: 2025.
What it can't do	It cannot make the legal call — that is where the human sits: fund counsel decides whether two differently-worded clauses are "the same term" for election purposes, because that judgment carries money. It also cannot be trusted on a clause it half-read — a missed carve-out or a misread threshold becomes a compliance breach that surfaces years later.
The real alternatives	The law firm's obligation matrix — the classic route: fund counsel abstracts every side letter into a compliance matrix at close. Accurate and defensible; expensive at hourly rates, and static — it decays as new letters are signed unless someone pays to refresh it. An obligation-management platform (Ontra-class, tech plus lawyer review) — wins on ongoing elections and living registers across funds. An in-house extraction on approved tools — where the group runs an internal LLM gateway, legal-ops teams increasingly do their own extraction into the compliance register; wins when confidentiality rules keep the letters inside the firewall. A paralegal and an Excel register — the in-house baseline; fine for a small letter count, fragile at scale. AI's edge over all of these is cost and freshness of the extraction — the legal review on top is common to every route.
What you need in place	The executed side-letter set and the LPA (context changes meaning); a legal-review gate before any extracted obligation is relied on; and an owner — in practice compliance or the fund counsel's office owns the register, IR consumes it. Confidentiality matters: side letters are commercially sensitive, so where the documents go for processing needs the same care as the data room. In a group that usually means the internal gateway or the approved-vendor list — the confidentiality rule often decides the tool before any comparison does.
Effort & cost	Weekend script — an LLM reading one side letter into an obligations table; free, and the right way to calibrate trust on letters you can eyeball. Off-the-shelf — obligation platforms, typically subscription plus per-document; five figures a year at manager scale. Real project — extraction feeding an obligation register and deadline feed with legal review; five figures plus counsel time. Under a couple of dozen letters, the paralegal-plus-Excel register (or the matrix your lawyers already built at close) is the honest answer.
What to watch	Verify against the source letter, not the summary — the failure mode is a clean-looking register that silently dropped a clause or a carve-out. Spot-check the obligations that carry a deadline or a payment, because those are the ones that bite.

Questions operators ask

Can AI run our MFN election?

It can line up equivalent clauses across letters so counsel decides faster — that alignment is the tedious part. The election itself (which terms are "the same", who qualifies) stays a legal judgment; treat any tool that claims to decide it as mispriced risk.

Is software better than the law firm's side-letter matrix?

Different jobs: the firm's matrix is a defensible snapshot at close; a platform (or your own extraction) keeps a living register as letters accumulate. Many managers use both — the matrix as the verified baseline, extraction to keep it current between closes.

Changelog

2026-07-12 — published.