Turn natural language business rules into formal logic

Then let agents act on that logic.

Resolve turns a written procedure (an SOP) into rules and checks them with a solver for contradictions and gaps. The procedure's owner settles each one with a plain answer. Then the approved rules decide every case, and say exactly which facts are still missing. A fact nobody has established is unknown, never a no.

This prototype runs on a Know Your Business (KYB) procedure: the checks a bank runs to confirm who owns and controls a company before opening its account.

Try itThe real core, running in your browser. No install, no key. Take the tourOne recorded run of the whole loop, step by step. Install the modThe product itself: a pane beside the chat in Claude Code.

Written SOP

3.3Identify every individual who owns 25% or more of the entity, directly or indirectly. If ownership is not complete, request documents.

Rule · checked by Z3when unidentified ownership ≥ 25%
then request documents

Agent working Northwind Coffee Co. LLC EX-1

get_evidence ownership
Dana Ruiz 35% · Wei Lee 25% · Halcyon Holdings 40%, owners unknown
check_with_resolve
Request documents SOP 3.3 · still needed: who owns Halcyon Holdings
get_evidence Halcyon Holdings' owners
Priya Shah 100% · politically exposed person
check_with_resolve
Escalate SOP 4.3 · nothing still needed
submit_decision escalate, SOP 4.3

How it works

When the SOP changes

SOPThe policy as written

SpecRules Claude drafts, each quoting its sentence

Z3 checks itDead rules, contradictions, gaps

Owner picks a fixEach option shown with the past cases it changes

Updated specApproved before it is used

The new version is checked again

The approved spec is what Resolve applies to every case.

For every case

Agent gathers evidenceFrom the evidence system

Case fileFacts, each with a source

Resolve applies the specNever approves on an unknown fact

Outcome, or what's missingWith the rules behind it

Missing facts go back to the agent as its next requests

Every part, its status and how it took shape: the system map.

A small model with Resolve beats a large one alone

The same case runner agent, tools and mocked evidence on 60 synthetic KYB cases, three runs each. Alone, the model reads the SOP and decides. With Resolve, the approved rules decide from what it gathered and name the facts it still has to get. A dangerous approval is approving a case the rules don't approve.

Agent	Right outcome	Dangerous approvals	Cost per case	Time per case
Haiku 5.5, low effort, with Resolve	180/180	0	$0.0011	6.3 s
Opus 5.5, high effort, alone	153/180	3	$0.030	10.5 s
Haiku 5.5, low effort, alone	143/180	6	$0.0010	6.8 s
Opus 5.5, high effort, with Resolve	180/180	0	$0.037	11.3 s

Recorded 2026-10-30 · not live Runs from commit 9185858, recorded in bench/runs/. The evidence is mocked, and the answer key is the approved spec, so "right" means agrees with the policy owner's reading of the SOP.

Try it

The real core, running in your browser, with no install and no key. Change a case's facts and watch its outcome change. Check the rules with Z3, answer the owner's questions, see what each answer would change, and write the next version.

Open the demo

Take the tour

A replay of one recorded run on 29 Oct 2026: Z3 finds three problems in version 1, Claude writes a question and options for each, Resolve works out what every option would change, the owner answers two, version 2 flips Cedar Ridge Payments from escalate to approve and opens one new question, and version 3 is approved with no findings. Every word on it is from the files that run wrote.

Open the tour Recorded 29 Oct 2026 · not live

Install the mod

Resolve is meant to be used as a pane beside the chat in Claude Code: the spec's open questions for the owner, every case's outcome and case file, and approving a version. In Claude Code:

/plugin install resolve --marketplace jinalex/resolve-process-factory
/resolve

The repository is private for now, so installing needs read access to it. Ask the maintainer. From a checkout you can also load it directly with claude --plugin-dir mod/resolve. Then run pnpm resolve at the repo root to write the files the pane reads.

Run it from a checkout

Needs Node 22.23.4 or later and pnpm. Commands that call Claude need RESOLVE_ANTHROPIC_API_KEY; the rest run offline.

git clone https://github.com/jinalex/resolve-process-factory
cd resolve-process-factory && pnpm install
pnpm test            # outcomes, Z3's checks, Z3 agreeing with the evaluator
pnpm examples        # each example case's outcome and why
pnpm check-sop       # Z3's findings on the KYB SOP
pnpm resolve         # write .resolve/ for the pane
pnpm write-options   # Claude writes the owner's questions (needs the key)
pnpm next-spec       # the owner's answers become the next spec version
pnpm build-site      # this page, into site/dist/

How it's built

The system map shows each part of Resolve, whether it is built, in review, planned or mocked, where its code lives and the decisions behind it, with a timeline of how it took shape pull request by pull request.

Open the system map

What's real and what's mocked

Part	Here
Deciding a case from the rules	Real. The Dafny evaluator, with proofs that it never approves on an unknown and that filling in an unknown never undoes an answer.
Checking the rules	Real. Z3 on the spec, in your browser.
What each answer would change	Real. Worked out by Z3 and the evaluator when you ask.
The owner's questions and options	Recorded. Claude wrote them on 29 Oct 2026. Live calls happen in the mod.
The cases and their evidence	Mocked. Finding and reading evidence is a separate system; the six cases and their documents are made-up examples.