Management record
Stable identity for people, companies, agents, suppliers, and contracts; documents with their sources and history; decisions, obligations, reports; retention, governed deletion, and legal holds.
Development evidence · 30 August 2026
Built is not the same as available.
This page records what the current build of Lagstyr demonstrably does, what still needs proving in a real installation, and the gates — in order — between here and a first customer. Every claim is dated, and nothing on this page is a promise about timing.
How to read our labels
Four labels, used the same way everywhere.
We use status language narrowly, so a technical achievement never becomes an availability claim by implication. Every status label on this site means exactly one of these four things.
Built & lab-tested
Works end to end on controlled test data
The capability exists in the product code, is covered by automated tests, and has been run through complete journeys — but on synthetic data we control, not a customer's.
Built, not yet proven live
Exists in code; the proof needs a real installation
The capability is built, but its most important evidence — running in a real deployment, against real outside systems, on a real buyer's documents — has not happened yet.
Planned
Designed, not built
The intent and often the specification exist. The code, or the proof, does not.
Not available
Nothing to install, trial, or buy today
No installation, hosted environment, trial, pilot, demo, or production support is currently offered — full stop.
Latest evidence milestone · 29 August 2026
Contract documents reach governed work through visible, bounded stages.
This is our own lab evidence, run by us on synthetic data. It shows the capability works and refuses correctly. It is not a customer's documents, a live connection to a customer's systems, or an independent assessment.
Input
A realistic, reproducible test set
102 synthetic documents we generated and hold all rights to — 727 PDF pages across 13 document types. We hold 26 documents back from tuning, and we record the correct answer for every page, field, and search in advance, so results are scored against a fixed answer key rather than judged after the fact.
Observed
Document reading stays inside hard limits
100 of the 102 documents index through the production path. All 118 scanned, image-only pages are read by text-recognition software inside the installation — nothing is sent to an outside service. The two remaining documents (one over the page limit, one an unsupported file type) are rejected outright rather than half-processed.
Observed
Extracted contract terms keep their receipts
23 indexed supplier contracts each yield the expected renewal date, notice period, obligations, and automatic-renewal risk — and every extracted value points at the exact passage of the source document it came from.
Observed
Extraction never becomes company record by itself
The AI can propose; only a person can make it official. When a reviewer accepts a proposal, everything in it is recorded in one step or not at all. Documents that are unsigned, unreliable, contradictory, or ownerless are refused whole — nothing is half-recorded.
Observed
The operator can see the whole journey
The console joins the evidence, the human decision, the scheduled work, the outward action, and the measurement — without inventing progress. Where a number has no evidence yet, it is shown as not configured, never rounded up into success.
Built, not yet proven live
What this milestone does not prove
A real buyer's documents and their review, a live round trip into a supplier's actual system, a provisioned installation, and observed production operation. Those proofs belong to the gates below.
Evidence log
Dated entries, newest first.
Each entry records something that was proven, with its date. Expect new entries roughly monthly while development continues — if this log goes quiet, read the silence as information.
29 Aug 2026
Contract-to-governed-work milestone
The evidence above: bounded document reading, extraction with exact sources, human-only promotion to record, and inspectable journeys, on the frozen 102-document test set.
27 Aug 2026
Mutation-testing sweep completed
Faults were deliberately injected across the authority chain and the governed surfaces that reach it — the code where a missed fault matters most — to test whether the test suite notices. Every surviving mutant was individually examined and recorded in a written ledger — including one wrong entry, kept struck-through rather than deleted.
18 Aug 2026
Clean-room launch proof
The full installation launch journey was run end to end in an isolated environment, by us, from documented steps and a reproducibly built install kit. The exercise also caught a broken release-publishing pipeline — that finding is in the record, which is the point of the exercise.
The foundation
The foundation is substantial — and heavily checked.
These capability groups exist in the product code today. Behind them sit more than 4,500 automated tests, deliberate fault-injection (mutation) testing with a written disposition ledger, properties proved over the entire risk-routing space (every tier enumerated, not sampled), and a release gate with named human approvers — one that has already refused a release, which is the control working.
Authority kernel
The core service every action must pass through: who may act, in what scope, within which limits; the T0–T3 autonomy ladder; approvals, conflict checks, separation of duties, emergency stop and restore.
Operator surface
Queues that bring work needing judgement to the right person, decision cards that carry the evidence with the proposal, registers, exceptions, and management reporting.
Agent work loop
Agent runs, tasks, proposals, and approvals — with every change to prompts, skills, and models going through the same explicit approval as any other material change.
Effect verification
Actions on outside systems are precisely defined, safe to retry, and checked after the fact: the owning system is read back to confirm what actually changed, and differences are reconciled rather than assumed away.
Measurement and learning
Costs, benefits, and outcomes measured against the decision that authorised the work — with exact definitions beside every number, so wider autonomy is an evidence-based decision.
Built, not yet proven live
What still needs a real installation to prove.
These exist in code or in supported specifications. Their most important proof requires a provisioned deployment, live outside systems, or a real buyer's data — none of which has happened yet.
Built, not yet proven live
Customer-controlled deployment
The installation design, isolation model, operations material, and backup-and-restore paths exist and are rehearsed in isolated environments. The first real installation has not been provisioned.
Built, not yet proven live
Connections into outside systems
Several governed write-back connections are built or partly built. None is commissioned against a real customer environment, so none is presented as an available connector.
Built, not yet proven live
Real-world document fitness
PDF and scanned-image reading, bounded English text recognition, and supplier-contract extraction are proven on our synthetic test set. A real buyer's documents — with their mess, their languages, and their owners' review — are not yet.
Built, not yet proven live
Operating value
The outcome view and its calculation definitions are built. Time, cost, quality, and benefit claims stay switched off until a real installation records the evidence they require.
Built, not yet proven live
Operational characteristics
Capacity, availability, upgrade behaviour, and support response can only be proven by running deployments under real load, over time.
The path to availability
What happens next, in order.
Each gate opens on evidence, not on a date — so we publish the sequence and the conditions, and deliberately no schedule. This is the same rule our own operating guide prescribes: every gate is evidence, not a date.
Two intended ways to run it
An installation cannot quietly change what it is.
Every installation locks to one of two operating profiles on the same kernel. Choosing a profile records how an installation is meant to run — it is not proof that one has run, and neither profile is offered for installation today.
Control Starter
Run by an approved partner, for you
For complex smaller businesses: curated connectors, assisted setup, business-hours support, and recovery from backup rather than a promised uptime percentage.
Authority Platform
Run by your own team, in your own cloud
For customers who operate the deployment themselves: bring-your-own-cloud (BYOC — the product runs in your cloud account, not ours), your identity systems in charge, tightly controlled outbound connections, and no third-party root access.
Not available
Neither profile is currently offered for installation
The install tooling refuses any configuration claiming more continuity than one restorable server — that refusal is deliberate. Not offering either profile yet is our own decision: a policy gate, not a technical one.
Not available
What you cannot obtain from Lagstyr today.
- A customer installation
- A hosted or shared sandbox
- A trial or pilot
- A product demo
- Early-access credentials
- Production support or SLAs
- Certified compliance artefacts
One of these will change first: the design-partner pilot is the next gate, and when it opens, its admission criteria will be published on this page. Until then, the website collects expressions of interest only — registering does not apply for access, place an order, or begin an evaluation, and it is how pilot candidates will be found.
Follow the evidence as it lands.
Register for occasional development and availability updates — including when the design-partner gate opens.