An expert in your most complex enterprise system — in a box. It does the real work, and it earned that expertise by drilling against a safe fork of your system until every answer was provably right.
Point a general model at a complex ERP or database platform and it writes plausible-but-wrong output. Teams fix this by hand — feeding docs and examples, wiring tools, then babysitting a trial-and-error loop until the model finally "gets it." Bespoke, slow, and locked in one engineer's head.
To keep data in-region, private deployments run smaller open models — which are even shallower on the domain. The harder the constraint, the worse general models perform.
There is no automated way to take a general — ideally sovereign — model and make it deeply, verifiably competent at one specialized system, and keep that competence persistent and improving.
v1 changes no model weights — pure scaffolding. The engine that makes it expert.
It requires a real, forkable environment plus curated oracles per domain. That is the central cost — and the barrier.
Runs the output against the real instance. Does the migration apply? Do the rows reconcile? Do tests pass, types check, invariants hold? Binary, auditable, cheap to trust.
Scores semantic quality where determinism can't — readability, idiomatic style, security smells. Used only to rank among passers, never to override a hard fail.
Pulls the relevant schema and a known-good migration example.
Drafts the migration via MCP tools, runs it on a forked dev DB.
A constraint fails. Structured feedback returns the exact error.
Fixes the constraint; migration applies, rollup totals reconcile.
"Safe schema-migration + reconciliation" — ready for next time.
The agent acts through the same MCP tools, runs on a sandbox fork, and shows the verifier's receipt — so an operator can trust the work.
Supply five things per vertical and MaxSavant produces a specialized agent — onboarding a domain means authoring the verifier + oracle set, not rebuilding the platform.
Apache-2.0 / MIT / BSD / PostgreSQL throughout. No AGPL/SSPL surprises. SBOM maintained.
Runs entirely in the customer's environment. Nothing leaves the region.
Corpus, skills & run history stay in the customer's own Postgres, in-region — never pooled across tenants, no external egress.
Thin abstraction layer — swap the base model as the frontier moves.
Every layer is interchangeable, permissive open-source, and self-hostable. We ship the capability — never a product name.
Apache-licensed models can be made expert with scaffolding alone — no weight changes required in v1.
Execution-feedback and skill-learning results are now published and repeatable — the loop is proven science.
EU & regulated enterprises need expert AI that can't use a US frontier API — and have budget for it.
The scaffolding tier: deployed expert agent + Operator Console for one system. Priced on the engineering it replaces.
Same engine, new System Y. Marginal cost falls as the pipeline hardens; net-revenue retention compounds.
SFT + RLVR against the same verifier, for customers who plateau on scaffolding and have the volume to justify GPU spend.
On a fixed held-out task set, the MaxSavant agent shows a statistically meaningful, verifier-scored improvement over a vanilla baseline on the same model.