Case studies

Aircraft parts procurement: from inbox chaos to a managed pipeline

An AI agent reads incoming RFQs, compares supplier quotes and checks trace documents; an operations system moves each deal through mandatory stages.

Full loop

full AI loop on a live procurement process — from incoming RFQ to team notification; confirmed by the owner

3

types of trace documents checked by the agent: FAA 8130-3, EASA Form 1, COC; counted from the owner's brief

A sales and support platform for a distributed partner network

Partners ask who on their team is inactive and what blocks the next level — and get numbers for their own part of the network only, enforced at the SQL level.

20 of 21

UAT checks passed on the client's live back-office database (reconciliation protocol); one partial — no last-activity date in the data

10 of 10

question categories from the assistant behaviour spec (~25 scenarios) implemented; one sub-item outstanding (checklist count)

Panel specs from CAD drawings in seconds, not hours

Reads DWG/DXF layouts and builds the Excel spec: 10–30 seconds instead of 2–15 hours by hand. All 784 panels of one real project matched the manual spec line by line.

784/784 and 189/189

panels on one project and wall panels on another matched the manual specs line by line, size groups included; area within 0.001 m²

2–15 h → 10–30 s

to produce a project spec: manual work vs app processing, measured on real projects

One profit per SKU across three marketplaces, reconciled to 0.00%

Five seller accounts on WB, Ozon and Yandex Market merged into one SKU-level P&L: 0.00% variance vs the client's manual benchmark, forecast 2.7× more accurate than naive.

0.00%

variance vs the client's manual benchmark across units, revenue, COGS, profit and margin for a control SKU over a month; threshold was 1%

2.7×

more accurate than naive: weekly WAPE on SKUs driving 80% of revenue, 29.6% vs 81.4%. The 25% goal is open: history covers 66.9% of SKUs

Music releases without missed deadlines

Release ops for independent labels: 9-stage lifecycle, pitching deadlines for 12 stores, AI drafts with human approval. Zero to production-grade in 7 weeks.

7 weeks

from first commit to a production-grade stack with Vault, encrypted backups, SLOs and a move to a Russian data centre (265 commits)

16 days

from project start to an investor presentation with a live product demo

Land-plot marketplace with a next-step plan: MVP in 2 months

From a mock-up to a working platform: plot → works → contractor → request. Rule-based next-step engine, three dashboards, personal-data compliance. MVP in 2 months.

2 months

from approved spec to pre-release MVP on an HTTPS stand — week 9 against the plan's own 10–13 week estimate

7 days

from spec to the first full-implementation commit: 168 files, 21.5k lines, then two months of hardening to pre-release

Repricing without manual price control: a contract-guaranteed pilot

Competitor prices tracked per SKU on the marketplace, a price computed inside an agreed corridor, applied only after confirmation. Pilot: 10 SKUs, setup within 14 days.

10 SKUs · 2 scenarios

pilot scope; the SKU cap and both scenarios are enforced in code and verified by contract tests — the cap cannot be exceeded

up to 14 days

contractual setup window from client inputs to launch, then a 1-month pilot; the service tracks the dates and closes access when the period ends

From business canvas to a student-work marketplace demo in about six weeks

The client had a business model and no product. We built a student-task marketplace MVP where the server enforces legal and platform rules, and put a demo stand live.

~6 weeks

from first commit to a deployed demo with all workspaces; 7 working days in commit history

3 checks

run by the server before a contractor is assigned: data consent, self-employed status, mentor — each with a plain refusal

Agent teams assembled by configuration that review their own work

Core of a multi-agent platform built in 2.5 weeks: 29 declarative agents in three teams, agent-critic pairs, shared memory on four databases, five autonomy levels.

25,000+

lines of Python in the platform core across 134 modules, counted from the repository

29

declarative agents in three ready-made teams — engineering, cognitive, research; counted from YAML specs

A multi-agent environment where rules are code, not prompts

In four days we built and open-sourced (MIT) an agent environment where constraints are enforced in code: cryptography, Byzantine consensus, reproducible experiments.

64 × 10,000

agents × ticks in the reference experiment: 131,372 events, zero invariant violations; sha256 attestation independently verified

up to 3.9×

faster policy tick on the reference load (1,126.7 → 286.5 ms) with bit-identical hashes; measured with the committed profiling script

Long-term student memory: from hypothesis to a working service

A neuromorphic memory core and cognitive digital twins of students: 32 REST endpoints, 368 tests and formally verified memory convergence — built in a 10-day sprint.

10 days

from first commit to a release with formal verification, measured by commit dates

368

test functions across 37 files, counted from code

From mathematical theory to a verified numerical library in 9 months

A compensated-computation library: precision loss is visible and auditable, properties machine-proved in Lean 4, every numeric claim backed by a reproducible benchmark.

1.0 instead of 0.0

residual preserved on the [1e16, 1, −1e16] aggregation that float silently drops; reproducible benchmark artifact in the repository

≥10x

stability ratio vs float64 on catastrophic cancellation; pinned baseline under regression control in CI

A mobile client for an AI learning platform, built without waiting on the backend

Flutter client for an exam-prep platform: adaptive micro-lessons, a streaming AI assistant, a knowledge map. UI built in parallel with the backend via a mock layer.

13 weeks

from first commit to a working app with auth, goals, lessons and AI chat

41 → 81 endpoints

API coverage doubled from MVP to the extended version — 14 → 31 modules on the same architecture

A pilot plan for the visitor, a qualified lead for sales

We replaced the contact form with an AI consultant: it interviews the visitor, returns a pilot plan with KPIs and risks, and sales gets a lead with budget and timeline.

1 day

Working MVP — frontend, backend and deploy configs — built in a single day

16 days

From first commit to production with HTTPS and an issued certificate on its own domain

StudyNinja and KnowledgeBaseAI

The learning platform and the graph knowledge platform are covered in the Ecosystem section.