Purple Orange AI
Featured systemViolemaFounder operations AILive
What it proves
Recurring work moves from connected sources through review gates to channel delivery with durable run and cost evidence.
Agentic product studio
We design and engineer AI products that coordinate real work across control surfaces, connected tools, and human approval gates.
Recurring work moves from connected sources through review gates to channel delivery with durable run and cost evidence.
Explore project proof“Build the system. Show the proof.”
Web app Slack Telegram
Delivery boundaryHuman approval on every run
Build stack: Claude Code, Fable 5, OpenAI, GitHub, Obsidian, n8n, Next.js, React, TypeScript, Python, Node.js, Tailwind CSS.
Unilever
Western UnionFor owner-led businesses, funded startups, and mid-market teams with one workflow that keeps stealing time. We identify what is worth automating first, map the implementation path, and tell you plainly whether it is worth doing now.
AI Workflow Audit · normally $1.5K
Bring the workflow eating your week, blocking a launch, or keeping a pilot out of production. We pressure-test it, score the implementation risk, and give you the clearest next move.
If we do not see a workflow worth automating, we will tell you before you spend a dollar.
A repeatable sequence currently happening manually — something an owner, operator, founder, support lead, sales team, or engineering org does over and over. If it has clear inputs, decisions, and outputs, it can usually be systemized.
If your workflow is not on this list, still book the audit. The point is to find the highest-leverage starting point before you commit to implementation.
Most modern business tools with an API: Microsoft 365, Google Workspace, HubSpot, Pipedrive, Airtable, Notion, Slack, Calendly, Stripe, Twilio, Shopify, GitHub, common CRMs, and case-management systems. If your tool has an API, probably yes. If it does not, we will tell you what is realistic before you commit.
No. It removes the worst hours of their day so they can do real work.
If there is a strong fit, we recommend the right implementation path: a $12K two-week sprint, a $25K+ four-week buildout, or a larger infrastructure scope. If there is no strong fit, we say so.
Default setup runs in your tools and your accounts. Data stays in your environment. We document the data flow before we build, you sign off, then we build.
Yes. It is normally a $1.5K diagnostic, but it is free while we onboard the first client cohort. The tradeoff is simple: we are selective, direct, and focused on workflows that can become paid implementation work if the fit is real.
Pick the workflow eating your week.
Free while onboarding first clients · Normally $1.5K · No commitment.
Audit, sprint, or buildout. Same senior engineer across every tier. No fake discovery theater.
Need ongoing or enterprise? See all packages →
Start here · first client cohort
Free $1.5K value
We diagnose one workflow, map the tools and data involved, rate complexity, and recommend the right implementation path — including “do not automate this yet” if that is the truth.
Best for: Founder-led teams that know manual work is expensive but need the right starting point.
Free while onboarding first clients. No commitment.
Book the audit2 Weeks
$12,000
One to two production workflows built inside your actual tools: access setup, implementation, testing, approval controls, documentation, and handoff.
Best for: A clear manual workflow with real business value and enough focus to ship in two weeks.
Fixed fee. Scope confirmed after the audit.
Book a free audit4 Weeks
$25,000+
Several related workflows, shared knowledge layer, cross-tool integrations, approval and escalation paths, monitoring, and team operating docs.
Best for: Teams with multiple workflows or an operational area that needs to become a real AI-enabled system.
Starting at $25K. Scope depends on systems, workflows, and complexity.
Book a free auditEvery engagement follows the same five beats. No mystery, no surprises on the invoice.
30-min call + async review of your stack, data, and goals.
Written plan: tools, MCPs, data flow, guardrails, eval harness.
Production code, real integrations, shipped in weekly demos.
Eval harness, observability, and red-team pass before launch.
Docs, runbooks, and a live walkthrough so your team owns it.
We pick the sharpest tool for the job — then we write the code, wire the pipes, and hand it off so your team can extend it.
Our default for complex agent orchestration, MCP integrations, and long-horizon autonomous work. Ships with AGENTS.md, skills, and hooks.
When a team is already deep in the OpenAI ecosystem or needs tight GPT-5 integration. We treat it as a peer, not a fallback.
Best-in-class IDE experience for developer-facing flows. We configure project rules, context, and model routing for the whole team.
Custom connectors into Shopify, NotebookLM, Notion, Postgres, internal APIs — whatever your team actually uses. Built to survive upgrades.
Production-grade orchestration. Compose, Nginx, SSL, zero-downtime deploys, and monitoring. Built like an engineering team would build it.
The glue layer. FastAPI, Next.js, worker queues, RAG pipelines. We write code your engineers will recognize, review, and maintain.
If your stack doesn't appear here, ask — we've probably shipped with it.
MCP means Claude Code and Codex read from, write to, and orchestrate across the tools you use every day — Notion, Slack, Gmail, Linear, Stripe, Shopify, and 1,000+ more. Anything internal, we build a custom MCP server for.
Don't see yours? Scope a custom MCP server →
We wire your agents directly into Slack, Telegram, Discord, WhatsApp, and iMessage. Your team types a sentence; the agent runs the workflow, updates the CRM, drafts the doc, or ships the post — then reports back in thread.
Telegram
Discord
WhatsApp
Live sequence — a real Violema mission pattern: request, sources, reviewable card, your approval, delivery. Every run logged with cost evidence.
Claude Code and Codex are both free to try. Docs are good. Here's why teams still call us.
2–3 months of trial and error
Your team can figure it out — but two months of tool hopping, brittle demos, and abandoned automations costs more than a focused sprint. We already know which patterns survive real work.
3–6 months to fill + 2–3 months to ramp
Senior AI engineers with real production chops are rare, expensive, and not looking. You would wait months to hire, then months more to ramp. We ship working workflows in weeks and hand off to your existing team.
Strategy decks that never ship
Most AI consultancies sell recommendations and leave you to implement. We write real code, deploy to production, and do a full handoff with documentation your engineers can actually use.
Real owned products and operating systems, with truthful status, current media, and deeper proof where it is publishable.
An outcome-first AI operator for recurring founder and team workflows: connect real systems, draft useful work, require approval where needed, deliver through real channels, and keep an inspectable run ledger.
A governed sales, partnership, press, and collector operating system that turns production-ledger evidence into qualified-revenue recommendations, proof readiness, pipeline health, and approval-gated action.
A non-executing control plane that selects models, verification, escalation, and approval contracts for Hermes, then records confidence, cost, execution, and outcomes.
An incubating visual evidence intelligence system for psychedelic medicine, designed to turn research, trials, compounds, and methodological context into a source-backed neuroscience surface.
An Obsidian knowledge graph built by Graphify: documents, decisions, agent runs, and entities are extracted into one linked, queryable vault that every agent and platform reads from — the same durable context, shared instead of re-derived.
A configurable outbound operating system for lean teams, joining campaign setup, source packs, research, qualification, review queues, and send controls.
A compounding pSEO, operator-research, distribution, and monetization stack that scores opportunities, gates claims on proof, and lets search and revenue signals choose the next batch.
Three entry points, one quality bar. Start with the free audit, then pick the smallest implementation path that can produce real leverage.
Typical signal: owner-led operator, funded startup, or mid-market lead with too many manual workflows and no clean first move. The audit turns that fog into a ranked implementation path.
Typical signal: a small team with one or two high-value workflows ready to build. You have examples, tools, and a real owner for the process.
Typical signal: several related workflows, multiple tools, or a team that needs a repeatable AI operating system across sales, support, finance, ops, or engineering.
We specialize in Claude Code, Codex, and Cursor — with deep MCP, agent orchestration, and RAG work. We bring the sharpest tool for your stack, not the one we brag about.
Every workflow runs in production with Docker, CI/CD, monitoring, and documentation. No prototypes that rot. No proofs of concept that never ship.
Your team owns everything we build. Full documentation, recorded walkthroughs, AGENTS.md configurations, and post-delivery support so your engineers can extend it.
Start with the audit, ship a sprint, scale to a buildout only when the business case is obvious. No lock-in, no retainers you do not need.
Purple Orange AI is a production AI engineering practice based in Chicago. We build and operate the AI systems that owner-led businesses, funded startups, and mid-market teams actually ship — Claude Code, Codex, Cursor, MCP servers, agentic workflows, Docker orchestration, CI/CD pipelines, and full-stack deployments.
Founded by Max Markovtsev, who ships AI infrastructure daily — from custom MCP server integrations to full operator deployments on production VPS. Before building AI systems, Max spent 15+ years shipping high-stakes projects at Leo Burnett, BBDO, and JWT for P&G, Unilever, and Wrigley — which means we know how to communicate with executives, hit deadlines, and deliver under pressure.
We take on 3–4 engagements at a time.
We build and deploy production AI systems for owner-led businesses, funded startups, and mid-market teams. That includes environment setup, MCP server integrations, agent workflows, CI/CD pipelines, and complete team handoff — using whichever tool fits best: Claude Code, Codex, Cursor, or a mix. Engineering practice, not a deck-selling consultancy.
Both — plus Cursor. We pick the tool by the problem: Claude Code for complex agent orchestration and MCP-heavy work, Codex when a team is already deep in the OpenAI ecosystem, Cursor for developer-facing IDE flows. Same team across all three.
We assess workflow readiness, integration surface, ownership, risk, and controls. You walk away with a specific automation candidate, tool/integration map, timeline, package recommendation, and honest scope estimate — even if you don’t hire us.
Hiring takes 3–6 months. We deploy in 1–6 weeks. You get production infrastructure, documentation, and handoff — not a person you need to manage. Our practice has already solved the problems a new hire would be discovering.
Yes. Many of the best first workflows live inside owner-operated businesses: real estate, dental, HVAC, CPA, law, auto dealers, light manufacturing, agencies, and service businesses. Same senior engineer, same quality bar, scoped to fit.
Yes — typically through Production AI Infrastructure engagements (see the full packages page). We navigate security review, SSO, audit requirements, and cross-team governance so a stalled pilot becomes real production infrastructure.
Book a free AI workflow audit. Normally a $1.5K diagnostic. We will review the workflow, map the tools, rate the implementation risk, and give you a concrete path to production — whether you hire us or not.
A ranked workflow recommendation, integration map, complexity rating, timeline, package recommendation, and an honest read on whether the work is worth doing now.
Claude Code
Fable 5
OpenAI
GitHub
Obsidian
n8n
Next.js
React
TypeScript
Python
Node.js
Tailwind CSS
