Starter
One AI Workflow
$5,000
Delivery: 2 weeks
One repeated task handed to AI, connected to one of your tools, with approval.
Get a quoteAI for business
AI that takes hours of manual work off your team every week.
AI agents, assistants and automations connected to the tools you already use, built by Marian Sorca, who runs 14 AI features in his own product.
AI projects from $5,000 Reply within 24 hours
(01) What we build with AI
AI connected to the work, not a demo.
Connected to the tools you already use, with approvals, logs and costs you can see.
AI agents that do real work
Research, update records, follow up and run workflows, with a person approving the risky steps.
Voice and audio
Talk to your app, voice assistants, call transcripts and summaries.
Documents and files
PDFs, contracts, invoices and spreadsheets turned into data.
Images and video
Analyze, tag, generate and edit at scale.
Chat and search over your data
Answers from your own data that cite the source.
APIs and webhooks
So your systems talk to each other.
MCP servers
So ChatGPT, Claude, Cursor, Grok and any other MCP client can work with your product.
(02) Services in this lane
AI for business, service by service.
Each one with a starting price and a delivery time. Pick one, or combine them.
AI agents and automations
Repeated work handed to AI, connected to your tools, with approval steps.
From $5,000 · 2 weeksAI assistant on your company knowledge
Answers from your documents and systems, with sources.
From $5,000 · 2 weeksDocument AI
Invoices, contracts and orders turned into data in your systems.
From $5,000 · 2 weeksVoice AI
Voice assistants, call transcripts and summaries.
From $5,000 · 2 weeksAI features inside your product
Search, drafting, chat and assistants on your own data.
From $5,000 · 2 weeksMCP servers
Let ChatGPT, Claude, Cursor, Grok and any other MCP client work inside your product.
From $5,000 · 2–5 weeks(03) Where AI pays
Start from the work, not the model.
- 01
“Our team does the same manual work every week.”
Automations - 02
“We have data nobody has time to read.”
Summaries and reviews - 03
“Customers ask the same questions again and again.”
An assistant on your own content - 04
“We want Claude or ChatGPT to work with our product.”
An MCP server - 05
“We want to know what changed, not read every row.”
AI insights in your app
And sometimes the answer is no AI at all. You’ll hear that first.
(04) How we build AI
The practices, and where they already run.
Every AI build gets the same care we put into our own product. These aren’t promises; they’re live in SelfManager.ai today.
What you getLive in SelfManager.ai
Costs you can see. The right model per task, with usage limits.
Each model’s price in credits shows before a request is sent.
A fallback when a model fails. Your feature keeps working.
If a model is busy, Gemini answers instead.
Review before it saves. AI output doesn’t overwrite your data.
AI plans land in an editable preview before they’re committed.
Permissions you choose. AI sees and does only what it should.
The MCP server can read only, make changes, or write to shared tables. It can’t delete tables, tasks, notes or comments.
A trail of what AI did.
Every change through MCP is marked “(via Claude)” in the table’s log.
Your data stays yours.
Requests to Claude, GPT and Grok go straight to the provider, which doesn’t train on them.
Plus testing on real data, usage tracking and a documented handover.
(05) In production
Not a demo. Used every day.
SelfManager.ai, AI built around real work.
A date-based task and project manager whose AI reads tables, statuses, priorities, time tracking, deadlines, comments and notes, then writes back into them. 14 AI features across 4 surfaces, 11 models in Fast and Thinking modes, and an MCP server in production.
AI
14 features live
Models
11 to pick from
MCP
Server in production
Integrations (no AI)
Shopify, SmartBill and Make: a client’s invoicing, automated end to end.
Royal Labs: a multi-step inquiry form that submits straight into HubSpot.
“Communication was clear and efficient, the integration between SmartBill, Make, and Shopify was completed successfully and everything works smoothly.”
(06) MCP servers
Your product, inside Claude and ChatGPT.
We built the MCP server for SelfManager.ai, and it runs in production. Users connect their assistant and ask in plain words: plan the day, tick a task, review the week. It works with ChatGPT, Claude, Cursor, Grok and any other MCP client. Each connection gets the permissions its owner chose, and every change is logged. We build the same for your product.
MCP serversYou
What’s on my list today?
get_dayClaudeTwo tables today. Launch prep: 1 of 3 done, and “email beta users” is high priority. Gym: not started.
From selfmanager.ai/mcp
(07) How it runs
Small enough to ship, big enough to matter.
- 01Pick the use cases.
One to three, chosen from where time or money is lost today.
- 02Prototype on real data.
We test with your actual data, not dummy content, to see if it genuinely helps.
- 03Build it into your stack.
With limits, fallbacks and logging from day one.
- 04Launch, measure, extend.
Usage tracked, then the next use case.
The minimum engagement is $2,000. Each use case is scoped and priced before work starts.
Models: OpenAI GPT, Anthropic Claude, Google Gemini or xAI Grok, chosen per task. US models only. Automations with Make, Zapier and Cloud Functions; backends on Firebase and Node.js.
(08) Prices
AI agents and automations, priced up front.
Three fixed-price packages with a delivery time, and Enterprise for larger companies. You get a written scope and price before work starts.
Standard
AI Across Your Tools
$8,000
Delivery: 3 weeks
AI connected to two or three of your systems: email, CRM, documents or database.
Get a quotePremium
AI System
$15,000
Delivery: about 6 weeks
Agents, integrations, a dashboard for your team, monitoring and team training.
Get a quoteEnterprise
Custom pricing
Company-wide AI, several agents, connections to systems like Salesforce or Microsoft 365, with access rules.
Contact usLarger projects
| Scope | Typical price |
|---|---|
| Agents across a workflow or product several features, your data, testing and monitoring | $25,000 – $100,000 |
Other AI work
| Engagement | Typical price |
|---|---|
| AI Opportunity Review: where AI pays in your business, ranked by cost and return, with a plan | From $5,000 |
| Product analytics setup: a tracking plan, event logging into your own BigQuery, and dashboards | $8,000 – $25,000 |
| AI analyst on your data: ask questions about your users in plain English, with read-only access and guardrails | $10,000 – $30,000 |
| Support AI: sorting tickets, drafting replies and answering from your help content, inside the helpdesk you already use | $10,000 – $40,000 |
| AI rollout for your team: ChatGPT or Claude connected to your tools, with usage rules and training | $8,000 – $25,000 |
| AI care: monitoring, model upgrades, testing and cost control after launch | From $2,500 a month |
Models: OpenAI GPT, Anthropic Claude, Google Gemini and xAI Grok, chosen per task. Model usage is billed by the provider to your own account; we estimate it before the build and add usage limits so it stays predictable.
Want a senior engineer every month? Monthly plans from $2,000 a month, fixed or hourly. Discuss a monthly plan
(09) Questions
Questions before you start.
What does an AI project cost?
Every AI service starts at $5,000, MCP servers included: agents and automations, an assistant on your company knowledge, document AI, voice AI and AI features inside your product. Each use case gets a written price before work starts, and model costs are estimated up front.
What data does the AI see?
Only what the feature needs, under your rules. We decide that together before anything is built. Your data stays in your own accounts, on business API plans that don’t train on it, with access set per user.
Which models do you use?
OpenAI GPT, Anthropic Claude, Google Gemini or xAI Grok, chosen per task: a fast, cheap model for simple steps, a stronger one where reasoning matters. US models only.
Will AI costs surprise us?
They shouldn’t. Usage limits and caching are built in, and you see what each feature costs to run.
What is an MCP server, and do we need one?
It’s how assistants like Claude and ChatGPT read and act inside other software. You need one if your customers or team should be able to use your product from their assistant. See MCP servers.
Can you add AI to a Shopify store?
Yes, where it pays: a shopping assistant, support answers from your orders and policies, product content and back-office automations. See AI for your Shopify store.
Do you work on visibility in ChatGPT or Google answers?
Not as a separate service. Every website we build is ready for Google and AI search, but ongoing SEO and AI visibility work isn’t part of our services.
Start a project
Have a project in mind?
Where others see impossible, we see solutions.
When a project gets called too hard, our answer is simple: bring it.
We don’t fear complexity. It’s where we do our best work.
Tell us what you’re building and where it’s stuck. Within 24 hours you get useful questions and a proposed next step, or an honest answer if we’re not the right fit.
- 01Tell us about it.A few lines on the goal, the deadline and what exists today.
- 02A reply within 24 hours.Useful questions and a proposed next step, in writing.
- 03Scope and price agreed before work starts.Projects from $2,000. Ongoing fractional CTO work is billed monthly.
Email
[email protected] ↗
Response time
Within 24 hours, 7 days a week