אנא נפשי כתבית יהביתyitzi

For the executive on the hook for the AI decision

Your board wants an AI answer.
Guessing wrong is expensive.

Consultancies will charge you $50,000 and six weeks just to tell you what to build. Vendors will sell you their product whether it fits or not. Meanwhile the manual work that AI should be doing keeps burning payroll every week, and the decision still has your name on it.

1 · See the plan first, free

Describe the problem on the front page and watch the full implementation plan get written. No call, no card, and the plan is yours to keep either way.

2 · Scope and price the pilot

In the same frontier-model step, every milestone in your plan gets its own scope-based estimate and acceptance trigger. The displayed total is non-binding; the signed SOW controls the final scope and price before work begins.

3 · Roll it out, or hand it over

The same generation proposes your retainer: a monthly base, a platform revenue share, and a monthly cap, scoped to your plan. Your product runs on the platform with hosting included. Revenue shows up on a shared dashboard, and the platform takes its share the way a creator program does.

The plan

Free

Generated on the front page. Yours to keep, or to take to another vendor.

The pilot

Generated quote

Priced milestone by milestone in the same step as your plan. Non-binding until the scope and price are signed in a SOW.

The retainer

Generated with your plan

A monthly base plus a platform revenue share, with a monthly cap, proposed together with your plan. Cancellable.

The hosting

Free

Your product runs on the platform. Hosting, monitoring, and upgrades are funded by the revenue share, not billed.

Get your free plan →Or email a question first

01: What that plan is worth

That free plan is the deliverable
enterprises pay $50,000 for.

The role that produces it is called a Forward Deployed Engineer, the hybrid architect Palantir invented and Salesforce, OpenAI, and Anthropic now compete over. Here is what that costs on the open market.

$50,000+

Discovery phase

What an enterprise AI consultancy charges before a line of code is written. Six weeks. The deliverable is a slide deck.

$250–$400+

Per hour

Professional-services billable rate for an FDE-tier resource: the technical people who actually get AI into production.

$300k–$600k

Per year, fully loaded

What a client company pays to keep one Forward Deployed Engineer embedded in their team for 6–12 months.

$0

What the plan costs you

The plan the front page writes for you: executive summary, architecture, measurement protocol, milestones. Generated in seconds.

Time to first plan

Traditional FDE engagement

3 to 6 months of discovery

This engine

Seconds, then weeks to a live pilot

Cost to see the plan

Traditional FDE engagement

$50k–$500k committed up front

This engine

Free. Two plans, no card, no call

Who does the delivery

Traditional FDE engagement

Senior team pitches, juniors build

This engine

The engineer who wrote the engine builds it

What discovery produces

Traditional FDE engagement

A slide deck and a statement of work

This engine

Architecture, measurement protocol, milestones

How it scales

Traditional FDE engagement

Linearly: they must hire more engineers

This engine

The planning layer is software; delivery is a dedicated engineer

It is an engineering job, not a sales job

70–90% of an FDE's week is shipping production code. They are paid on engineering scales with equity, not on sales quotas and commission.

Total comp runs $200k–$400k

Salesforce publishes base bands of roughly $99k–$186k, rising to $119k–$203k in San Francisco and New York and past $365k for principal tracks. Palantir- and Anthropic-tier AI FDEs land nearer $250k–$450k+.

Clients rent them, they don't hire them

FDEs are procured through professional services or top-tier support contracts. The client pays a fully loaded rate covering overhead and margin on top of the salary.

The premium is for the deployment gap

Internal IT teams can run a demo. Bridging a demo to a working production system inside real data, real latency, and real compliance is the scarce part, and it is what the plan above is scoped around.

Figures are public market benchmarks for the Forward Deployed Engineer role, compiled from Salesforce’s published pay bands, Levels.fyi reporting, and Andreessen Horowitz’s writing on the forward-deployed model. They describe what the role costs in the market. They are not quotes for the work offered here. Your generated plan includes its own milestone-based pilot estimate; the canonical retainer terms appear below.

02: The engagement model, and what it costs

The expensive part is free
on purpose.

The planning phase is where consultancies make their margin and where buyers lose six weeks. Here it is automated and free. Paying starts only when the building starts, and every stage after that is one you can walk away from.

Stage 00: The plan

Free

Months of forward-deployed planning, generated instantly.

One complete plan without an account, with another update when you leave an email. The full dossier (build spec, workplan, evaluation rubric, guardrails, and risk register) is a one-time paid unlock that also removes the cap.

  • Outcome, workflow, architecture, contracts, measurement, and validation
  • Three copyable, model-specific implementation prompts
  • Yours to take to your own team, or to another vendor

Stage 01: The pilot

Generated with your plan

Exact milestones, scoped and priced together.

The frontier model creates the milestone plan and a matching non-binding estimate in the same step. Each amount reflects that milestone's systems, delivery work, governance, and acceptance evidence; the signed SOW controls the final scope and price.

  • One price for every generated milestone, with no universal pilot price
  • Payments tied to acceptance against the milestone's written criteria
  • A visible total derived from the milestone amounts, not model arithmetic

Stage 02: The retainer

Generated with your plan

The one-year plan, executed: priced for your plan, not a rate card.

The same generation that prices your pilot proposes a monthly base, a platform revenue share, and a total monthly cap, scoped to your plan's delivery and operating burden. The base keeps a dedicated senior engineer on the build; the cap keeps your upside predictable; the signed agreement controls the final terms.

  • A dedicated senior engineer through the whole rollout, no hand-off to juniors
  • Base, share, and cap proposed together with your plan, to mutual benefit
  • Cancellable: the retainer is for building, not for lock-in

Stage 03: The platform

Free hosting

Your product runs on the platform, like a video runs on YouTube.

The product is developed and hosted on the platform for free. Revenue is generated through the platform, you watch it on a live dashboard with full analytics, and the platform's compensation is its share of that revenue: it earns only when you do.

  • Hosting, monitoring, and upgrades included, funded by the revenue share
  • A shared revenue dashboard: both sides see the same numbers
  • Model and dependency upgrades handled before they break you
  • SOC 2 / HIPAA / GDPR evidence gathering and audit support

Retainer terms, generated with your plan

Monthly base

Priced with your plan

Funds a dedicated senior engineer, scoped to the delivery and operating burden your plan actually names.

Platform revenue share

A share of platform revenue

Your product runs on the platform and revenue shows up on a shared dashboard. The platform takes its percentage the way a creator program does.

Monthly cap

Total compensation capped

Base and share together never exceed the proposed monthly cap, so your upside stays predictable.

The same generation that prices your pilot proposes all three numbers for your specific plan: a non-binding starting point that becomes binding only in the signed agreement. Hosting on the platform is included; the share is how the platform earns.

What you own, and what the studio keeps

You own the deliverables named in the scope, plus a permanent licence to any studio components needed to run them. The studio keeps its pre-existing platform, reusable components, and general know-how. Confidentiality is mutual and narrow. Please do not send anything confidential before an NDA is in place. A general description is plenty at this stage.

Talk about a pilot →

03: Why it usually fails

Most enterprise AI dies
on the way to production.

The demo trap

Prototypes built on clean sample data break the moment they meet real edge cases, real latency budgets, and the state your database is actually in.

The junior hand-off

Agencies sell you the senior team in the room, then assign the build to whoever is on the bench. The architecture decisions get made by the person with the least context.

The attribution void

Without a baseline agreed before the work starts, nobody can prove the system paid for itself, so it quietly loses its budget at the next planning cycle.

04: The work

Four shapes of work
that survive contact with production.

Workflow cost automation

The paperwork, compliance checks, and data re-entry that quietly consume a department. Automated end to end, with a human validation step where being wrong is expensive.

Revenue staff multipliers

Your highest-value people (advisors, analysts, specialists) given a domain-tuned system so they can cover an order of magnitude more accounts without losing the personal touchpoints that win the business.

Customer-one products

Build the AI product for your own operation first, prove the unit economics on your own P&L, and only then decide whether it is worth selling to anyone else.

Multi-tenant platform architecture

Turning an internal capability into a tenant-isolated platform you can license under your own brand. This part needs to be designed in from the start, not bolted on later.

05: Roles you can deploy today

Hire the role,
not the demo.

Every decision-maker’s inbox is already full of AI demos looking for a problem. A role is different: it has a job description, working hours, rules it must follow, and a log you can read. These are roles the studio’s own platform (ScaleMe, the multi-tenant system in the proof record below) runs in production today.

Flagship template

Outbound sales caller

The hire every founder is told to make: someone who actually picks up the phone. This one calls the prospects you choose, discloses that it is an AI calling for your business, opens with one researched problem you can genuinely fix, and pushes for a single concrete next step, a meeting on the calendar or a paid pilot with a deadline.

  • Works only lists you provide and may lawfully contact, with do-not-call and calling-hour rules set before the first dial.
  • Qualifies honestly for budget, timeline, and whether the problem is real, and ends the call politely when there is no fit.
  • Logs every attempt, outcome, and summary, so the follow-up trail is yours to read and act on.
Deploy from the template on ScaleMe

24/7 intake receptionist

Answers the phone on the first ring, day and night. Qualifies the caller against your criteria, collects the matter details, and books the consultation before a competitor picks up.

See the intake template

Consulting & coaching agent

Explains your offers in your voice, captures each lead's goals and constraints, and routes the high-fit ones to booking, so you start every call already briefed.

See the coaching template

Expert-in-a-product

Turns a senior expert's method, IP, and curated examples into a product clients can use. It interviews the expert to capture the method in their own words, answers only from what they signed off, and holds high-stakes requests for their review.

See the expert template

Paralegal email desk

For the paralegal drowning in email: classifies every forwarded thread by matter and urgency, extracts dates as drafts for the docketing system to confirm, and prepares replies that never send without sign-off.

See the email desk

Talk to a live one first

Shaindy is a production agent running on WhatsApp right now, holding real conversations for a real product. Message her and judge for yourself how a deployed role actually sounds.

Message the live agent

Every template is self-serve on ScaleMe. Deploy it yourself and keep it. The pilot is for when you want the role hired for you: configured on your data, wired into your systems, and measured against a baseline agreed before the work starts.

06: The stream of record

Ten years of production work,
flowing through one pipe.

Every item below is drawn from the studio’s actual record: project repositories, published guides, and systems still in production.

HealthcareE-commerceLegal techEdTechMedia and videoDeveloper platformsVoice and telephonyIndustrial analyticsHealthcareE-commerceLegal techEdTechMedia and videoDeveloper platformsVoice and telephonyIndustrial analytics
Multi-tenant realtime voice platformShaindy · live WhatsApp agentTry that agent on WhatsAppClinical documentation pilotWix Headless launch guideBylined Wix developer columnWhatsApp storefront botHealth-media platform · team engagementML lifecycle writingGaussian splatting on the webThis site's plan generatorMulti-tenant realtime voice platformShaindy · live WhatsApp agentTry that agent on WhatsAppClinical documentation pilotWix Headless launch guideBylined Wix developer columnWhatsApp storefront botHealth-media platform · team engagementML lifecycle writingGaussian splatting on the webThis site's plan generator
TypeScriptReactNext.jsNode.jsPythonJavaPostgreSQLSupabaseAWSEdge workersTwilio telephonyWebSocketsRealtime voice APIsSchema-constrained outputRetrieval-augmented generationSpeaker diarizationWhatsApp Business APIThree.jsGaussian splattingIn-browser local modelsTypeScriptReactNext.jsNode.jsPythonJavaPostgreSQLSupabaseAWSEdge workersTwilio telephonyWebSocketsRealtime voice APIsSchema-constrained outputRetrieval-augmented generationSpeaker diarizationWhatsApp Business APIThree.jsGaussian splattingIn-browser local models

Sourced from the studio’s own project archive and published writing, 2016–2026.

07: The receipts

Three engagements, described
the way they actually happened.

No testimonials, no invented percentages, no logos I have not earned. What follows is what shipped, what is still gated, and where I was one engineer on someone else’s team.

Client pilot · 2026

Clinical documentation, structured from a raw session recording

A healthcare provider needed standardised clinical assessments written up without practitioners losing an evening to paperwork. The system takes a diarized session transcript and maps it onto dozens of structured fields of the provider's own note format, using speaker-aware transcription and schema-constrained model output rather than free-text summarisation.

Live and gated. Automatic audio capture is deliberately still switched off until the provider's clinical team signs off on the field mapping: the failure mode of getting a clinical note wrong is worse than the cost of a manual step.

Shipped
49 commits, first to production in under four weeks
Runtime
Edge worker, access-token gated, PHI safeguards reviewed
Method
Speaker-diarized transcription → schema-constrained extraction

My own product · ongoing

A multi-tenant realtime voice and messaging platform

The infrastructure underneath the client work: seven applications covering API, background workers, marketing, mobile, web, and a WhatsApp adapter and runtime. Realtime voice over telephony, tenant isolation, and the unglamorous harness code that makes model output survive contact with production.

This is my product, not a client engagement. It is listed here because it is why a pilot can move in 30 days (the harness already exists), and because it is the reason I no longer sign category non-competes.

Scale
~2,060 TypeScript files across 7 applications
History
3,305 commits since October 2025
Stack
Realtime speech APIs, Twilio telephony, Postgres

Team engagement · 2023–2024

Health-media platform, backend and frontend, on a distributed team

Nearly two years on a production healthcare content platform, working across backend and frontend alongside four or more other engineers in different timezones. The relevant experience here is not the code. It is knowing how enterprise delivery actually behaves when there are review gates, other teams, and a release calendar you do not control.

Explicitly not a solo build. I was one engineer on a team, and I am naming it that way because the alternative is the kind of proof inflation this page exists to argue against.

Duration
January 2023 – September 2024
Contribution
~101 backend commits among a 5+ engineer team
Context
Distributed team, regulated content domain

Public and verifiable

Developer Advocate at Wix

Wrote the developer ecosystem content for Wix Headless APIs. Public, bylined, and still online.

See it →

Published technical writing

Architecture breakdowns, ML lifecycle guides, and code-first walkthroughs under my own name.

See it →

Multi-model production routing

Cascading fast classifiers into frontier models for reasoning, with PII masking between the layers.

Generative media and spatial

Three.js and Gaussian splatting for 3D on the web, synthetic audio, and custom vision workflows.

08: Inside the engine

Years of senior AI architecture and platform engineering, baked directly into the tool engine.

This strategy generator is not a generic wrapper. It incorporates years of hands-on platform engineering, Developer Advocate expertise at Wix, multi-model agentic routing, and operational workflow automation.

The maintainer, creator & principal AI architect

The maintainer

Creator & Principal AI Architect

What powers the Architect AI evaluation engine?

When you input your enterprise objective, the engine evaluates your request against real-world production architectures, baseline attribution formulas, and governance controls derived from proven deployments.

Wix Developer Advocate Heritage

Built by former Wix Developer Advocate leading developer ecosystem content for Wix Headless APIs. Read guides on the Wix Author Column →

Schema-Constrained LLM Pipelines

An instant local classifier scopes your objective, then gpt-5.6 Sol writes the plan against a strict JSON schema on the Responses API, streamed back section by section, parseable by construction rather than by retry.

Attribution before delivery

Every plan it writes starts by naming the baseline to measure against, because the engagements that lose their budget are the ones that never agreed what “working” meant.

Verified Public Proof

Open-source code, 3D WebGL / Gaussian splatting guides, and ML publications documented on dev.to/yitzi →

Try the generator→

09: Writing & publications

Live Engineering Feed.
Articles, guides and publications.

Written by the maintainer · former Wix Developer Advocate

Featured AI Toolkit GuideWix Dev & Dev.to Deep-Dive

Building a WhatsApp Chatbot with Wix Headless API & AI Toolkit

Full technical walkthrough of building an autonomous e-commerce bot using WhatsApp, @wix/headless-ai toolkit, function calling, and real-time cart orchestration.

Read Full AI Guide & Architecture →Updated Guide 2026
Wix Engineering PostWix Engineering Blog

Wix Headless APIs: Unlocking Multi-Platform Headless Architecture

Comprehensive technical guide on leveraging Wix Headless APIs to power custom React, Next.js, and mobile applications with enterprise backend services.

Read Article →Wix Engineering
ML Deep-DiveI On Demand Engineering Blog

The Never-Ending Story of Model Training: A New Chapter for Machine Learning

In-depth technical breakdown of continuous model retraining, automated feedback loops, and production AI model lifecycle management.

Read Article →I On Demand Blog
Author ColumnWix Developer Blog

Yitzi Ginzberg: Official Author Column & Developer Guides at Wix

Collection of technical tutorials, API integration blueprints, and developer ecosystem guides written during my tenure as Developer Advocate at Wix.

Read Article →Wix Author Column
Open Source CodeDev.to Technical Walkthrough

3D Gaussian Splatting & WebGL: Real-Time Spatial Experiences with Three.js

Code-first breakdown converting captured video into interactive 3D web environments using Gaussian splatting, Three.js, and custom shader pipelines.

Read Article →Dev.to / yitzi

10: Fit

This model is a bad fit for plenty of good companies.

Worth reading before you fill in the form. It saves a wasted call.

Worth a conversation

  • You have an operational bottleneck that costs real money every week it stays unsolved.
  • You are willing to agree a measurement baseline before the work starts, even if the number is unflattering.
  • You want the person who designs it to also be the person who ships it.
  • Someone with budget authority is actually sponsoring this internally.

Go elsewhere

  • You need a large team billing many seats. That is a job for an agency, and there are good ones.
  • You want strategy decks without anyone writing production code.
  • You are optimising for the cheapest possible day rate.
  • There is no internal sponsor, so nothing can actually be deployed at the end of it.

11: Get in touch

If the plan looks right,
the pilot builds the first piece of it.

Take the generated plan to your own team first if you want. It is yours either way. To have it executed instead, outline what you are trying to fix in the form below. Please keep it general: nothing confidential before an NDA is in place.

Apply to work together

Three questions

Keep it general. Please don’t include confidential information here. We’ll sign a mutual NDA before anything sensitive changes hands.

The retainer terms

Monthly base + platform revenue share, with a monthly cap, all three generated with your plan.

Non-binding until the engagement agreement is signed. Hosting on the platform is included; the share applies to revenue generated through it.

Be specific. “Logistics” is a category; “customs brokerage for EU-bound perishables” is a description. Minimum 10 characters.

The thing that would make a real difference to how the business runs. Rough is fine. Minimum 10 characters.

Internal attempts, vendors, off-the-shelf tools: whatever didn't get there, and why. Minimum 10 characters.

I read these myself · Mutual NDA first