AI tools for your support team, built for a fixed price.

I'm Johny Patrick. I build pre-send reply checks, AI drafting and agent workflows for SaaS and service businesses. A person on your team approves anything a customer will read. A first look at one workflow is free, and paid work starts at $1,500.

Free, no slides. You leave with a scope and a price, or a plain "this isn't a fit".

I built Support Coach, a reply checker that is live on the Chrome Web Store and works inside Zendesk, Intercom and Zoho SalesIQ.

An agent is about to send this:

"Like I said, you need to reconnect it yourself. It's not a bug on our end, and there is nothing I can do from here."

  • Blames the customer
  • No help offered
  • Dead end

The check suggests:

I can help you get this reconnected. This happens when the local connection token resets rather than a platform outage, and I can walk you through reconnecting it right now so everything syncs cleanly.

Real output from the demo on this page. The agent can accept it, edit it, or ignore it.

Who this is for

  • Support leads. Your agents are good, but rushed replies still go out, and you find out in QA days later.
  • Operations heads. You want AI to take the repetitive work off the team without letting it send anything on its own.
  • Founders. You need one AI feature working in your product or help desk this quarter, not a six-month roadmap.

Where to start, and what it costs

Every price is fixed in writing before any work starts. Where you see a range, the size we agree decides where in it you land.

Packages, typical duration and price
Package Typical time Price

One-Workflow Teardown

48 hoursFree

Send me one repetitive workflow: what it is, how often it runs, and which tool it lives in, with screenshots or a short recording. Within 48 hours you get a written verdict. No call needed. I take four a week.

You get:

  • A written verdict on that workflow.
  • Where AI would help, where it would hurt, and what I would build first.
  • No obligation to buy anything.
48 hours Free

5-Day Automation Blueprint

5 working days$1,500

Two 45-minute audio or screen-share interviews, then five working days on your workflow. I rank what is worth automating using your own numbers, and build a working proof of the top pick.

You get:

  • A map of the workflow.
  • Three automations ranked by hours saved and difficulty.
  • A working proof of the top pick, on sample data.
  • A fixed-price build quote with written acceptance tests.
  • A one-page decision memo.

If the Blueprint does not name at least one automation worth building and show a working proof of it, you get your money back. The fee counts in full toward a build signed within 90 days.

5 working days $1,500

First Agent Live

About 3 weeks$3,500 to $9,500

One workflow running with a person in the loop. For example, a pre-send check on agents' drafts, a drafting agent that waits for approval, or a browser extension inside a tool your team already uses.

You get:

  • The workflow, live, with a person approving before anything reaches a customer.
  • Acceptance tests written first, so you can see it pass.
  • The code in your own repository.
  • A runbook and an audio handover.
  • 30 days of fixes and support after launch.

Small $3,500, standard $6,500, large $9,500. Billed 50% at start, 25% at the midpoint, 25% when the agreed tests pass. If they have not passed 10 working days after the agreed date, that last 25% is waived.

About 3 weeks $3,500 to $9,500

Keep It Running

Month to month$1,500 to $2,500 a month

After a build, I keep the workflow healthy. I read the approval log, adjust prompts and rules when your policies change, and fix what breaks when a connected tool changes. Stop any month.

You get:

  • A monthly review of approvals, edits and rejections.
  • Prompt and rule updates as your policies change.
  • Fixes when a connected tool changes.
  • A short note each month on what changed and why.
Month to month $1,500 to $2,500 a month

Agent Operations Build

About 8 weeksIn your proposal

Two to four connected workflows for one team, one operating dashboard, and 90 days of Keep It Running. Built on the same queue, approval and permission pattern I run my own work on. The price is set in a written proposal, usually after a Blueprint or a first build. I take one a quarter.

You get:

  • Acceptance tests for each workflow.
  • One approval queue across them.
  • Runbooks and a handover for your team.

See the system it is built on

About 8 weeks In your proposal

Built for Zendesk, Intercom and Zoho SalesIQ today. Another help desk needs a short paid discovery first, usually two to three days.

If the scope changes, we agree a new price before I continue. Keep It Running is billed monthly.

Book a 15-minute call

How it works

  1. A 15-minute call.

    You describe the problem. I tell you whether I can help, which package fits, and roughly what it will cost.

    15 minutes

  2. A scope and a fixed price, in writing.

    One page: what you get, what it costs, what I need from you, and when it ships. You decide with everything in front of you.

    Within three working days

  3. Build, review, handover.

    You see it working on your own examples before it goes live. At the end you get the code, the documentation and a walkthrough.

    Five days to about eight weeks, depending on the package

Proof: a product I built and run

Support Coach is a Chrome extension that checks a support agent's reply before it is sent. It is live on the Chrome Web Store and works inside Zendesk, Intercom and Zoho SalesIQ. The packages above are the same kind of work, done for your team.

  • It reads the draft, not the customer.

    Only the agent's own draft is sent for checking. Customer messages are never read and never leave the browser.

  • It asks for almost nothing.

    The extension requests one browser permission and runs only on those three help desks.

  • It is tested at every layer.

    The rules engine, the AI layer, the backend and the extension each have their own automated tests.

I don't quote customer satisfaction or resolution-time gains, because I have not run a controlled before-and-after. If those numbers matter to you, we can build the measurement into your project.

Try it: three small versions of what I build

Check a reply before it is sent, review a finished chat, or decide on an action an agent wants to take. Each one gives a real answer on this page.

These are simplified copies, running on sample rules and sample chats. They make no AI calls. What you type is not stored.

Pick an example or paste a reply your team might send. You will see what the check flags and the rewrite it offers.

In the real extension, only the agent's draft is sent for checking. Customer messages never leave the browser.

Risky

What's good: Identifies the reconnection requirement needed to resolve the issue.

What to fix:

  • Sounds dismissive
  • Blames the customer
  • Nobody takes ownership
  • Reads cold

Suggested rewrite:

I can help you get this reconnected. This happens when the local connection token resets rather than a platform outage, and I can walk you through reconnecting it right now so everything syncs cleanly.

How it reads, out of 10:

Empathy
2/10
Ownership
2/10
Clarity
9/10
Actionability
9/10
Professionalism
2/10
De-escalation
2/10
Conciseness
9/10

Want this on your team's real replies, with your tone and rules? A pre-send check is one of the builds in First Agent Live.

The full technical version, for engineers

Questions people ask first

What happens to our data?

I use the smallest slice of data that does the job. For a pre-send check that is the agent's draft, not the customer's messages. Before any build you get a one-page map showing what leaves your systems, where it goes, and which AI provider sees it. Where possible the AI runs on your own provider account, so your data stays under your own agreement. I will sign an NDA or a data processing agreement before seeing anything.

What does "human-in-the-loop" mean?

The AI drafts and a person decides. Nothing is sent to a customer, and nothing is sent, spent or changed in your systems, until someone on your team approves it. Every approval, edit and rejection is logged, so you can see how often the AI was right before you trust it with more.

Can the agents act on their own?

No. They prepare the work: they sort, draft, research and plan. A person approves anything that leaves your business or changes a record. More freedom comes one step at a time, and only after we have measured how often the agents were right.

How long does a project take?

The teardown takes 48 hours. The blueprint takes five working days. A standard first agent takes about three weeks, and an operations build about eight. You get the dates in writing with the price.

What does it cost to run afterwards?

You pay your AI provider directly for usage. I set spending limits as part of the build and tell you the expected monthly cost before you commit. If you want me to look after it, Keep It Running is $1,500 to $2,500 a month.

Which help desks do you work with?

Zendesk, Intercom and Zoho SalesIQ today. For anything else I do a short paid discovery first to check what the platform allows, then give you a fixed price.

Who does the work?

I do. I write the spec, the test cases and the checks myself, and I use AI coding tools to build faster. Every change is tested against your own examples before release. I work US Eastern hours.

Can you show client references?

Not yet for consulting. What I can show is my own product, live and public, and a demo you can try on this page. It is also why the first project is small and the price is fixed.

What if we need changes after handover?

Anything that does not match the agreed scope, I fix at no charge for 30 days. New features are quoted as a new fixed-price piece of work.

Fifteen minutes, and you will know if it's a fit.

Tell me what your team is dealing with. I will tell you whether I can help and what it would cost.

Book a 15-minute call

Prefer to write?

Send a short brief