01 / Web development
MaverickX
A website presenting chemistry across energy, mining and water treatment for a Y Combinator–backed company.
Visit the live website ↗CREATE SOMETHING .agency / Diagnose · Engineer · Learn
AI-native Technical support
Agents that do the work.
In the tools you already use.
We set up, connect and improve agents that carry out agreed work in your team’s tools. You see what they may access, review their outputs, and get ongoing technical support from people who know the project.
Support from $900/month Membership and costs ↗
The opportunity
Sharing an agent opens a conversation. Context makes it useful.
Using and sharing our OpenAI dots changed how we thought about helping others put agents to work. The next step is practical: connect the recipient’s tools and context, agree on permissions, and inspect the result.
Sharing an agent does not grant access to someone else’s private context or credentials. Each client setup needs its own approved access.
Selected work / inspect the evidence
Work you can
inspect.
From a customer-facing website to the checks behind a review. Explore what we built and where our work begins and ends.
02 / Tools & review workflows
Webflow review systems
Creator interfaces and evidence for human reviewers. The field report documents what worked, what failed, and what still needs judgment.
Read the work and its limits ↗Selected projects demonstrate our capabilities. Your deliverable, acceptance checks and support scope are agreed separately.
Inspect our engineering contributions ↗Explore the full work library Source, walkthroughs & project stories
Context → Permission → Work → Proof
An agent is the beginning.
The work starts with context.
We help turn an agent someone shares with you into a working path in your own environment. We confirm tool compatibility, connect or build the missing pieces, test the agreed task, and help your team use and improve it.
Watch canon explain · 26 seconds · silent
A possibility, then a practical setup.
canon meets someone new. Their context, tools and permission define the next step. An illustrative workflow takes shape, ready for human review and a receipt.
Concept illustration. The canvas sequence is staged; no client task or live agent run is shown. The complete explanation and buying paths below work without the video or character.
Playback starts only when you choose Play. The story stays still by default, including with reduced motion.
Download the silent video ↗Illustrative Draw workflow / no task has run
- 01
Request
“Map intake, review and delivery on this sample canvas.”
- 02
Permitted context
The sample steps and selected Draw canvas. No inbox, client records or database access.
- 03
Agent action
Add three named shapes and connect them in order. This is an illustrative task, not an observed run.
- 04
Review checkpoint
The owner inspects the sequence before sharing. Missing permission or unclear scope stops the work.
- 05
Output
An editable workflow canvas. A shareable canvas URL is a handoff, not a database connection.
- 06
Receipt
Record the request, allowed context, actions, output reference, review decision and open questions. A receipt alone does not prove correctness.
Start with one bounded workflow.
Bring one task, the tools involved and an example of a good result. We agree on access and scope, build the working path, check an example and a failure case, and hand over instructions and recovery steps.
What a checked handoff includes ↗Roll it out with your team.
Agree on owners, identity and tool access, data boundaries, approval points, budgets, evaluation cases and recovery before expanding the workflow.
Discuss team setup ↗Technical and governance detail
Instructions describe policy; host permissions and tool checks enforce authority. We confirm each integration’s availability and limits. Your team reviews the result before a separately agreed production promotion.
Ongoing technical support preserves project context, improves the agent and helps your team use it. Scope and response times are agreed before payment. Production incident response requires a separate managed Control agreement.
Read the Control boundary ↗Start with one task
What would you like working better?
Bring the tools involved and an example of the result you need. We’ll discuss fit, then agree on the work and how to check it.
Talk through your workflow ↗AI-native technical support membership
Choose the support your work needs.
Two plans for agreed improvements, with project context carried from one task to the next. Choose by the number of workstreams and the time your team needs.
Micah Johnson currently delivers the service. Meet Micah →
Focused and managed Control cover different work. Focused is $900/month for agreed improvements, learning and operator support. Managed Control starts at $900/month for agreed live operations after launch, under a separate agreement. Production incident response is not included in membership.
One workstream
Focused
$900/month
For one agreed workstream at a time, with diagnosis, engineering, learning and operator support.
- 2 × 30-minute check-ins each billing month
- 2 × 60-minute attended remote work sessions
- 1 agreed milestone with 1 feedback and revision round
- Skills, learning resources and Slack support
Up to two workstreams
Team
$2,500/month
For up to two agreed workstreams and more time working with your team.
- 2 × 30-minute check-ins each billing month
- 4 × 60-minute attended remote work sessions
- 2 agreed milestones across up to two workstreams, each with 1 feedback and revision round
- Skills, learning resources and Slack support
A milestone is one agreed workflow map or one scoped improvement to an existing workflow. It includes an acceptance check, verification and a handoff you keep. We agree on scope, session times, response times and any usage budget before payment. Cancel before renewal. Larger Builds, managed Control and production incident response need separate agreements.
You keep the agreed code, tests and instructions under your agreement, with reusable tools licensed for continued use. See how delivery works → What you keep →
From agreement to handoff
An agreed improvement.
A result you can keep using.
Both plans follow the same process. The difference is the agreed capacity each billing month.
01 / Before work begins
Make the milestone specific.
A milestone is one agreed workflow map or one scoped improvement to an existing workflow. We agree on the result, selected tool access, the human approval boundary, acceptance check, session times and response times before payment.
For example: map a handoff between two tools, or agree on one improvement to that handoff. These illustrate the scope of a milestone; a whole new build is quoted separately.
02 / Each billing month
Choose the capacity your work needs.
Focused · $900/month. 1 workstream, 1 agreed milestone and 2 attended 60-minute remote work sessions.
Team · $2,500/month. Up to 2 workstreams, 2 agreed milestones and 4 attended 60-minute remote work sessions.
An illustrative Focused month could map the approval handoff for your website. With Team, you might agree on that map plus one scoped improvement to an existing intake workflow. We confirm feasibility and acceptance checks before committing to either milestone.
Both include 2 × 30-minute check-ins and 1 feedback and revision round per milestone. Capacity and scope are agreed; neither plan is unlimited development.
03 / Check, then carry it forward
Keep the work understandable.
Each milestone includes verification and a handoff you keep under your agreement. The handoff records what changed, the actual check results, any blockers and the next step. We explain how to use the result. Skills, learning resources and Slack support are included; access is confirmed during onboarding.
Project context carries into the next agreed improvement. Larger Builds, managed Control and production incident response need separate agreements. AI usage, hosting and third-party services are budgeted separately.
Delivery and usage are separate
Know the cost before the work starts.
- Included in membership
- Agreed delivery work, guidance and support. Our everyday coding tools are our expense.
- Budgeted separately
- Project-specific AI development, testing and production usage, hosting and third-party services. You approve the budget first.
- Quoted before we expand
- Work beyond the agreed scope. More API credit does not add unlimited delivery capacity.
For substantial AI work, we arrange client-owned API access or agreed metered billing before starting. No API account is needed for work that does not use AI.
Before we begin
A few practical questions.
Agree on the work, keep what we build, and control the costs.
What does ongoing support mean?+
We keep project context across agreed work: the diagnosis, decisions, changes, checks and open questions. Scheduled sessions and Slack support follow your plan. Scope and response times are agreed before payment; production incident response requires a separate managed Control agreement.
Where do we start?+
Bring one task and an example of a good result. We agree on the deliverable, capacity, revisions and how to check the work before payment. If the task is unclear, start with a mapping session.
How do you check the work?+
We test an agreed example and a failure case. For AI agents—software that uses AI and connected tools to carry out a task—we agree on what AI may do and what needs approval. Your team reviews the result before launch. Launch and production incident response require a separate agreement.
What do we keep?+
After full payment, you own commissioned deliverables under your agreement, except reusable provider tools. You keep the instructions, tests, project history and recovery guide. We help your team use and maintain what we deliver. See Services for the delivery process and What You Keep for ownership and provider details.
How is AI spending controlled?+
For substantial AI development, testing or production, we arrange a client-owned provider project or agreed metered billing. Development and production have separate budgets. We pause new billable runs at the agreed limit until you approve more. A website or form that does not use AI needs no API account.
Can we cancel?+
Cancel before your next renewal by emailing [email protected] to stop future membership charges. Support continues through your paid period while we hand over your code and documentation, document open work, and plan the transition. If you need more help afterward, we’ll agree on the scope and price before extending support. Separately scoped projects follow their agreed terms.