Zentered Studios

Boulder, Colorado

Put AI to work.
In your business.

Work with Patrick Heneise to choose the right work for AI, connect it to your systems, and build the software to make it useful. Based in Boulder, Colorado. From the first architecture decision to the handoff, you work with the person doing the work.

Work with us See what we run

Why us

Company-wide adoption. Hands-on engineering.

Patrick spent four years building software at Nevados, a utility-scale solar tracker manufacturer, as Director of Software and then Director of AI & Platform. His work covered the software, the integrations, and the people expected to use them. Today, he brings that experience to client engagements and the products Zentered Studios builds and operates.

70+
people on Claude and our agent platform at Nevados
4
departments involved in the rollout
4 years
building software at Nevados

Services

Start with the work you need done

Help your team use AI, connect it to your systems, or build a product. If you need to decide where to start, book an advisory engagement with Patrick.

Help your team use AI

01

Claude Team setup

Get Claude Team configured around how your company works. In one day, we set roles and connector permissions, create company-specific guidance and a shared glossary, and hand your administrator a runbook for onboarding and offboarding. Up to 50 seats. Fixed at $3,000; Anthropic subscriptions purchased separately. See the day.

02

AI training for your team

Put AI to work on two workflows your team already does every week. The four-week pilot measures them before and after, develops an AI policy with your team, and leaves you with a 90-day plan. In-person training in Boulder County. Fixed at $6,500 for up to 10 people; workshops and larger teams of up to 50 on request. See the four-week pilot.

Connect AI to your systems

03

MCP workshop

Decide whether a custom MCP server is worth building. In one day, we examine your internal products, identify useful integrations, and draft the tools for the strongest candidates. You leave with a ranked recommendation your team can act on, including where not to build. In person or remote, up to 12 people. Fixed at $2,000. See the day.

04

MCP servers: design, build, audit

Give agents tools they can use correctly. We design and build MCP servers around the work your users need to do. For an existing server, we record about two weeks of real agent traffic with mcpsignals, identify misleading descriptions, misused tools, and missing capabilities, then ship the fixes. You get working changes, not a report left for your team to implement.

Build software and improve delivery

05

AI-native product development

Get your product from a scoped idea to working software, with Patrick responsible for architecture and delivery. We use the agent-assisted development process behind Roadbook: define the work, implement it, review it, and verify it in a real browser. We can build the product or deliver the first slice and hand your team the pipeline.

06

Agent pipelines for your team

Stop rebuilding the same instructions for every coding session. We turn recurring engineering work into Claude Code commands and agent workflows: bug triage, backlog preparation, implementation, review, and regression checks. The commands, skills, and runbook live in your repository, where your team can inspect, change, and run them.

Decide where to start

07

AI consulting

Decide where AI deserves engineering time before you commit to a build. Patrick reviews your workflows, architecture, and constraints, then recommends what to automate, what to keep human, and how to evaluate the result. Model choice, tool design, and cost per session serve that decision.

Bring the workflow that is slowing you down

Tell Patrick what your team is trying to do, where the work stalls, and your deadline. We will tell you whether we can help and scope the next step at a fixed price.

hello@zentered-studios.com

Fixed price

One day, one price

Make a build decision or get your team set up. A defined scope, a working session with Patrick, and a handoff your team can use.

MCP workshop

$2,000

  • 1 day, in person or remote
  • Up to 12 people
  • For the people who own your internal products

Decide what is worth connecting before you pay to build it. Patrick works with the people who own your internal products to find where handoffs stall, assess whether MCP is the right fit, and draft tools for the strongest candidates. You leave with a recommendation you can take to your own engineers or another supplier. No code is written on the day.

The day

  1. Morning

    How MCP servers work and what makes a tool easy for an agent to use, with examples from servers we run.

  2. Late morning

    Walk through each internal product with the people who run it, and find where work stalls between products.

  3. Afternoon

    Decide where an MCP server makes sense, and sketch the tools it would offer and which of them write data.

  4. End of day

    Rank the candidates by value and effort. Recommend a first build, or explain why none is justified yet.

You leave with

  • ✓ A map of your internal products, workflow bottlenecks, and potential MCP integrations
  • ✓ A draft tool list for the top candidates
  • ✓ A ranked recommendation your team can act on, including where not to build. An optional implementation quote is separate
Book and pay $2,000Book a 15-minute call

Pay by card or US bank transfer (ACH) through Stripe. Sales tax is added at checkout only if it is owed.

Claude Team setup

$3,000

  • 1 day, in person or remote
  • Up to 50 seats
  • You buy the seats from Anthropic

Give your team a shared starting point for using Claude on company work. Patrick configures roles and connectors, turns your company rules into reusable guidance, and builds a glossary from your internal terms. Your administrator leaves with the setup documented and a runbook to maintain it. Bring your workspace owner, company policies, and product terminology; buy your Anthropic seats separately.

The day

  1. Morning

    Set roles and permissions, and decide which connectors stay on.

  2. Late morning

    Write a company-guidance skill from your policies, including what requires approval before sharing.

  3. Afternoon

    Write a glossary skill from your product names, acronyms and internal terms.

  4. End of day

    Provision both skills organization-wide, check the setup, invite the team, and hand over the admin runbook.

You leave with

  • ✓ Roles and permissions set, and written down in an admin runbook
  • ✓ Company-guidance and glossary skills provisioned organization-wide and enabled by default
  • ✓ An invite and offboarding checklist for whoever manages seats
Book and pay $3,000Book a 15-minute call

Pay by card or US bank transfer (ACH) through Stripe. Sales tax is added at checkout only if it is owed.

Claude Team setup

Company context your team can reuse

Your policies and terminology should not have to be rewritten in every conversation. We turn them into two skills your organization can maintain centrally, with a clear owner and instructions for updating them.

Company-guidance skill

Make the rules part of the work

An employee asking Claude for help needs to know which information can be shared and which actions need approval. A policy in a separate document leaves that context out of the conversation.

We translate your existing policies into guidance for Claude: sensitive information, sharing restrictions, and actions that need a human decision. Your administrator can update the guidance centrally as the rules change.

What changes
  • ✓ Company-specific instructions for handling internal tools, source code, and customer information
  • ✓ Explicit approval points for publishing and external sharing
  • ✓ An editable skill your team owns, provisioned across the organization

Skills guide model behavior; they do not enforce access controls or guarantee confidentiality. Owner-provisioned skills are enabled by default, but users can disable them. We document those limits in the handoff.

Glossary skill

Give Claude the context your colleagues already have

Product names and acronyms carry meaning inside your company. Without that context, Claude has to guess, and someone has to correct the draft.

We build a glossary from your product names and internal terms, with plain-language definitions and guidance for customer-facing writing. Your team keeps the source file and can update it as products and terminology change.

What changes
  • ✓ A shared reference for new hires learning your terminology
  • ✓ Instructions to explain internal shorthand in customer-facing drafts
  • ✓ One maintained vocabulary instead of separate explanations in every chat

At Nevados, newcomers used the glossary to learn internal terminology, and colleagues used it when writing to customers. Drafts still need review.

Book and pay $3,000 Book a 15-minute call
Payment
Paid in full before the day, with an invoice for your records. Remote days cost the same as in person.
Travel
Included within Boulder County. Anywhere else is agreed in writing before we book. Out of state, we agree a travel budget in writing first.
Bigger teams, more days
Multi-day workshops and teams over the size limit are priced on request.

Send us the team size and the number of days, and we send back a fixed quote.

Request a quote

Experience

The work behind these services

Company-wide adoption at Nevados. Software and MCP servers we build and operate ourselves.

Nevados

70+ people in four departments

Patrick led the Claude and agent-platform rollout for more than 70 people across engineering, supply chain, sales, and operations. The work included HubSpot, Monday.com, and Salesforce integrations with sales and product management: adoption across business functions, alongside the technical implementation.

Nevados

Every acronym, explained

A glossary skill held the company's internal terms and acronyms. Newcomers used it to learn the language. People writing to customers used it too, so Claude could decode internal shorthand and write it out in words a customer understands.

Nevados

The company's first AI policy

Patrick wrote the first AI policy and the enablement program at Nevados. That experience informs the four-week training pilot: work on real tasks, measure the change, and develop a policy your team can use.

Our own servers

MCP servers we use every day

We build and operate the MCP servers behind Roadbook and Rivian MCP. Roadbook uses mcpsignals to record agent calls. That gives the workshop concrete examples of tool design and observed agent behavior, and gives our audits a method for finding what needs to change.

Patrick Heneise
“The interesting part was never the model. It was adoption, which means sitting with a team and learning which spreadsheet they actually open on a Monday.”
Patrick Heneise, Founder, Zentered Studios

Co-founder of BoulderJS. Writing software since 2000.

Book a 15-minute call with Patrick

In Production

What we run

We build our own products with the pipelines we sell. They are the reference implementation, not a portfolio.

Roadbook

Plan EV road trips to the wild places

Roadbook is an EV road trip planner for the US, Canada, and Mexico. It surfaces chargers, campgrounds, and national & state parks along your route - built for planning the trip, not navigating it.

  • ✓ Charger-aware every leg - drive times, fees, typical weather
  • ✓ Real, verified places - OpenStreetMap, NPS, Open Charge Map
  • ✓ Plan together - your crew drops suggestions on the map
  • ✓ Sign in with a free Bluesky account - nothing to post
Visit Roadbook

Standups for AI-driven development

GitMorning observes your GitHub activity and generates standups automatically. Observed, not reported. Continuous, not ceremonial, and built for AI-era development.

Not open for sign-ups. Join the interest list.

  • ✓ AI-generated standups from real GitHub activity
  • ✓ No self-reporting required
  • ✓ Developer profiles built from actual work
  • ✓ Blockers detected from issue labels
Visit GitMorning

See what your agents actually do with your MCP tools

mcpsignals is a drop-in library for Node and Python that records how AI agents actually use your MCP server - tool calls, errors, latency, and the agent's stated intent - into a database you already own. No account, no hosted service, no per-session pricing.

Response size costs as much as call count. A single bloated tool response can burn through a user's entire session budget while the server works exactly as intended. mcpsignals tracks payload size per tool, so oversized responses are visible before they cost you users.

  • ✓ Works with Node and Python - drop it into your existing server
  • ✓ Writes to your own Postgres, BigQuery, ClickHouse, or OTLP
  • ✓ Captures agent intent, not just call counts
  • ✓ MIT licensed and free - no per-session billing

Pairs naturally with OpenAPI-to-MCP generators like FastMCP, Speakeasy, Stainless, and Gram - they turn your API surface into tools, mcpsignals shows you which of those tools agents actually use.

View on GitHub

Rivian MCP

An open-source, read-only MCP server and CLI for Rivian vehicles. Battery, range, charging, and software updates, from Claude or straight from your terminal. MIT licensed, and strictly read-only: it never sends vehicle commands.

View on GitHub

About Us

Human-led, Boulder-rooted

Zentered Studios LLC is an independent software company in Boulder, Colorado, run by Patrick Heneise. We ship our own products and build for businesses and enterprises.

Agents do the implementation. You still talk to and work with a person, from the first call to the handoff.

GitHub