What kind of organizations do you work with?

Small and mid-sized businesses, nonprofits, and public-facing organizations, locally in Sonoma County and the SF Bay Area and remotely anywhere. If you have a search-visibility problem, an accessibility obligation, or work that software should be doing, that is the fit.

Do you only work locally?

No. Local clients we can meet in person, which some people prefer. Most of the work happens remotely, and we take on clients anywhere.

Can you do just one of these?

Yes. Each area stands on its own, and most people start with one thing: a search fix, an accessibility audit, one automation, or a site.

Do I need to understand AI to work with you?

No, that is our job. We will tell you where AI helps your business and where it is not worth the trouble, and we are not going to push you into doing AI for its own sake.

Do you take ongoing work, or only projects?

Both. Ongoing work is still defined work at a defined price rather than an open retainer. We keep a handful of clients at a time so each gets real attention.

What does the first conversation cost?

Nothing. Twenty minutes to understand the situation and see whether it is a fit. If it is not, we will say so.

Technical SEO · AEO · AI automation · WCAG 2.1 and 2.2 AA

We measure search visibility, build AI intake systems, and remediate sites and PDFs for WCAG.

That covers technical SEO and AI-answer measurement, intake automation, WCAG audits, and PDF remediation. When the site itself is the problem, we rebuild it.

Book a 20-minute call See the work

Live and clickable: an AI intake assistant you can use right now (running a demo business, so you can see it do the job), and the wcag21aa.com and wcag21aa.org reference sites we built and maintain.

What we do

Four questions, and the work behind each one

Search visibility: SEO and AI search

Does it show up when someone searches, and do AI assistants name it?

Technical and local SEO for Google, plus repeated AI-answer measurement and the content work that follows from it. We measure which businesses those tools name, change what is most likely to affect that, then run the same questions again.

Learn more → 02

AI integration and automation

Does every inquiry reach a person or a system that answers?

Intake assistants, data pipelines, and integrations between the systems you already pay for. They collect the details you define, at 9pm on a Saturday as readily as Tuesday morning, and route anything unusual to a person.

Learn more → 03

Accessibility and ADA compliance

Can a screen reader get through the site and the PDFs?

WCAG 2.1 and 2.2 AA audits and PDF document remediation. Checked by a person rather than a plugin, documented, with a conformance attestation on every file. No overlays.

Learn more → 04

Websites and landing pages

Is the site itself the thing holding the rest back?

Static builds that load fast and are accessible from the first commit. New sites, rebuilds, or repairs to the one you have.

Learn more →

Straight answers

Know the terms before you call, not after.

Scope and price agreed before anything starts. The same people from the first call to delivery. Real remediation instead of a widget that claims it. And documentation good enough that your team can run the thing without us.

See how we work

Working with us

What to expect

If you have paid for a website or SEO that never brought in work, or could not get a straight answer out of an agency, this is built against that.

You work with the people building it

The same people from the first call to delivery. No account managers, no handoffs, no subcontractor you never met.

We document the handoff

You get operating notes, ownership details, and training if the project needs it. If your team could not run it without us, it is not finished.

We say where AI is not worth it

Some of this work is better with AI in it and some is not. You get told which is which before you spend on it.

Recent work

Systems running in production

Live sites you can open, and written case studies on the systems behind them: what the problem was, how it was built, and what it does now. Every card says whether it is a live site, a screenshot case study, or a private system with no public URL.

Emissary AI intake assistant interface screenshot

Full-stack AI Engineer

Live, open it yourself

Emissary

Our flagship AI intake assistant. Use it yourself on a demo business.

Sonoma Solutions' flagship AI intake assistant. There is a working demo you can use: it runs a fictional Sonoma County HVAC company, answers questions from that company's knowledge base, collects the details a real job would need, refuses anything outside its rules, and hands back the summary the business would receive. The assistant at emissary.sonomasolutions.io answers questions about Emissary itself instead. Astro 4, React, and TypeScript on the frontend; Node and TypeScript backend modules for database access, a knowledge base, intake email parsing, lead routing, and downstream email integration. It is the productized version of the AI intake systems we build for clients.

Astro 4
React
TypeScript
Node.js

Read the case study →

MarketBrew Reference Manual documentation screenshot

Knowledge architect, AI engineer

Screenshot case study

MarketBrew Reference Manual

A structured knowledge base of evidence-tagged atoms, turned into an exhaustive client reference manual.

An exhaustive, client-ready reference manual for MarketBrew (a deep SEO analytics platform), generated from a structured knowledge base. We extracted MarketBrew’s public reference material into evidence-tagged "knowledge atoms" through a parallel multi-model pipeline, then built the manual from that vetted database under strict schema and QA gates.

Knowledge architecture
Knowledge-atom extraction
Multi-model pipeline
Technical documentation

Read the case study →

SRJC Course Outline Archive data table screenshot

Data Engineer

Screenshot case study

SRJC Course Outline Archive

Turned hundreds of unstructured catalog pages into a queryable archive.

Course outline data at a community college is public but not queryable: it lives in hundreds of individual web pages with no structured export. This pipeline scrapes and normalizes the full Santa Rosa Junior College catalog, extracting course codes, titles, units, objectives, and outcomes into a consistent archive built for curriculum research.

Node.js
Scraping
Structured extraction

Read the case study →

There is ongoing AI integration work for a local services firm (Light & Shade Solutions), plus the full case-study set and an open GitHub if you want to read the code.

See the full portfolio

How it works

How a project goes

We talk

Twenty minutes on the business and what is in the way. No pitch.

We map the fix

The two or three things worth doing first, with scope and price.

We build it

And keep you posted as it comes together. No black box.

We hand it off

Operating notes, ownership details, and training if you want it.

Common questions

Tell us what is in the way

Describe the problem and we will reply within one business day with whether we can help and the first thing we would do. The 20-minute call is free.

Book a 20-minute call