Some parts of this page need JavaScript.

Skip to main content

Analytics only if you accept. Privacy

All work

Sales & Marketing / Case study

Overwatch

SEO and AI-search intelligence, with every change behind a human approval

Overwatch running
In production · Overwatch

In short

Overwatch is our self-hosted SEO and AI-search intelligence platform: it shows how a site is found in rankings, AI answers and local search, and holds every agent-proposed fix for human approval.

ResultIn production, with every proposed change approved by a person before it ships.

Status
In production
State
In production
Covers
Search, AI answers, local
Changes
Human-approved
Hosting
Self-hosted
Built with
TypeScript / React / PostgreSQL

Inside the project

01 / 03

Every proposed change with its evidence. Nothing runs until it is approved.

Application views are the Overwatch app run locally against seeded demonstration data; the figures are synthetic. Captured November 1, 2026.

Overwatch1 / 3

Overwatch approval queue with a list of proposed changes and the selected change's exact diff

Every proposed change with its evidence. Nothing runs until it is approved.

The brief

The problem

Buyers now find a business through AI answers, map packs and classic rankings, and each of those is measured in a different rented tool. The data sits in someone else's dashboard, the history leaves when the subscription does, and none of it connects to the work that would improve the site.

What we did

Our approach

We built our own platform and host it ourselves. It gathers search, analytics, local and page-experience signals for each site, and it tracks whether AI assistants mention and cite the business. An operator agent reads that data and proposes specific changes. Every proposal waits in a review queue that shows the exact change, so a person decides what ships.

Features

What it does

  • See search from more than one angle

    Traditional rankings, AI visibility and local search views answer different questions. Overwatch brings those perspectives into one place so operators can investigate how a site is being discovered.

  • Connect visibility to site health

    Core Web Vitals, search data and technical monitoring sit alongside the visibility reports. The workflow connects an observation in search to the website work that may need attention.

  • Run the checks repeatedly

    Background workers gather and refresh the data behind the reports. The self-hosted application supports ongoing operations across multiple sites rather than a single exported audit.

Results

What happened

  • In production and in daily use
  • Classic rankings, AI-search visibility and local presence in one view
  • Visibility connected to site health, so a drop points to the page that needs work
  • Agent-proposed changes held in a review queue until a person approves them
  • Data and history kept on our own servers

Questions

About Overwatch

What does 'AI-search visibility' mean here?

Whether AI assistants and AI search results mention the business and link to it, tracked over time next to classic rankings.

Can the agent change a live site on its own?

No. It proposes a specific change, and the change waits in a review queue until a person approves it.

Services

What this work shows we do

  • Digital marketing

    Search, ads and reporting tied to the leads they produce.

    Service page
  • Custom software

    Software built around how the business works, and run after launch.

    Service page
  • AI automation

    Models wired into the tools your team already uses, with logs and limits.

    Service page

Related work

Built with the same services

Other work of ours that shares this project's services.
  • JarvisMCP, running
    Developer Tools

    JarvisMCP

    JarvisMCP gives AI agents one governed door into our company systems: CRM, search intelligence, infrastructure, memory and coordination. Agents find the capability they need, act through it, and leave a record. They never hold the keys.

    Read the case study
  • ButlerCRM, running
    Business Systems

    ButlerCRM

    ButlerCRM keeps contacts, deals, email, calendar and tasks in one workspace that updates live for everyone in it. We rebuilt it on Elixir/Phoenix so changes appear for the whole team as they happen.

    Read the case study

How we work

How a change reaches production

The same five gates for our own products and for yours. Nothing reaches your customers on the strength of a demo.

  1. 01 · Isolate

    Its own branch and workspace

    Every change starts in a separate copy of the code, so work in progress never touches what is live.

    git worktree add .worktrees/your-change
  2. 02 · Build

    Engineers with AI agents

    Agents write and test code beside us. They hold no passwords: every call they make goes through our gateway, which checks it and logs it.

    agent → gateway → policy · audit · call
  3. 03 · Prove

    Evidence, then review

    Tests, before-and-after screenshots of the running app, then independent reviewers. It does not move on until no serious finding is left.

    review: 0 high · 0 medium → pass
  4. 04 · Ship

    Deployed and checked live

    The pipeline builds and deploys. Then we check the running service itself, not just a green build.

    replicas 1/1 · image sha matches · health 200
  5. 05 · Watch

    Checked every night

    Each integration we run is tested against its provider every night, so a changed API is caught before your team notices.

    nightly: each integration vs its provider

Want something built like this?

Tell us what your team does by hand and the tools involved. Digital marketing is where most projects like this start.