JW
Dossier Sentinel
Hire me
Internal platform · Source private · Python
Built by Justin Willhite for Willhite Strategy Group

Sentinel: SEO, GEO and AEO observability, self-hosted.

Sentinel is a self-hosted SEO, GEO and AEO observability and opportunity-engine platform. It watches what humans search for, what LLMs say about a brand, what gaps exist between site claims and model beliefs, and what the corpus a business doesn't control is telling the world, then produces a ranked queue of concrete actions.

The source is private and Sentinel is internal to Willhite Strategy Group; there is no public repo or public dashboard to link.

01

Repo stats

Commit history and language mix, live hourly. The repo is private, so there is no star count.

283Commits
2026-05-06First commit
2026-09-28Last push
PythonPrimary language
02

Why I built it

The working thesis is what I call the Field Theory of Machine Confidence: the next moat in branding is not visibility, it is verifiability, surviving an audit conducted by an LLM acting as a fiduciary for the user. Sentinel is built around three consequences of that idea. A brand that says nothing about a topic doesn't read as "no known issues" to a model, it reads as a blank the model fills in from priors, so silence gets filled. Most of what a model believes about a brand is assembled from sources that brand doesn't own, so the corpus is the lever, not the campaign. And a multi-agent buyer convenes several lenses at once, engineering, legal, finance, security, marketing, and one weak lens can sink the whole verdict.

Sentinel and its companion system, Strider, are kept as two separate things on purpose: Sentinel observes, measures and reports, and Strider acts on what Sentinel finds. Anything that reads, measures, scores or renders is Sentinel; anything that writes, commits, deploys or closes is Strider. Keeping the two apart means Sentinel's report can be sold on its own, to a client who never has to let an agent near their site.

03

What it does

Three layers, from observe to operate.

  • Monitor. Site health checks, Google Search Console performance, AI-citation tracking across five LLM engines, rank tracking, bot crawl logs, PageSpeed Insights, schema audit, crawl audit, brand-mention monitoring, Bing Webmaster data, backlink authority, and a directory-presence check (Google Business Profile, Yelp, BBB and category-specific listings).
  • Analyze. Multi-engine AEO grading, a five-lens swarm cross-examination, silence-gap detection (site-stated facts vs. LLM-stated facts, side by side), source attribution across the third-party domains a model actually cites, and anomaly detection on search performance.
  • Act. A ranked queue of content briefs, scored from search-trend, competitor and AEO-gap signals, plus a corpus-shaping queue naming exactly which outside source to go influence next.
04

Stack and architecture

Python workers on a schedule, each one a small, focused job that reads or writes one slice of the picture, backed by Postgres. A Flask dashboard renders the combined view per property: health, search performance, AI citations, briefs, bot crawl, AEO grades, swarm verdicts, belief sources and silence gaps in one pane. A budget guard enforces a hard monthly spend cap per client before any paid LLM call runs, so a runaway job cannot produce a surprise bill.

PythonFlaskPostgreSQLsystemd timersOpenRouterSearXNG
05

Status

Live and running nightly against Willhite Strategy Group's own site portfolio and its active web-design clients. Internal only: there is no public dashboard or self-serve signup, and it is never pointed at a prospect on an ongoing basis.

06

FAQ

What is Sentinel?
A self-hosted SEO, GEO and AEO observability and opportunity-engine platform. It watches what humans search for, what LLMs say about a brand, what gaps exist between site claims and model beliefs, and what the corpus a business does not control is telling the world, then produces a ranked queue of concrete actions.
Who does Sentinel monitor?
Willhite Strategy Group's own web properties and its active web-design clients. It is not a public self-serve tool and it never runs against a prospect on an ongoing basis; a one-off prospect audit is switched off the moment it is delivered.
What does the swarm simulator do?
It cross-examines a property through five lenses, engineering, legal, finance, security and marketing, the way a real buying committee would. A single weak lens can sink the verdict even if the other four are strong, so Sentinel scores and reports each one.
What is source attribution, or belief sources?
A rollup of which third-party domains are load-bearing for what an LLM says about a brand, per property, prompt and engine. Most of what a model believes about a business is assembled from sources that business does not own, so this is the corpus-shaping action queue: which outside page, directory or article to go influence next.
Is Sentinel's output something a client can buy on its own?
Yes, by design. Sentinel is kept as the data and reporting engine on purpose, separate from any system that changes a site, so its report can be sold on its own to a client who never lets an agent near their code.

← Back to Work