Three things often get confused — the app, the engine, and the model. Once they are clear, most of our open questions answer themselves. No technical background needed.
Most confusion comes from treating these as one thing. They are not.
The raw intelligence — Claude, DeepSeek, a local model. It reasons and writes. It is interchangeable: you can swap it without changing anything else.
On its own it is a mind in a jar: it can think, but it cannot do.
Claude Code — the engine that gives the model hands and memory. It reads and writes your files, runs tools, keeps the Brain's knowledge up to date.
Runtime and model work together. This is what makes the Brain an assistant, not just a chatbot.
The web interface you actually use. Upload, voice, buttons, history, sharing. It is the room you meet the assistant in.
Each Brain runs in its own sealed box (Docker), so one client's data never touches another's.
Comparing the Brain to a chat window is comparing an employee to a phone call.
When you open Claude or ChatGPT in a browser, you get a model in a chat box: smart, but with no memory of your business, no access to your files, no ability to act. Every conversation starts from zero.
The Brain is the model plus the runtime plus your accumulated knowledge. It remembers your candidates, your projects, your way of writing. It can open a document, draft an email in your voice, update its own records. That value lives in the runtime and the memory — and it stays even if we change the underlying model.
The engine is powerful from a terminal. The business cannot live there.
Claude Code is, at heart, a command-line tool — excellent for a developer, hostile for everyone else. The web app exists because the things GR Work Tech actually needs are impossible or painful from a terminal:
The app is not a nicety. It is the surface on which the product becomes usable by a team and saleable to clients.
There is no single "best" model. There are trade-offs, and a plan.
| Model | Quality | Cost | Notes |
|---|---|---|---|
| Claude | Top for writing | high | Favourable pricing is temporary; login/auth is painful, especially inside a web app. |
| DeepSeek | Reasoning ~ on par | ~nothing | The pragmatic default for most work. |
| Local (on our GPU) | Lower ceiling | fixed | The compliance fallback — runs on hardware we control. |
The fastest way to give everyone every model is OpenRouter: one integration, one key, access to Claude, GPT, DeepSeek and the rest, selectable per task. That is why it wasn't wired in earlier on its own — it is not free. OpenRouter adds roughly a 5% surcharge on top of each provider's price. Small in itself, but pure overhead — and it does not change the real cost driver, which is which model runs underneath.
Real usage over 30 days, all three users aggregated, measured from both the chat database and the session logs:
One user drives almost all of it (heavy daily Claude use, large context re-read each turn); the other two are light. Benchmark: 3 Pro licences = $300/month. Each row below is the provider's most expensive model — the ceiling.
| Provider — top model | Real usage / month | vs $300 (3 licences) |
|---|---|---|
| DeepSeek V4 Pro client default | ~$188 | under |
| DeepSeek V4 Flash light / internal | ~$16 | 19× less |
| Grok 4.3 (xAI) | ~$260 | under |
| Gemini 2.5 Pro | ~$390 | over |
| Claude Sonnet 4.6 | ~$640 | 2× more |
| GPT-5.5 | ~$980 | 3× more |
| Claude Opus 4.8 | ~$1,065 | 3.5× more |
OpenRouter adds ~5% to any row (the teal sliver). Figures cost the measured token mix at each provider's rate; the dominant term is cached context — priced ~100× higher on Claude than on DeepSeek — which is what splits the chart.
A natural reflex: skip the API bill entirely and put a Claude subscription (Max, ~$100–200/mo) behind the platform. It looks free at the margin — and it is a closed door. A subscription authorizes one person, interactively, at their own terminal. Wiring its login token into the platform to serve many users is, in effect, reselling one personal subscription as a service — against Anthropic's terms, capped by a single shared rate limit, and a single point of failure the day they tighten it (which they are doing). It does not scale by construction. For a single heavy user it would be cheaper than metered Claude — but it stays blocked: you cannot share one login across the team, and DeepSeek is cheaper than both anyway.
The clean line is by usage mode, not by login mechanism:
A capability you add — independent of which model is running.
LinkedIn scraping, Outlook inbox reading, candidate presentation, job descriptions: these are skills. They live in the runtime layer and work the same regardless of the model behind them. Adding LinkedIn is not a model question — it is installing a skill. Outlook is the same kind of work, to be built.
This matters because it untangles a frequent knot: "the AI can't do X" is usually not the model being weak — it is a skill not yet installed.
Recruitment runs on personal data. Sovereignty is not optional, long-term.
Even if a cloud model is excellent and cheap, GR Work Tech handles candidate data — names, histories, contacts — under GDPR. For the most sensitive work, the data should be able to stay on hardware we control. That is why we keep researching a fully local fallback, accepting a quality ceiling in exchange for the data never leaving.
It only becomes economically sensible above a certain client base — the full analysis is here:
→ Scaling the local LLM server → Sovereign AI: architecture & economics → What the Brain is, technically
This page is the overview. Two companion documents go one level down — one on the architecture, one on the infrastructure.
How "how the Brain works" scales to a whole company. A company's brain isn't built top-down — it emerges from the union of the people's brains. Tested on a real three-person deployment.
The model and hardware question in full: dense vs MoE, prefix-cache, the ~200-user break-even between cloud and owning the iron, and what data sovereignty actually buys.
Short version, so nobody waits on a misunderstanding.