Confidential AI workspace
Draft replies, summarise notes, and review documents. Aizel detects identifying details on your device and swaps them for stand-ins — you see what will be sent before the AI does, and get the real names back in the answer.
For solicitors, therapists and counsellors, accountants — anyone who works under a duty of confidence.
Draft a reply to Daniel Whitmore — Hartley Family Law LLP will only settle the financial remedy if we accept £240,000 before Friday's FDR.
Draft a reply to Person A — Company A will only settle the financial remedy if we accept [amount 1] before [date 1] FDR.
See the stand-ins Aizel will send before anything leaves your browser.
Open the network tab to verify: only the swapped version is sent.
/ 001 /
Example data, real mechanics. Scroll through the three states — what you write, what the AI is allowed to see, and what you read back. In your workspace this happens automatically, on every job.
Email from Daniel Whitmore (d.whitmore@gmail.com): Hartley Family Law LLP are offering £240,000 to settle the financial remedy before Friday's FDR. Their solicitor, Ms Sinclair, won't move unless we answer the pension disclosure questions on Rowan Okafor today.
Identifying details detected on your device — nothing here has been sent anywhere.
Email from Person A ([email 1]): Company A are offering [amount 1] to settle the financial remedy before [date 1] FDR. Their solicitor, Person B, won't move unless we answer the pension disclosure questions on Person C today.
The model can still reason about the situation without knowing the real names — it never sees who you mean.
Waiting cuts both ways. Hartley Family Law LLP's push to settle before Friday's FDR — and their reluctance on pension disclosure — suggests they fear what full disclosure surfaces. That's leverage for Daniel Whitmore: the £240,000 opener likely has room.
Names restored on your device, before you read a word. The AI never saw them.
/ 002 /
Then you're doing what the careful half of every profession does. UK regulators are clear on the direction of travel: when AI is used, solicitors stay responsible for confidentiality, privilege, supervision and accuracy. The instinct to strip names before pasting is right — doing it by hand is the problem:
Names are the easy part. "A 32-year-old teacher at a Leeds primary school" identifies someone with zero names in it — ages, employers, amounts and places re-identify what you scrubbed.
The answer comes back full of blanks and initials, and you re-edit every name back in. Every prompt, every day. Aizel restores them automatically before you read a word.
Yesterday's "J.S." is today's "my client" is tomorrow's "John" — and the AI loses the thread. Aizel keeps the same stand-in across a whole workspace, so it reasons coherently about people it never meets.
/ 003 /
The Solicitors Regulation Authority warns that firms using AI must make sure their use of it protects confidentiality and legal privilege — and that solicitors "remain responsible and accountable for the outputs." SRA Risk Outlook →
In Munir v SSHD [2026] UKUT 81 (IAC), the Upper Tribunal warned that putting confidential documents into an open-source AI tool such as ChatGPT "is to place this information … in the public domain, and thus to breach client confidentiality and waive legal privilege." What it means →
Aizel changes what reaches the AI in the first place. Identifying details are detected and swapped for stand-ins on your device before anything is sent — you see what will go, and your workspace records exactly what left your browser. US litigation points the same way: a federal court found no attorney-client privilege in consumer-chatbot documents (Heppner, 2026), and a court order forced OpenAI to preserve even deleted chats (NYT v OpenAI, 2025). Aizel is a tool that reduces risk, not a certification — your professional obligations remain your own.
/ 004 /
Policies are promises. Topology is fact. We never ask for trust that structure can provide instead.
The model can still reason about the situation without knowing the real names. Thinking is hired; knowing stays home.
Every claim we make, you can verify yourself — starting with the demo above.
/ 005 /
Planned GBP launch pricing — free during private beta
Plans include a monthly allowance of work, metered honestly in credits. A quick draft or summary ≈ 4 credits. A full document review ≈ 13 credits. Heavy month? Top up — top-up credits never expire. Monthly allowances refresh each renewal. Cancel anytime, export everything.
Private beta is free. GBP pricing shown is planned launch pricing and may change before paid access opens. Beta reviewers use Aizel free on daily credits — no card, no contract.
/ 006 /
Aizel is in private beta. Two quick details — if it's a fit, we'll email you a one-click sign-in link.
No password to remember — if approved, you'll get a sign-in link by email.
/ 007 /
Don't take our word for it. The swap runs on your device — open your browser's developer tools and watch the network tab, or disconnect from the internet and keep typing. Only the swapped version is ever sent to the AI, and your workspace record shows you exactly what that was.
A question about "Person A" and "Company B." Requests run under commercial API terms, which do not permit training on your inputs — and because identities are swapped before sending, even retained text contains nothing that points to the people you work with.
Names you add to a workspace are protected deterministically — exact and close variants, guaranteed, not AI guesswork. Automatic detection covers the rest, and every message shows what was protected, so nothing happens silently.
Signed in, your workspace uses split-key encryption: the identity map is encrypted on your device, and the key that unlocks it lives with your account on our side. A thief holds your data without a key. We hold a key without your data. Neither side alone can read anything. (Honest limits: nothing protects against malware running inside your own logged-in browser — we won't pretend otherwise.)
Everything you do costs credits — a few for a chat message, more for processing a long document. Your plan refills monthly; top-ups never expire. There is no "unlimited" because honest metering beats hidden throttling.
No software can guarantee privilege, and we won't pretend otherwise. Aizel is built around the duties UK regulators highlight for AI use — the SRA's Risk Outlook on AI (confidentiality, privilege, supervision, accountability) and the Upper Tribunal's warning in Munir v SSHD [2026] UKUT 81 (IAC) that confidential material put into open AI can be treated as public. Aizel keeps identities on your device and gives you an exportable record of exactly what was sent. Your professional obligations remain your own.
Because removing names by hand isn't complete: quasi-identifiers (ages, employers, places, amounts) re-identify what you scrubbed. And it's one-way — you re-edit every name back into every answer, forever. Aizel swaps the identifying details completely, restores the real names automatically, keeps the same stand-ins consistent across a matter, and gives you a record. The habit you already have — without the tax.
It's the one question that separates architecture from marketing. If the answer is "on our servers," your client's raw text traveled there first — a no-training clause doesn't stop a breach, a bug, or a court order once it's there. Aizel's answer: in your browser, the identifying details are detected and swapped for stand-ins before anything leaves, on any material — and you can watch it happen in your developer tools.
Those are policy protections: contracts that say your data won't be trained on. Policies can be good — and they can be overridden, as the 2025 preservation order proved when even deleted consumer chats had to be retained. Aizel's protection is architectural: the swapped version is what's sent — you see it first — so there is far less to retain, disclose, or leak. You can use Aizel with a policy-protected account and have both.
Treat it like brilliant junior staff: excellent first drafts, summaries, and analysis — always reviewed by you before anything goes out. We design for that honestly: the Research brief deliberately returns topics to verify and where, never citations from memory, because fabricated citations are how AI embarrasses professionals — in Ayinde v Haringey [2025] EWHC 1383 (Admin) the High Court referred a lawyer to the SRA over AI-invented case citations. Your judgment is the product; Aizel just gives it more time.