ROUTER
Sends each request to the right model and the right files.
Private AI · how it works
Your firm picks the model and owns it, with your own files ranked above anything it was trained on. Sidian sets up the deployment, wherever you want it, and runs the Sidian AI control layer around it inside DataGuard.
Sends each request to the right model and the right files.
Ranks your files above the model's own memory, and reads the reasoning while it forms.
Stops on an uncertain answer instead of writing it, and keeps the record of why.
One request. Three concurrent controls, never a pipeline.
The benchmark
The same open-weights model your firm owns, before and after the Sidian AI control layer, against the frontier models the legal AI tools run on.
GPQA Diamond · higher is better
Frontier and base-model scores are OpenRouter's own evaluations, one fixed question set put through each provider's live endpoint on 17 September 2026. The lift is Sidian's published figure for the control layer on that same model.
Fits on one machine you control. Frontier models are reported to carry trillions.
Decided while it answers, against your files.
That takes a 27-billion-parameter model your firm owns past Claude Opus 5 and past GPT‑5.6 Sol. So the question is not which model is cleverest. It is whose building the work happens in.
Where it lives
Most of what passes between a firm and its client is confidential, and some of it is privileged. None of it has to leave the firm for the AI to be useful.
You own the weights wherever it runs. The machine is dedicated to your firm and closed to the internet, and nothing dials out except the connectors you approve.
For a file shared through a connector you approved, DataGuard records where it went, the policy it applied and what it changed. When a client or your carrier asks what went out, that is a record rather than a recollection.
Here is the same question asked twice. Once to a generic AI tool with no access to your files, once to your firm's own AI connected to your real documents.
Router · 01
This tool never saw the real Doe v. TechCorp document set. Those exhibit numbers could be right or invented, and nothing in the answer tells you which.
This would go straight into a filing unless someone happened to check every exhibit by hand.
Every exhibit number is checkable, because it only pulls from what is actually in the case.
Grounding · 02
No matching case in any real record. This is the problem behind reported incidents like Mata v. Avianca: a citation with nothing real behind it.
This would go straight into a brief unless someone happened to check it by hand.
Arbitration compelled under FAA §4. Found in your firm's connected case law research index, so you can open the source and check it yourself.
Caught automatically, every time, because it checks a real index before answering.
Governance · 03
This tool never saw the real clause 7.2. The number could be right or wrong, and nothing in the answer tells you which.
You would only catch this if a person happened to reread the whole clause by hand.
The clause on file says $500,000. This rewrite says $50,000. Flagged before it reached you.
Caught automatically, every time, because it checks the real file first.
The comparison · 04
Harvey and Spellbook are genuinely useful, widely adopted legal AI tools. The difference is not which one writes better. It is where your data goes, whose model it runs on, and what happens when the AI is not sure.
| Harvey | Spellbook | Your private AIDelivered by Sidian | |
|---|---|---|---|
| Where your data goes | Processed on Harvey's cloud infrastructure | Sent through GPT‑5, Opus and other outside model providers | Stays on one machine dedicated to your firm, in your building, in your own cloud, or run for you by Sidian. Closed to the internet except the connectors you approve |
| Whose model it runs on | OpenAI, Anthropic and Google models routed on Harvey's platform, plus its own model post-trained on an open-weight base | The third-party frontier models Spellbook connects to | The open-weights model your firm chooses, owned by the firm whoever is running the machine it sits on |
| Hallucination rate, independently published | Not published at the task level, per public reporting | Not published, per available public sources | No independently audited rate, and the benchmark published above is not one either. Every answer shows its source, so the thing you rely on is the citation and not the score |
| Who checks the answer | The model checks its own work. Harvey states its system hallucinates less than the underlying foundation model, but does not publish how that check happens or how well it holds up | Not documented as a separate, independent check | The reasoning is read while the answer forms, and a step that drifts off your documents is corrected before the sentence is written, rather than a second pass grading a finished draft |
| Risk of an ungrounded frontier model on legal questions | A 2024 Stanford study found general-purpose AI models, used directly on real legal questions with no independent source check, gave an unsupported or incorrect answer 58 to 88% of the time depending on the model. This describes the risk of using a frontier model raw, not a published number for Harvey or Spellbook's actual product | Your own files outrank the model's training data, and an answer drifting off them is caught while it forms. This is a substantial reduction in that risk, not a claim to have removed it | |
| When the AI is not sure | Not documented as a separate, visible control | Not documented as a separate, visible control | It says so and holds for your review rather than committing, at a strictness threshold your firm sets |
| What you can show about one privileged file | Not documented publicly at the file level. Harvey states it does not train on customer data and requires zero data retention from its model providers | Not documented publicly at the file level. Spellbook states it holds zero-data-retention agreements with OpenAI and Anthropic | A hash-chained record of every file that left through a connector you approved, naming the rule that applied and what it changed |
| If you ever switch tools | Your work stays on Harvey's platform | Your work stays on Spellbook's platform | Your model and your data leave with you |
Neither Harvey nor Spellbook publishes an equivalent to the Sidian AI control layer, with Router, Grounding and Governance running as separate, visible controls. The comparison above is about what each platform documents publicly, not a claim about what happens inside either one.
Book a short call with Ben, Sidian's founder. Bring a real question from a live matter and watch the answer come back with its source attached. No slides.
15 minutes, no commitment.