Find where your policies contradict each other
A periodic sweep that reads all your policy documents together and flags where they contradict each other or have gone stale.
- How it works
- A periodic batch job reads the handbook, individual policy documents and intranet pages together and flags apparent contradictions and stale references: the handbook says expense claims within thirty days, the finance wiki says fourteen; the travel policy still names an employee who left. The output is a review list for a human, not automatic edits.
- Data you need
- All policy and process documents in text form, in one place. If they are scattered across personal drives and email attachments, collecting them is step one — and most of the work.
- What to expect
- A helpful sweep before your annual handbook review, not an audit: it will not find everything, and subtle conflicts spread across several documents can slip through, since coverage depends on how the documents are chunked and retrieved. Some flags will be false positives, because deliberate exceptions read like contradictions. Run it before onboarding season, when stale documents do the most harm.
- Where people stay involved
- A person adjudicates every flag — the model finds candidate conflicts but cannot know which version is the intended one.
Which model, and what it costs to run
Qwen3-8B
This job runs in bulk rather than to a waiting person, so size is not the constraint — we take the strongest independent score on sticking to the document that we may serve freely and that fits on a single card.
- Licence
- Apache-2.0
- Weights at 4-bit
- 5 GB
- Context
- 32K tokens
- Publisher
- Alibaba (Qwen Team)
What the hardware costs
One 48 GB card holds it
- Rent in the EU
- $1.60/hrScaleway, Paris (PAR2)
- Buy the card
- $7,569new, one-off
- Or rent it by the token
- $0.04 / $0.04per M in / out · DeepInfra
Hardware only, third-party prices from 2026-07. The figure excludes the KV cache, which grows with context length and how many people use it at once — sized properly in a conversation, not guessed here. Renting by the token is cheaper up front; why our customers still self-host is below.
Sticking to the document
Measured on public documents, by a model acting as judge. Read it beside the answer rate: the lowest hallucination rates on this board belong to models that simply decline more often.
Independent measurement · Vectara · board updated May 11, 2026
Reading a long document whole
No benchmark measures this
No current benchmark ranks today's open models here. HELMET showed that the popular test — finding a planted sentence — predicts nothing, and its own table has not been rerun on 2026 models.
So we do not show a chart here. We measure it on your own content, in the first week, and you see the result before anything ships.
The API is cheaper per token. Here is why our customers don't use it.
We will not pretend otherwise: renting a model by the token from a serverless API costs less per million tokens than a card we run for you. We show that price on every use-case page. What it does not include is the part a shop with a customer database actually pays for.
- 01
Your data never leaves hardware you can point at
A serverless "we don't retain your data" is a clause in a contract. Running the model on a card in Amsterdam is a fact of architecture: your catalogue, tickets and customer records are never sent to a third party at all. For a GDPR audit, that is the difference between a promise and a floor plan.
- 02
The price cannot move without your say-so
A serverless rate card is somebody else's lever. The provider can raise the price, retire the model, or change the terms, and your cost moves with it. The same model on the same card costs the same next year — you own the number.
- 03
The model cannot be taken away
Hosted APIs deprecate models on their own schedule; the one you built on can be gone in a quarter. An open-weight model on your own hardware runs for as long as you keep the lights on. No vendor can end-of-life it out from under you.
And the price gap closes with volume: past a card you keep busy — very roughly four billion tokens a month — owning is cheaper outright, even before the three reasons above.
Getting a case like this one from a conversation to production takes about two months, and you can stop at the end of any phase.
Also in hr & internal
All 14 →Let staff ask the handbook a question instead of asking HR
A private chat box that answers staff policy questions from your own handbook, with a link to the exact section. Runs entirely in Amsterdam.
Give every new starter an onboarding buddy that never gets tired of questions
New hires get answers about printers, approvals and processes from your own onboarding docs, with sources, instead of interrupting busy colleagues.
Search the shared drive by meaning, not by remembering the filename
Semantic search over your internal documents: staff describe what they need and find the right file, whatever it happens to be called.
Draft the job ad from a five-line brief
Turn a five-line role brief and a couple of past ads into a structured job-ad draft in your company's tone, ready for the hiring manager to edit.
Next
Tell us what your team does by hand
Describe the process that takes the most time. We will say plainly whether a model is the right tool for it.