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.
- How it works
- Your onboarding pack, IT how-tos and process documents are indexed with embeddings. A new hire asks the things they are embarrassed to ask a colleague for the third time — how to set up the label printer, who approves larger refunds, where the returns process is documented — and the system answers from the retrieved sections, citing the source document. Questions it cannot answer route visibly to a named person and are logged.
- Data you need
- Onboarding documents, IT setup guides, process descriptions and a who-does-what page. Most small companies have these half-written; the honest first step of the project is usually finishing them.
- What to expect
- It takes the repetitive lookups off the two people who know everything, and the log of unanswered questions becomes a useful map of your documentation gaps. The gaps in your documents become the gaps in the bot, and new starters tend to trust it — so review the indexed material before launch, because a wrong answer in someone's first week does real damage. It cannot judge whether the new hire is actually settling in.
- Where people stay involved
- A designated buddy or manager still owns onboarding. The bot handles lookups only; anything it cannot answer routes to a person, visibly.
Which model, and what it costs to run
Qwen3-8B
This job answers while someone waits, so latency comes first: we hold it to a single small card and, within that, take the best independent score on sticking to the document.
- 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.
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.
Build a structured interview guide from the job description
Feed in the job ad and get a draft interview plan: competency questions per requirement, follow-up probes and a shared scoring rubric.
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.