ai
Cheap models, visible suggestions, human decisions
agHire uses AI where it saves you time, labels it wherever it appears, and never lets it act alone.
The rules AI follows here
Suggestions only
No automatic rejection, no AI text sent without a person, no final grade without someone confirming it.
Redacted first
Email, phone, address, date of birth and salary are removed before any model sees a resume or an answer.
Always labelled
Anything AI produced carries an “AI suggested” tag, in the colour agHire reserves for machine output.
Low-confidence goes to you
Below 60% confidence a suggestion is shown as “grade this yourself”, not pre-filled.
Low-cost routing
Defaults below; you can change the order per task. With your own key, tasks run on the providers you have a key for. Small typed judgements (a rubric score, a yes/no) run on the same models — or, where your company opts in, on TypeSafe Jev.
| Task | Default | Typical cost |
|---|---|---|
| Generate a 20-question assessment | DeepSeek through OpenRouter → Claude Haiku → DeepSeek | about 0.5¢ (DeepSeek through OpenRouter) · about 2.5¢ (Haiku) |
| Suggest a grade for a written answer | LLM decision (or Jev) | a fraction of a cent |
| Fill gaps in a parsed resume | LLM decision | a fraction of a cent |
| Summarise a debrief | Claude Haiku | under a cent |
Budgets and your own key
Set a monthly AI budget. At 80% owners are told; at 100% everything pauses except grading suggestions. On every plan, AI runs on your own key — OpenRouter, Anthropic, DeepSeek or OpenAI-compatible — stored encrypted, with only its last 4 characters ever shown again. Without a key agHire still works — assessments use built-in templates.
In some cases ArivuGuru switches on AI on its own key for a company, with a monthly cap we set. If that company adds its own key, its key is used instead.
Start with the free plan
One job, three teammates, 200 applicants a month. No card, no time limit.