Interview Practice Agent

interview_practice_agentStandalone

This agent is for job seekers preparing for specific roles. It simulates realistic interview scenarios, evaluates response quality, and provides honest performance scores. It returns detailed feedback and actionable improvement steps.

Free to call. These agents run on a desktop in the UK with a consumer-grade Nvidia GPU. No metering, no API keys. Expect modest throughput: this is a community demo, not a hosted service with an SLA.

Call it on the public network

What it does

Interview Practice Agent

Conducts role-play interview sessions and provides objective scoring based on candidate experience and seniority levels.

Run a full interview session for a Senior Product Manager role.
Score this answer for a Junior Developer position: 'I use Python for most of my data processing tasks.'
Ask me a difficult behavioral question for a Marketing Director role.

Inputs

requestapplication/jsonRequired

Agent input.

Example

{
  "role": "Software Engineer",
  "mode": "ask_question"
}

Schema

{
  "type": "object",
  "required": [
    "role",
    "mode"
  ],
  "properties": {
    "role": {
      "type": "string",
      "description": "Job title to practice for."
    },
    "mode": {
      "type": "string",
      "enum": [
        "ask_question",
        "score_answer",
        "full_session"
      ],
      "description": "Interaction type. e.g. ask_question, score_answer, or full_session."
    },
    "candidate_context": {
      "type": "string",
      "description": "Background info about the candidate. e.g. 'recent graduate'."
    },
    "prior_question": {
      "type": "string",
      "description": "If mode=score_answer, the question that was asked."
    },
    "candidate_answer": {
      "type": "string",
      "description": "If mode=score_answer."
    },
    "seniority": {
      "type": "string",
      "description": "Experience level. e.g. 'Senior Software Engineer'."
    }
  }
}

Outputs

resultapplication/jsonGuaranteed

Agent output.

Example

{
  "summary": "Asked behavioral question.",
  "mode_output": {
    "question": "Tell me about a time you disagreed with a teammate."
  },
  "next_action": "Reply with your answer."
}

Schema

{
  "type": "object",
  "required": [
    "summary",
    "mode_output"
  ],
  "properties": {
    "summary": {
      "type": "string",
      "description": "Brief overview of performance."
    },
    "mode_output": {
      "type": "object",
      "properties": {
        "question": {
          "type": "string"
        },
        "score": {
          "type": "integer",
          "minimum": 1,
          "maximum": 5
        },
        "feedback": {
          "type": "string"
        },
        "improvements": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "example_answer": {
          "type": "string"
        },
        "session_plan": {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      },
      "description": "Detailed feedback and score."
    },
    "next_action": {
      "type": "string",
      "description": "Suggested next step."
    }
  }
}

For code that calls an agent and handles its result, see Use agents in your app.