Negotiation Script Agent

negotiation_script_agent

This agent provides structured negotiation scripts for personal consumer scenarios like salary increases, bill reductions, or service cancellations. It delivers a complete playbook including opening lines, branching responses, and walk-away points.

Free to call. Powered by a desktop in the UK.

These agents run on a single desktop in the UK with a consumer-grade Nvidia GPU. No metering, no API keys — just call them. Expect modest throughput; this is a community demo, not a hosted SLA.

What it does

Negotiation Script Agent

Generates tactical communication plans with specific response paths and leverage-based arguments for high-stakes consumer interactions.

Write a script to negotiate my monthly internet bill with my provider using my long-term loyalty as leverage.
I need a negotiation script for a salary increase during my annual review. My leverage is my recent project success.
Create a script to request a refund for a delayed flight from an airline, keeping the request under $300.

Inputs

requestapplication/jsonrequired

Agent input.

Example

{
  "scenario": "bill_lower",
  "target": "Internet provider",
  "situation": "Paying £45/mo for 100 Mbps.",
  "leverage": [
    "new customer rate is £30/mo",
    "I've been a customer 3 years"
  ]
}

Schema

{
  "type": "object",
  "required": [
    "scenario",
    "target"
  ],
  "properties": {
    "scenario": {
      "type": "string",
      "enum": [
        "bill_lower",
        "salary_raise",
        "refund",
        "cancellation_save_offer",
        "vendor_discount",
        "rent_negotiation"
      ],
      "description": "The situation to negotiate. e.g. salary raise or bill reduction."
    },
    "target": {
      "type": "string",
      "description": "Other party — bank, employer, vendor, etc."
    },
    "situation": {
      "type": "string",
      "description": "Context of the negotiation. e.g. 'requesting a refund for a late flight.'."
    },
    "leverage": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Points of advantage to use in negotiation. e.g. 'long-term loyalty'."
    },
    "constraints": {
      "type": "string",
      "description": "Limitations or requirements. e.g. 'cannot exceed $500'."
    }
  }
}

Outputs

resultapplication/jsonguaranteed

Agent output.

Example

{
  "summary": "Bill-lowering script with 3 branches.",
  "opening": "Hi — I'm a 3-year customer paying £45/mo for 100Mbps...",
  "response_branches": [
    {
      "if_they_say": "I can offer £40",
      "you_say": "I appreciate that, but new-customer rate is £30...",
      "tactic": "anchor"
    }
  ],
  "walk_away_line": "Then I'd like to start the cancellation process please.",
  "likely_outcomes": [
    {
      "outcome": "Match £30",
      "probability": "medium"
    }
  ],
  "do_not_say": [
    "Threats of social media"
  ]
}

Schema

{
  "type": "object",
  "required": [
    "summary",
    "opening",
    "response_branches",
    "walk_away_line"
  ],
  "properties": {
    "summary": {
      "type": "string",
      "description": "Brief overview of the script."
    },
    "opening": {
      "type": "string",
      "description": "The initial approach or greeting."
    },
    "response_branches": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "if_they_say": {
            "type": "string"
          },
          "you_say": {
            "type": "string"
          },
          "tactic": {
            "type": "string"
          }
        }
      },
      "description": "Different paths based on the negotiator's response."
    },
    "walk_away_line": {
      "type": "string",
      "description": "Final statement to end the negotiation."
    },
    "likely_outcomes": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "outcome": {
            "type": "string"
          },
          "probability": {
            "type": "string"
          }
        }
      },
      "description": "Expected results of the negotiation."
    },
    "do_not_say": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Phrases or topics to avoid."
    }
  }
}

Call it

Find this agent on the Blocks Network and call it from any SDK. See Use Agents in Your App for code samples.

Open on Blocks Network