> ## Documentation Index
> Fetch the complete documentation index at: https://docs.plaisolutions.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Answer Filters

> API endpoints for managing agent answer filters

## Create Answer Filter

<api-endpoint method="POST" path="/agents/{agent_id}/answer-filters" />

Add an answer filter to an agent. Answer filters help fine-tune the agent for specific queries by providing examples of good and bad responses.

### Path Parameters

<ParamField path="agent_id" type="string" required>
  The unique identifier of the agent
</ParamField>

### Request Body

<ParamField body="queries" type="array" required>
  Array of query strings that this filter should apply to
</ParamField>

<ParamField body="trigger_threshold" type="number" optional>
  Threshold value for triggering the filter (0.0 - 1.0, default: 0.5)
</ParamField>

<ParamField body="bad_responses" type="array" required>
  Array of examples of bad/unwanted responses
</ParamField>

<ParamField body="good_responses" type="array" required>
  Array of examples of good/desired responses
</ParamField>

### Response

<ResponseField name="id" type="string">
  Answer filter unique identifier
</ResponseField>

<ResponseField name="agent_id" type="string">
  ID of the agent this filter belongs to
</ResponseField>

<ResponseField name="trigger_threshold" type="number">
  Threshold value for triggering the filter
</ResponseField>

<ResponseField name="queries" type="array">
  Array of query strings this filter applies to
</ResponseField>

<ResponseField name="bad_responses" type="array">
  Array of bad response examples
</ResponseField>

<ResponseField name="good_responses" type="array">
  Array of good response examples
</ResponseField>

<ResponseField name="created_at" type="string">
  When the filter was created (ISO 8601 format)
</ResponseField>

<ResponseField name="updated_at" type="string">
  When the filter was last updated (ISO 8601 format)
</ResponseField>

<CodeGroup>
  ```bash cURL theme={null}
  curl --location --request POST 'https://api.plaisolutions.com/agents/agent_123/answer-filters' \
  --header 'Authorization: Bearer YOUR_TOKEN' \
  --header 'Content-Type: application/json' \
  --data-raw '{
    "queries": [
      "What are your refund policies?",
      "How do I return an item?",
      "Can I get my money back?"
    ],
    "trigger_threshold": 0.7,
    "bad_responses": [
      "I dont know about refunds.",
      "You cannot return anything.",
      "No refunds allowed."
    ],
    "good_responses": [
      "Our refund policy allows returns within 30 days of purchase with original receipt.",
      "You can return items in their original condition within 30 days for a full refund.",
      "We offer hassle-free returns within 30 days of purchase."
    ]
  }'
  ```

  ```javascript JavaScript theme={null}
  const agentId = 'agent_123';
  const response = await fetch(`https://api.plaisolutions.com/agents/${agentId}/answer-filters`, {
    method: 'POST',
    headers: {
      'Authorization': 'Bearer YOUR_TOKEN',
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      queries: [
        "What are your refund policies?",
        "How do I return an item?",
        "Can I get my money back?"
      ],
      trigger_threshold: 0.7,
      bad_responses: [
        "I dont know about refunds.",
        "You cannot return anything.",
        "No refunds allowed."
      ],
      good_responses: [
        "Our refund policy allows returns within 30 days of purchase with original receipt.",
        "You can return items in their original condition within 30 days for a full refund.",
        "We offer hassle-free returns within 30 days of purchase."
      ]
    })
  });

  const filter = await response.json();
  console.log(filter);
  ```

  ```python Python theme={null}
  import requests

  agent_id = "agent_123"
  url = f"https://api.plaisolutions.com/agents/{agent_id}/answer-filters"
  headers = {
      "Authorization": "Bearer YOUR_TOKEN",
      "Content-Type": "application/json"
  }
  data = {
      "queries": [
          "What are your refund policies?",
          "How do I return an item?",
          "Can I get my money back?"
      ],
      "trigger_threshold": 0.7,
      "bad_responses": [
          "I dont know about refunds.",
          "You cannot return anything.",
          "No refunds allowed."
      ],
      "good_responses": [
          "Our refund policy allows returns within 30 days of purchase with original receipt.",
          "You can return items in their original condition within 30 days for a full refund.",
          "We offer hassle-free returns within 30 days of purchase."
      ]
  }

  response = requests.post(url, headers=headers, json=data)
  filter_result = response.json()
  print(filter_result)
  ```
</CodeGroup>

***

## Get Answer Filters

<api-endpoint method="GET" path="/agents/{agent_id}/answer-filters" />

Get all answer filters for an agent.

### Path Parameters

<ParamField path="agent_id" type="string" required>
  The unique identifier of the agent
</ParamField>

### Response

<ResponseField name="count" type="integer">
  Total number of answer filters
</ResponseField>

<ResponseField name="has_more" type="boolean">
  Whether there are more results available
</ResponseField>

<ResponseField name="data" type="array">
  Array of answer filter objects

  <Expandable title="Answer Filter Object">
    <ResponseField name="id" type="string">
      Answer filter unique identifier
    </ResponseField>

    <ResponseField name="agent_id" type="string">
      ID of the agent this filter belongs to
    </ResponseField>

    <ResponseField name="trigger_threshold" type="number">
      Threshold value for triggering the filter
    </ResponseField>

    <ResponseField name="queries" type="array">
      Array of query strings this filter applies to
    </ResponseField>

    <ResponseField name="bad_responses" type="array">
      Array of bad response examples
    </ResponseField>

    <ResponseField name="good_responses" type="array">
      Array of good response examples
    </ResponseField>

    <ResponseField name="created_at" type="string">
      When the filter was created
    </ResponseField>

    <ResponseField name="updated_at" type="string">
      When the filter was last updated
    </ResponseField>
  </Expandable>
</ResponseField>

<CodeGroup>
  ```bash cURL theme={null}
  curl --location --request GET 'https://api.plaisolutions.com/agents/agent_123/answer-filters' \
  --header 'Authorization: Bearer YOUR_TOKEN'
  ```

  ```javascript JavaScript theme={null}
  const agentId = 'agent_123';
  const response = await fetch(`https://api.plaisolutions.com/agents/${agentId}/answer-filters`, {
    method: 'GET',
    headers: {
      'Authorization': 'Bearer YOUR_TOKEN',
      'Content-Type': 'application/json'
    }
  });

  const filters = await response.json();
  console.log(filters);
  ```

  ```python Python theme={null}
  import requests

  agent_id = "agent_123"
  url = f"https://api.plaisolutions.com/agents/{agent_id}/answer-filters"
  headers = {
      "Authorization": "Bearer YOUR_TOKEN",
      "Content-Type": "application/json"
  }

  response = requests.get(url, headers=headers)
  filters = response.json()
  print(filters)
  ```
</CodeGroup>

***

## Update Answer Filter

<api-endpoint method="PATCH" path="/agents/{agent_id}/answer-filters/{answer_filter_id}" />

Update an existing answer filter for an agent.

### Path Parameters

<ParamField path="agent_id" type="string" required>
  The unique identifier of the agent
</ParamField>

<ParamField path="answer_filter_id" type="string" required>
  The unique identifier of the answer filter
</ParamField>

### Request Body

<ParamField body="queries" type="array" optional>
  Updated array of query strings that this filter should apply to
</ParamField>

<ParamField body="trigger_threshold" type="number" optional>
  Updated threshold value for triggering the filter (0.0 - 1.0)
</ParamField>

<ParamField body="bad_responses" type="array" optional>
  Updated array of examples of bad/unwanted responses
</ParamField>

<ParamField body="good_responses" type="array" optional>
  Updated array of examples of good/desired responses
</ParamField>

### Response

Returns the updated answer filter object.

<CodeGroup>
  ```bash cURL theme={null}
  curl --location --request PATCH 'https://api.plaisolutions.com/agents/agent_123/answer-filters/filter_456' \
  --header 'Authorization: Bearer YOUR_TOKEN' \
  --header 'Content-Type: application/json' \
  --data-raw '{
    "trigger_threshold": 0.8,
    "good_responses": [
      "Our comprehensive refund policy allows returns within 30 days of purchase with original receipt.",
      "You can easily return items in their original condition within 30 days for a full refund.",
      "We offer a customer-friendly return policy with hassle-free returns within 30 days of purchase."
    ]
  }'
  ```

  ```javascript JavaScript theme={null}
  const agentId = 'agent_123';
  const filterId = 'filter_456';
  const response = await fetch(`https://api.plaisolutions.com/agents/${agentId}/answer-filters/${filterId}`, {
    method: 'PATCH',
    headers: {
      'Authorization': 'Bearer YOUR_TOKEN',
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      trigger_threshold: 0.8,
      good_responses: [
        "Our comprehensive refund policy allows returns within 30 days of purchase with original receipt.",
        "You can easily return items in their original condition within 30 days for a full refund.",
        "We offer a customer-friendly return policy with hassle-free returns within 30 days of purchase."
      ]
    })
  });

  const updatedFilter = await response.json();
  console.log(updatedFilter);
  ```

  ```python Python theme={null}
  import requests

  agent_id = "agent_123"
  filter_id = "filter_456"
  url = f"https://api.plaisolutions.com/agents/{agent_id}/answer-filters/{filter_id}"
  headers = {
      "Authorization": "Bearer YOUR_TOKEN",
      "Content-Type": "application/json"
  }
  data = {
      "trigger_threshold": 0.8,
      "good_responses": [
          "Our comprehensive refund policy allows returns within 30 days of purchase with original receipt.",
          "You can easily return items in their original condition within 30 days for a full refund.",
          "We offer a customer-friendly return policy with hassle-free returns within 30 days of purchase."
      ]
  }

  response = requests.patch(url, headers=headers, json=data)
  updated_filter = response.json()
  print(updated_filter)
  ```
</CodeGroup>

***

## Delete Answer Filter

<api-endpoint method="DELETE" path="/agents/{agent_id}/answer-filters/{answer_filter_id}" />

Delete an answer filter from an agent.

### Path Parameters

<ParamField path="agent_id" type="string" required>
  The unique identifier of the agent
</ParamField>

<ParamField path="answer_filter_id" type="string" required>
  The unique identifier of the answer filter to delete
</ParamField>

### Response

Returns a 204 status code on successful deletion.

<CodeGroup>
  ```bash cURL theme={null}
  curl --location --request DELETE 'https://api.plaisolutions.com/agents/agent_123/answer-filters/filter_456' \
  --header 'Authorization: Bearer YOUR_TOKEN'
  ```

  ```javascript JavaScript theme={null}
  const agentId = 'agent_123';
  const filterId = 'filter_456';
  const response = await fetch(`https://api.plaisolutions.com/agents/${agentId}/answer-filters/${filterId}`, {
    method: 'DELETE',
    headers: {
      'Authorization': 'Bearer YOUR_TOKEN',
      'Content-Type': 'application/json'
    }
  });

  console.log('Answer filter deleted:', response.status === 204);
  ```

  ```python Python theme={null}
  import requests

  agent_id = "agent_123"
  filter_id = "filter_456"
  url = f"https://api.plaisolutions.com/agents/{agent_id}/answer-filters/{filter_id}"
  headers = {
      "Authorization": "Bearer YOUR_TOKEN",
      "Content-Type": "application/json"
  }

  response = requests.delete(url, headers=headers)
  print(f"Answer filter deleted: {response.status_code == 204}")
  ```
</CodeGroup>

***

## Understanding Answer Filters

Answer filters are a powerful mechanism for improving agent responses through example-based learning. They work by:

<Steps>
  <Step title="Query Matching">
    When a user query comes in, the system calculates similarity scores against the filter's query examples
  </Step>

  <Step title="Threshold Check">
    If the similarity score exceeds the trigger threshold, the filter activates
  </Step>

  <Step title="Response Guidance">
    The agent uses the good/bad response examples to guide its answer generation
  </Step>

  <Step title="Quality Improvement">
    Over time, this leads to more consistent and higher-quality responses for specific topics
  </Step>
</Steps>

### Best Practices

<AccordionGroup>
  <Accordion title="Query Examples">
    * Include 3-5 different ways users might ask the same question
    * Use natural language variations and synonyms
    * Consider different levels of formality
    * Include common misspellings or abbreviations if relevant
  </Accordion>

  <Accordion title="Response Examples">
    * Provide 2-3 examples of ideal responses
    * Include 2-3 examples of poor responses to avoid
    * Make examples specific and detailed
    * Ensure good examples follow your brand voice and guidelines
  </Accordion>

  <Accordion title="Threshold Tuning">
    * Start with 0.5 and adjust based on performance
    * Higher thresholds (0.7-0.9) for very specific topics
    * Lower thresholds (0.3-0.5) for broader topic categories
    * Monitor and adjust based on activation frequency
  </Accordion>

  <Accordion title="Maintenance">
    * Regularly review and update filters based on new queries
    * Remove or modify filters that are no longer relevant
    * Add new filters for emerging topics or issues
    * Test filters with real user queries
  </Accordion>
</AccordionGroup>

### Use Cases

<CardGroup cols={2}>
  <Card title="Customer Support" icon="headset">
    Filter common support queries like refunds, shipping, or technical issues to ensure consistent, accurate responses
  </Card>

  <Card title="Product Information" icon="box">
    Standardize responses about product features, specifications, and availability
  </Card>

  <Card title="Policy Clarification" icon="file-contract">
    Ensure accurate communication of company policies, terms of service, or legal information
  </Card>

  <Card title="Brand Voice" icon="microphone">
    Maintain consistent tone and messaging across all agent interactions
  </Card>
</CardGroup>

<Note>
  Answer filters complement but do not replace comprehensive training data. They work best for fine-tuning specific response patterns rather than teaching entirely new knowledge.
</Note>

<Tip>
  Monitor filter performance through agent analytics to identify which filters are most effective and which may need adjustment.
</Tip>