Get Results

This API involves getting the result items created by AI

Get Results

This is the final call in the main API process flow.

• Retrieve all AI-generated items related to a specific protocol.
• This includes protocol metadata, agenda items, and task items.
• The getResults docs can be found here.

Overview

• Use the getResults query to fetch all AI-created results for a given protocol.
• If creationDone is false, the creation process is still ongoing.
• You can check the current creation progress in the creatingStep field of ApiProtocolType.

Example GraphQL Query

fragment protocolDetails on ApiProtocolType {
  slug
  name
  date
  language
  empty
  creatingStep
  status
}

fragment agendaDetails on ApiAgendaItemType {
  id
  classType
  title
  depth
  maxDepth
  metaData
  textList
  resolutionList {
    resolution
    decision
  }
  createdAt
  updatedAt
}

fragment taskDetails on ApiTaskType {
  id
  text
  date
  assignedTo
  done
  createdAt
  updatedAt
}

query GetResults($protocolSlug: String!) {
  getResults(protocolSlug: $protocolSlug) {
    creationDone
    protocol {
      ...protocolDetails
    }
    agendaItemList {
      ...agendaDetails
    }
    taskItemList {
      ...taskDetails
    }
  }
}

Example JavaScript Implementation

import axios from "axios";

export const GET_RESULTS = `...`; // GraphQL query from above

export async function getResults(protocolSlug) {
  const queryData = {
    query: GET_RESULTS,
    variables: { protocolSlug },
  };

  try {
    const response = await axios.post(
      process.env.VUE_APP_GRAPHQL_API,
      JSON.stringify(queryData),
      {
        headers: {
          "Content-Type": "application/json",
          "x-api-key": process.env.VUE_APP_API_KEY,
        },
      }
    );

    const result = response.data.data.getResults;
    const { creationDone, protocol, agendaItemList, taskItemList } = result;

    return { creationDone, protocol, agendaItemList, taskItemList };
  } catch (error) {
    console.error("Error fetching results:", error.response?.data || error.message);
    throw error;
  }
}

Notes

• You can poll this query periodically until creationDone becomes true. Set the interval to around 3 minutes. Usually it takes 40% of the audio length to process the whole data.

• The creatingStep field shows which phase the AI is currently processing.

• AgendaItem.textList has different detail levels. For summary the correct textList looks the following: ”{“0”: […]}“. For politics the correct textList looks the following: ”{“0”: […], “1”: […], “2”: […]}“.

• An agendaItem.textList value can also be empty - it then has the following content: ”{}“. This means that the AI was not able to map it to the given file content.

Next steps

The core API process flow is complete: you can go from an audio or video file to a fully generated protocol based on the AI-generated or your own agenda, including the content for each agenda item.

Optional API calls let you further modify the generated content, access the underlying data used to create the agenda items, or delete individual files or entire protocols.

Have questions?

Still have questions? Talk to support.