JobMojito
HomePublic pageAdmin app
HomePublic pageAdmin app
  1. Platform
  • Welcome
  • API keys creation
  • API usage and libraries
  • Vibe coding
  • Platform
    • Interview workflow
    • Interview scoring
    • Data privacy model
    • Custom web domain
  • Actions API
    • Client URL for new user
    • Client URL for existing user
    • Invite user
    • Interview result, details with transcript
    • Interview result, generate html/PDF report
    • Create interview, using position data
    • Create interview, using position data & candidate pre-screening
    • Create interview, using provided questions
  • Tables API
    • interview_def_set
      • /interview_def_set
      • /interview_def_set
      • /interview_def_set
      • /interview_def_set
    • interview_def_pre_screening
      • /interview_def_pre_screening
      • /interview_def_pre_screening
      • /interview_def_pre_screening
      • /interview_def_pre_screening
    • interview_def_question
      • /interview_def_question
      • /interview_def_question
      • /interview_def_question
      • /interview_def_question
    • interview_def_response
      • /interview_def_response
      • /interview_def_response
      • /interview_def_response
      • /interview_def_response
    • interview_file
      • /interview_file
      • /interview_file
      • /interview_file
      • /interview_file
    • interview_file_page
      • /interview_file_page
      • /interview_file_page
      • /interview_file_page
      • /interview_file_page
    • interview_result
      • /interview_result
      • /interview_result
      • /interview_result
      • /interview_result
    • interview_templates
      • /interview_templates
      • /interview_templates
      • /interview_templates
      • /interview_templates
    • interview_result_question
      • /interview_result_question
      • /interview_result_question
      • /interview_result_question
      • /interview_result_question
    • interview_result_pre_screening
      • /interview_result_pre_screening
      • /interview_result_pre_screening
      • /interview_result_pre_screening
      • /interview_result_pre_screening
    • knowledge_base
      • /knowledge_base
      • /knowledge_base
      • /knowledge_base
      • /knowledge_base
    • knowledge_base_store
      • /knowledge_base_store
      • /knowledge_base_store
      • /knowledge_base_store
      • /knowledge_base_store
    • knowledge_base_chunks
      • /knowledge_base_chunks
      • /knowledge_base_chunks
      • /knowledge_base_chunks
      • /knowledge_base_chunks
    • position_def_set
      • /position_def_set
      • /position_def_set
      • /position_def_set
      • /position_def_set
    • position_def_step
      • /position_def_step
      • /position_def_step
      • /position_def_step
      • /position_def_step
    • position_result
      • /position_result
      • /position_result
      • /position_result
      • /position_result
    • position_result_step
      • /position_result_step
      • /position_result_step
      • /position_result_step
      • /position_result_step
    • profile
      • /profile
      • /profile
      • /profile
      • /profile
    • profile_interview
      • /profile_interview
      • /profile_interview
      • /profile_interview
      • /profile_interview
  • Webhooks
    • Creating webhooks
    • Webhook: Interview submitted
  1. Platform

Interview scoring

Interview creation#

In JobMojito, interviews can be created in two ways:
1.
Automatically using a large language model. Based on the job title, job description, and additional metadata, the platform generates an
1.
interview sequence, ****a set of questions that will be asked by the avatar during the interview. These include test questions to ensure the candidate has at least a basic understanding of the field they’re applying for
2.
Candidate expectations, which are hidden criteria outlining what is expected from the candidate’s profile
2.
Manually, where recruiters define both the interview sequence and candidate expectations themselves.
candidate expectations.png
Sample candidate expectations

Customizing scoring weights#

Before publishing the interview, recruiters can customize the scoring weights for each algorithm that JobMojito runs. If a score is set to 0, that specific algorithm will not be executed for any candidate in the interview.
custom scoring.png
Variable Descriptions
Maximum Number of Attempts: Allows candidates to retake the interview multiple times.
Disable Retry When User Reaches a Score: When enabled with multiple attempts, this feature prevents further retries once the candidate achieves a specified score—helping candidates avoid unnecessary attempts for minimal score improvements.
Weights of Each Score Relative to Overall Score: Determines how much each individual score contributes to the overall result, letting you fine-tune the impact of each evaluated area.

Scoring#

This section is describing, how individual scores are calculated

AI analysis of full conversation#

Is LLM based scoring method that is executed, once full interview is completed
Input:
Position name
Position description
Candidate expectations
Full transcript of the interview
Output is score between 1 - 10 where
Score 1: for candidates that you would never hire based on their responses
Score 5: for average candidates or candidates that didn’t completed the full interview
Score 10: for candidates you would hire on the spot without any further testing
Purpose: To accurately assess how well the candidate aligns with the requirements of the job position.

AI analysis of individual answers#

LLM-based scoring is applied to each individual question and answer, ensuring precise evaluation of candidate responses.
Input:
Position name
Position description
Candidate expectations
Avatar question
Candidate response
Output is score between 1-5 (translated into score between 1-10)
Score 1: The answer missed the point
Score 2: Partially addresses the question but lacks key details
Score 3: Adequate and correct
Score 4: A strong answer that goes beyond the basic requirements of the question
Score 5: Demonstrates expertise, creativity, or exceptional depth
Purpose: To determine whether the candidate is answering each question accurately.

AI Resume analysis (turned off by default)#

This feature uses LLM-based scoring to evaluate the candidate’s plaintext resume against the job position.
Input:
Position name
Position description
Candidate expectations
Candidate resume
Output:
Score 0: Candidate doesn’t have any suitable experiences
Score 10: Candidate is amazing fit to the job position
Purpose: To incorporate pre-screening resume analysis into the overall interview score.
Note: Scoring accommodates entry-level positions across various fields, supporting candidates who wish to change their career path.

Speech sentiment#

This is a text-based assessment of the candidate’s answer, conducted for each individual response.
Input:
Text of the candidate answer
Answer language code
Output:
Sentiment between -1 and 1
Score 0: When sentiment is -0.2 or lower
Score 10: When sentiment is 0.3 and higher
Purpose: To detect whether the candidate uses profanity or provides generally negative responses.
External vendor: https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/overview

Speech pronunciation#

Audio analysis compares the candidate’s raw audio input against a native speaker’s voice profile. This analysis is performed for each of the candidate’s answers.
Input:
Candidate response audio data
Answer language code
Output:
AccuracyScore: Pronunciation accuracy of the speech. Accuracy indicates how closely the phonemes match a native speaker's pronunciation. Syllable, word, and full text accuracy scores are aggregated from the phoneme-level accuracy score, and refined with assessment objectives.
FluencyScore: Fluency of the given speech. Fluency indicates how closely the speech matches a native speaker's use of silent breaks between words.
CompletenessScore: Completeness of the speech, calculated by the ratio of pronounced words to the input reference text.
ProsodyScore: Prosody of the given speech. Prosody indicates how natural the given speech is, including stress, intonation, speaking speed, and rhythm.
Score: Overall score of the pronunciation quality of the given speech. Is calculated from AccuracyScore, FluencyScore, CompletenessScore, and ProsodyScore with weight, provided that ProsodyScore and CompletenessScore are available.
Purpose: To assess the candidate’s spoken language proficiency in comparison to a native speaker.
External vendor: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-pronunciation-assessment?pivots=programming-language-javascript

Speech cadence#

During speech-to-text transcription, the platform records the exact millisecond each word is spoken. This data is converted into an industry-standard words-per-minute score, calculated using a purely mathematical formula.
Input:
Words per minute data
Output:
Score 1: When words per minute is less than 80 or more than 220
Score 10: When words per minute is between 100-130
Purpose: To evaluate the candidate’s ability to produce naturally flowing speech.

Risk assessment#

After the interview is completed, an automated or manual review will determine if any cheating was detected during the process.
There are 2 types of risks
Potential, when certain issue could happened but it is can’t be confirmed for 100%
Confirmed, when certain issue is confirmed
The overall score will be reduced by the values listed in the table below.
Interview cheatScore reduction (when potential)Score reduction (when confirmed)
Answer whispering, when someone is whispering to the candidate the answers-1-4
Answer reading-0.25-1
Usage of voice assistant-1-4
Screen capture, using AI tool-1-4
Face swap-1-4
Candidate is not visible on the video-0.25-1
Typing-0.25-1
Stall tactics during interview-0.25-1
Asking to repeat a question multiple times-0.25-1
Multiple simultaneous interviews0-2
KYC failed-0.25-1
Too many failed attempts0-2
Multiple emails with the same name0-2

Independent testing#

In April 2025, JobMojito performed an thorough analysis on the final interview scoring.

Test setup#

Number of candidates 179
Each candidate went through the JobMojito interview process and an independent psychometric assessment.
The psychometric assessment score reflected the candidate cognitive abilities.
The JobMojito interview score, on the other hand, reflects the candidate's readiness for the job.
The system effectively evaluates candidate responses against predefined expectations and the specific job description. It takes into account the relevance, informativeness, and coherence of answers throughout the interview.
Both the psychometric assessment scores and JobMojito interview scores were divided into five categories (bins) for analysis. These bins were compared and further examined, with the key takeaways highlighted below.

Results#

psych_assesment_boxplot.png
psych_assesment_distribution.png

Key takeaways#

The score reflects the candidate’s readiness for the role.
It objectively evaluates candidate responses against defined expectations and the specific job description, considering the relevance, informativeness, and coherence of answers throughout the interview process.
There is a strong correlation between the psychometric assessment scores and JobMojito interview scores.
The JobMojito interview scores are clustered between 6.xx and 7.xx, which reflects the nature of the interview process. Candidates participated in a general position interview, answering questions that focused on their overall affinities in life rather than on specific domain expertise. This approach made it challenging for the LLM to assign lower scores, as all responses were informative, consistent, and directly addressed each question. Nevertheless, a clear trend emerges: candidates with higher cognitive ability consistently achieve higher interview scores.
This analysis enabled us to identify both overachievers and underperformers—candidates who excelled in the JobMojito interview but did not perform as well on the psychometric assessment, and vice versa.
Previous
Interview workflow
Next
Data privacy model
Built with