TREN

Human resources · Scope to be defined during discovery

AI System for Mapping Interview Notes to Competency Evidence

We design an AI system that reviews interviewer notes and the competency form together with their source and recency details. The system prepares a map of evidence and unanswered questions, but does not implement it as a final decision. If interviewer notes conflict, the suggestion does not proceed; the recruitment panel makes the final assessment.

Representative interview operations panel with a work queue, checks and an audit trail: interview evidence conflict queue — **Interview evidence conflict queue** Representative interface — contains no real data. Interview notes are anonymised. The panel does not produce a candidate score or selection decision.

The problem

In day-to-day operations, interviewer notes and the competency form arrive through different systems and files, preventing the team from reviewing the same case in one view.

As a result, the link to source evidence can be lost while a map of evidence and unanswered questions is prepared, leading to repeated checks and uncertainty about the basis for the decision.

Incomplete automation may overlook conflicting interviewer notes, while incorrect automation risks an AI interpretation being mistaken for a decision.

What we set out to improve

Time taken for the evidence and unanswered-question map draft to be ready for review
Correct routing of records with conflicting interviewer notes to the appropriate specialist queue
Record of suggestions corrected or rejected by the recruitment panel

How the system works

01 Retrieve interviewer notes and the competency form from authorised sources
02 Verify the source system, record identifier and recency information
03 Map the fields to the target process schema
04 Prepare the evidence and unanswered-question map draft
05 Compare the draft with business rules and source records
06 Check for an exception: interviewer notes conflict
07 Have the recruitment panel approve, revise or reject the suggestion
08 Write the input, suggestion, changes and final decision to the audit log

Methods we used

Source-traceable data extraction for interviewer notes and the competency form
Structured output that limits the evidence and unanswered-question map fields through business rules
An exception gate that separates cases with conflicting interviewer notes
A queue that shows the recruitment panel the source evidence and suggestion together
Duplicate-processing controls and a reversal record to reduce the risk of an AI interpretation being mistaken for a decision

Where people stay involved

The recruitment panel is the final decision-maker. The workflow pauses when interviewer notes conflict and presents the case to the specialists with its supporting records. The panel can revise or reject the suggestion, or stop the process.

Data and security

Only fields required for the task are processed from interviewer notes and the competency form. Source-system permissions are preserved, and personal or commercially sensitive data is minimised before being passed to the model. Every read, suggestion, human change and write to the target system is logged.

Who this suits

A good fit

Human resources teams that perform repetitive reviews
Companies with defined ownership for sources and approvals
Organisations that want exceptions to remain under human supervision

Not a good fit

Operations where source data is not current
Operations where the decision owner and reversal process are not defined
Operations where the existing method is sufficient for the low volume

Frequently asked questions

What data is used?

Interviewer notes and the competency form are used. The exact connections, fields and retention limits are defined during the access review.

How are exceptions handled?

The workflow pauses when interviewer notes conflict. The record is placed in the recruitment panel's queue with its source evidence.

How is incorrect automation controlled?

Because of the risk of an AI interpretation being mistaken for a decision, no final action is taken without human approval. The source, suggestion and human decision are recorded separately.

Project led by:DijitalPi

✦ PI ASSISTANT · ARTIFICIAL INTELLIGENCE

online

Ask the DijitalPi AI Assistant your question

No need to fill in a form and wait for a reply — write your question and let Pi, trained on DijitalPi's 20 years of know-how, answer within seconds.

Instant answers, 24/7
Service-specific context — no generic replies
Can connect you to a free consultation if you wish

Hi! 👋 I'm Pi — DijitalPi's AI assistant. Write whatever you'd like to know about AI System for Mapping Interview Notes to Competency Evidence and I'll answer right away.

Pi Assistant answers are for information purposes; for a proposal get in touch.

ASK AI ABOUT DIJITALPI

Let an AI explain what DijitalPi does.

Opens your chosen assistant with a ready research prompt. It reads the site live and answers.

ChatGPT Claude Gemini Grok Perplexity