Talent Acquisition
AI Interview Scheduling for Lever
Coordinates interview times with candidates and panels, connected natively to Lever so it reads and updates postings, opportunities and interview panels.
Talent Acquisition
AI Interview Intelligence
Interview transcripts summarized into evidence against your scorecard, so panels compare candidates fairly.
After a round of interviews, panels often compare candidates from memory and scribbled notes, and the loudest opinion wins. This build transcribes each interview and lays out what the candidate actually said against your own scorecard criteria. Every panel member reads the same structured evidence before the debrief. It never scores or rejects anyone. The hiring decision stays entirely with your people.
- Every interview transcribed and mapped to your own scorecard criteria
- Panels debrief from shared evidence instead of personal recollection
- Alerts flag interviews that deserve a closer second look
$3,900
20–30 working days
Optional maintenance $249/mo
What it is
AI Interview Intelligence transcribes interviews and summarizes the evidence against your scorecard, so every panel member sees the same structured notes rather than fragmented personal impressions. It delivers by email, Slack or a web dashboard. It is checked against your own past interviews before launch, and final hiring decisions always stay with your team.
Why businesses buy it
A bad hire is expensive, and many start with a debrief where nobody can quite recall what the candidate said. Notes vary by interviewer, criteria get applied unevenly, and strong people are passed over for reasons no one can explain later. This build gives every panel the same evidence, organized by the criteria you already use, so decisions are fairer and easier to defend. The Scope Card lists the data sources, the criteria count and the delivery channel before you order, so you know precisely what arrives and what stays with your team.
Problems this solves
Panel members remember the same interview in very different ways
Interviews are transcribed and the evidence is summarized against your scorecard. Every panel member works from the same structured notes rather than their own partial memory.
Interviewers take notes instead of listening to the candidate
Because the transcript and summary are produced for them, interviewers can focus on the conversation. Structured notes arrive afterwards by email, Slack or a web dashboard.
Debriefs drift into opinion with little evidence on the table
Each summary ties what the candidate said to your scorecard criteria. Debriefs can start from evidence, while the final hiring decision always stays with your team.
A good fit if
Interview panels currently compare candidates from memory or scattered personal notes rather than a shared record.
You already use a structured scorecard with defined criteria you want evidence mapped against.
You record interviews today, or are ready to, and want that recording turned into something usable afterwards.
You want recurring visibility into interview quality and consistency across roles, not a one-off analysis.
Not the right fit if
You need applications screened before there is an interview to analyze. See AI Resume Screening.
You need interview times coordinated, not the interview content analyzed. See AI Interview Scheduling.
You need candidates found and contacted before interviews are even scheduled. See AI Candidate Sourcing.
You need more than three data sources or more than 25 tracked metrics. Add a note at checkout for a Change Quote.
How it works
- You connect the interview data. Up to three read-only sources, such as your interview recording tool and ATS, feed the transcription and analysis.
- You define the scorecard. The up to 25 criteria your panels already score against become what evidence gets mapped to.
- It learns your baseline. At least three months of your historical interview data sets the pattern for what a strong or weak answer looks like on your scorecard.
- Each interview is transcribed and mapped to the scorecard. What the candidate said is summarized as evidence against each criterion, not just a raw transcript.
- Panels get a shared, structured summary. Delivered by email, Slack or a web dashboard, so every panel member compares the same evidence, with up to five alerts for interviews worth a closer look.
- You review and refine before launch. Two rounds of changes let you adjust which criteria the summary emphasizes and how evidence is presented.
What you provide within 72 hours
Your portal lists these the moment you order. Delivery starts the working day after everything is in and your access is checked.
- Read-only access to your interview recording tool and ATS.
- Your existing interview scorecard and its criteria.
- At least three months of historical interview data to set the baseline.
- The list of report recipients and the delivery channel for summaries.
- Admin access and API keys for every connected system, shared by adding our team as a user or creating a key you control, never by email.
- Your business information (company basics, hours and brand voice), shared during intake.
- One decision-maker who can approve the scorecard mapping and alert thresholds.
- An API key for your own AI model account (for example OpenAI or Google Gemini), created for this build with a spending limit.
The 72-hour rule. Send everything on your checklist, including access, within 72 hours of ordering so your build starts on time.
Timeline
Start
Intake verified and your interview scorecard confirmed.
Weeks 1–2
Interview data connected and transcription-to-scorecard mapping built.
Week 3
Summary format, alerts and the recurring report configured.
Weeks 3–4
Results checked against three months of your historical interview data.
Week 4
Your review and two rounds of changes to scorecard mapping and layout.
Go-live
Live, recorded handoff session held, and 30 days of support begins.
| Option | Delivery time | Price |
|---|---|---|
| Standard | 20–30 working days | $3,900 |
| Express | 15–25 working days | $4,600 |
| Rush | 10–20 working days | $5,250 |
What you receive at handover
- AI Interview Intelligence connected read-only to up to three data sources
- Interview summaries structured against your scorecard, delivered by email, Slack or web dashboard
- One recurring report or dashboard plus up to five alerts
- Test report with output checked against your own past interviews
- Admin guide and a recorded handoff session
- 30 days of post-launch support
Expected benefits and how to measure them
- Can make debriefs shorter and more focused on evidence
- Helps interviewers give candidates their full attention
- Makes it easier to compare candidates on the same criteria
- Time from final interview to decision
- Compare the average days from last interview to hiring decision, from your hiring records, before and after launch.
- Debrief length
- Note the length of debrief meetings for a few roles before launch and similar roles after.
- Scorecards completed with evidence
- Spot-check a monthly sample of scorecards for written evidence against each criterion.
Before you start: For a few recent roles, record days from final interview to decision and debrief length. Keep sample scorecards for comparison.
These are things to track, not promised results. Outcomes depend on your data, your team and your market.
Running costs
The build is a one-time price. Running it afterwards costs roughly $20 to $150 a month for AI model usage and hosting or scheduler fees, billed directly in your own accounts. Build and test usage follows the same rule, so every provider relationship stays yours.
Ask about running costsCustom requirements
If you need a fourth data source or more than 25 scorecard criteria tracked, add a note at checkout. You get a written Change Quote before any extra work starts. Larger or bespoke projects go through the Custom AI request form instead.
Request a custom versionKeep it running
We recommend monthly maintenance: monitoring, fixes and monthly hours for changes, enough to update the scorecard mapping when your criteria change for a role. The change hours scale with the build. Maintenance starts after the 30 days of included support.
$249/mo (the minimum fee, includes 2 change hours)
Optional. Starts after the post-launch support period. Cancel any month.
How maintenance worksHow this compares
| Do it yourself with a SaaS tool | Hire a custom agency | Upmark Labs | |
|---|---|---|---|
| Price | An interview intelligence platform charges a monthly seat fee per interviewer | A custom interview analysis build is quoted after discovery calls | Ours is one fixed price, shown before you buy |
| Scope | A generic platform ships default competency templates you must adapt | An agency agrees scope as the project develops | Ours is mapped to your own scorecard, on the Scope Card before purchase |
| Delivery | Self-serve interview intelligence tools still take weeks of scorecard setup | An agency project usually runs several weeks, set per project | Ours has a fixed delivery time shown before you buy, with faster options |
| What panels see | Many tools return a raw transcript panels must read in full | An agency build depends on what was specified | Ours summarizes evidence mapped directly to your scorecard criteria |
Questions about this product
Does AI Interview Intelligence score or decide on candidates?
No. It transcribes interviews and summarizes evidence against your existing scorecard criteria, so panels can compare candidates on the same structured basis. It does not assign a pass or fail itself and does not make the hiring decision. Final decisions always stay with your interview panel and hiring team.
How does AI Interview Intelligence differ from AI Resume Screening?
AI Resume Screening scores applications before an interview happens. AI Interview Intelligence analyzes what was actually said during the interview itself, mapped against your scorecard. They cover different stages of hiring, both come with 30 days of support, and many teams use one to feed the other as their process matures.
What interview data does it need access to?
Up to three read-only sources, commonly your interview recording or video conferencing tool plus your ATS for scorecard data. You grant read-only access, so nothing changes in your source systems. At least three months of historical interviews sets the baseline before live use.
How much does AI Interview Intelligence cost to run each month?
Roughly $20 to $150 a month for AI model usage and hosting or scheduler fees, paid directly in your own accounts. The figure depends on interview volume and recording length. There is no separate ongoing platform fee from Upmark Labs, and the build itself is paid once.
Is interview recording and transcript data handled securely?
Yes. Access credentials are shared by adding our team as a user or creating a key you control, never sent by email, and connections to your recording tool and ATS are read-only. Summaries go only to the recipients and channel you named. PII redaction and data retention configuration are available as add-ons for sensitive candidate data.
Can we update the scorecard criteria for a new role?
Yes. Updating the mapping for a role within the 25-criteria limit fits inside the monthly change hours that come with maintenance. Expanding past that limit or adding a fourth data source is a larger change, quoted as a Change Quote before that work starts.
How accurate are the interview summaries before we rely on them?
We check results against three months of your own historical interview data before launch, so you can confirm the summaries reflect what panels actually observed. Two rounds of changes let you adjust how evidence is weighted or presented against each scorecard criterion before going live.
Can we cancel the AI Interview Intelligence maintenance after launch?
Yes, plans bill monthly with no lock-in and can be cancelled for any coming month. The 30 days of support included with the build continue regardless of whether you take a plan. If you cancel, summaries keep generating on the existing configuration until you change something yourself.
Give every panel the same evidence, not scattered notes.
Order AI Interview Intelligence and your interviews are transcribed and mapped to your scorecard, on a delivery date fixed before you pay. The Scope Card above is exactly what you get.
Works well with
Talent Acquisition
AI Interview Scheduling for Workable
Coordinates interview times with candidates and panels, connected natively to Workable so it reads and updates jobs, candidates and stages.
Talent Acquisition
AI Interview Scheduling for Greenhouse
Coordinates interview times with candidates and panels, connected natively to Greenhouse so it reads and updates jobs, candidates, applications and scheduled interviews.