Main site

Education AI agent · Admissions

Admissions Assistant AI Agent

Read applications against published criteria with name, school and postcode withheld — because each can stand in for race — and hold every file for the admissions officer, who decides.

Typical delivery
4–6 weeks
Deployment
Your stack
Officer decides
Pre-decision
After launch
Agent Care

What this agent does

Prepares the read, not the decision

In

  1. 01

    Ingest applications, transcripts, essays and recommendations from supported admissions.

  2. 02

    Normalise transcript formats and field labels, and carry each fact forward with the document it came from.

Reason

  1. 03

    Withhold name, photograph, secondary school and postcode from the evaluative read.

  2. 04

    Summarise what the applicant has demonstrated against the criteria the institution publishes.

  3. 05

    Bind each line of the summary to a passage in the file, and mark what the file leaves ambiguous.

Decide

  1. 06

    Constrain the output against racial and ethnic descriptors.

  2. 07

    Route every file to the named admissions officer, and any aid question to the financial aid administrator.

Out

  1. 08

    Retain the criteria applied, the summary, the reviewer's correction and the release against the application.

  2. 09

    Execute write actions only inside the approval boundaries agreed during implementation.

Product statement

The agent proposes a reading; the admissions officer decides the outcome, and an aid determination stays with the financial aid administrator.

Example workflow

One application, file to read

  1. 1Application receivedApplication platform, admissions system, transcript service or SIS record
  2. 2Criteria assembledTranscripts, essays, recommendations and activity records, each with its source document
  3. 3Read proposedCriteria met, demonstrated strengths, open questions and confidence
  4. 4Eligibility checks runRedaction checks, output constraints on racial and disability content, criteria rules and confidence threshold

No human action required

Nothing is ranked or decided in the first four stages, and identifying fields are withheld before the read — the officer's lane opens at the confidence gate.

5DecisionSplits on the review threshold
Clear on criteria

Goes to the admissions officer to weigh.

Criteria unclear

Adds a second reader first.

Officer review

The file is held with its criteria, its evidence spans and the confidence.

Approve · Correct · Send to committee read

Approved — the read goes forward

  1. 6Admissions systems updatedOnly where write access and review policy allow it
  2. 7Read evaluatedCriteria consistency, reviewer corrections, redaction misses and errors found after a decision went out

Corrections

Every reviewer correction is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required

8 items

  • Rendering an admit, deny or waitlist decision.
    • Exercising professional judgement on need analysis or cost of attendance.
    • Granting and signing a dependency override.
    • Deciding that verification documentation is acceptable.

  • Automation boundary

    Agent acts unaided

    • ✓Check a file for completeness and list what is missing for the named owner.
    • ✓Send deadline and document-request reminders.
    • ✓Answer published policy.
    • ✓Deduplicate applicant records and normalise transcript formatting.

    Any write happens inside the boundaries agreed at implementation, never ahead of review.

    • Authorising or releasing a disbursement.
    • Weighing an applicant's own account of racial experience.
    • Applying or waiving a legacy, athletic or institutional preference.
  • Signing off the release of a decision or award batch.

Example output

One applicant read, annotated

Everything the agent proposes is attached to the file it was drawn from.

Admissions output · single application

Illustrative example
Application
Transfer applicant
Summary line
Held a term-time job through the programme and led the design team to a regional final
Fields withheld
Name · school · postcode
Source of record
Essay, as submitted
Confidence
91%
Race in output
No racial descriptor emitted

As received

Taken from the file as submitted and read after redaction — nothing on this side is decided by the agent.

Evidence used

  • Essay, as submitted
  • Transcript on file
  • Recommendation letter

Why this summary

It reports what this applicant did and a person still decides and it is logged..

What the score decides

Below the configured threshold the file picks up a second reader before it reaches the officer.

Action

ApproveCorrectSend to committee read

Value

Where AI adds value

The same four claims, placed at the point in the workflow where each one applies.

Where the value lands

Value 01 – 04

Every application

From the application file

03Reading

Read from the file

Postcode, school and name can each stand in for race with no protected field present — so the read never sees them.

01Approved path

Read every file the same way

Routine files arrive summarised against the criteria the institution publishes.

02Human review

Send the officer where it matters

Open questions, thin files and anything touching aid are marked, so a reader's time goes where a wrong call is expensive to unwind.

04

Build an evidence trail

Each read keeps the criteria applied and the reviewer who signed it.

Integrations

Typical integrations

Five system groups connect to the same agent. Which of them are in scope is decided in discovery.

  • Admissions systems

    • Slate by Technolutions
    • Ellucian Recruit

  • Application platforms

    • Common App
    • Coalition
    • Scoir

  • Institutional CRM

    • Salesforce Education Cloud
    • TargetX

Agent

Admissions assistance

  • Reads the file
  • Summarises to criteria
  • Holds for the officer

  • Verification and records

    • CampusLogic StudentForms
    • Parchment
    • Clearinghouse

  • Observability & evaluation

    • OpenTelemetry
    • Langfuse
    • Supported monitoring/evaluation sources

Integration availability depends on the client's existing systems and API access.

Agent controls

Six layers between the model and a decision

The layers nest. What each one misses is named in the map below it.

L6 · Outermost — last line of defence

Inward → L1 · closest to the model

L6Rollback / safe modePull the agent back to completeness checks only when evaluation or production signals degrade.Roll back
L5Version monitoringTrack model, prompt, criteria-rule and redaction-configuration changes.Track
L4TraceabilityRecord the file read, the criteria applied, the output, the reviewer and the time.Record
L3Officer reviewHolds the read for the named officer; it governs who decides, not whether a disbursed award can be pulled back.Gate
L2Policy guardrailsTest output against the redaction list and the bar on racial, ethnic and disability descriptors; a failure returns the read.Restrict
L1Confidence thresholdsRoute low-confidence reads to a second reader before the officer sees them.Require review
Model coreRead produced — criteria met, demonstrated strengths, open questions and confidence
L1 – L2
Test whether a read may stand
L3
Puts the decision in an officer's hands
L4 – L5
Show which criteria applied and when they changed
L6
Reverts to summary-only when signals degrade

How Nestack evaluates it

Evaluate the whole read path — not only the summary that reaches the officer.

Coverage runs the whole depth of the workflow, and every layer is cut by slice.

Surface — the read the officer sees

  1. E1Final-output evaluationDid every line of the summary rest on a passage in the file?
  2. E2Step-level evaluationDid the agent use the right file, criteria and redaction configuration?
  3. E3Tool evaluationDid it read the correct application and write to the correct record?
  4. E4Confidence calibrationDo low-confidence reads actually attract more reviewer corrections?
  5. E5Slice evaluationHow far apart do correction rates sit across specific applicant pools?
  6. E6Business outcomeHow many reads needed correcting, and how many surfaced only after a decision or an award had gone out?

Floor — the decision the applicant receives

Failure modes

Where each failure originates in the agent

Seven modes, each pinned to where it starts.

Agent lifecycle

Direction of processing →

  1. 01 · Retrieval

    1 mode

    • AZ-03

      Unredacted file retrieved

      The store returns the original, and the read sees name and address.

    Stage gathers

    Application, transcripts, with the source each came from

  2. 02 · Reasoning

    2 modes

    • AZ-04

      Race rebuilt from proxies

      Surname and school become a note about background.

    • AZ-06

      Judgement turned into a formula

      A pattern across earlier files is applied as an aid rule.

    Stage proposes

    Criteria met, demonstrated strengths and confidence

  3. 03 · Tool / write

    2 modes

    • AZ-02

      Disability note written to record

      Volunteered medical content lands in a structured field.

    • AZ-05

      Read written to the wrong file

      An update lands on another applicant's record.

    Stage writes

    Only where write access and approval policy allow it

  4. 04 · Output

    1 mode

    • AZ-01

      Claim the file does not support

      A summary line rests on no passage in the file.

    Stage returns

    The read the officer weighs and acts on

  5. 05 · Change / Version

    1 mode

    • AZ-07

      Mid-cycle regression

      A model change moves summary phrasing while a cycle is open.

    Stage tracks

    Model, prompt, criteria rules and redaction config

  • Sev-1 · an award or a decision written
  • Sev-2 · a wrong read reaches the officer
  • Sev-3 · source degrades, file routes to review
See the complete Education failure-mode catalogue

Affected slices

Overall correction rates can hide one pool

The metric is the share of reads a reviewer had to correct before the file moved on. Averaged over every application it looks small; concentrated in the pools whose files carry.

Slice performance — reported separately, not only in aggregate

Illustrative example
SliceFailure rateLiftLift vs. thresholdStatus
Files whose essays discuss race7.6%3.6×Review
Files disclosing a disability5.7%2.7×Review
Files needing professional judgement4.0%1.9×Watch
Files in none of these pools1.9%0.9×Normal

Bar: correction-rate lift vs. the all-application baseline · scale 0–4.0× · tick marks the 2.0× review threshold

2 of 4 slices over threshold

Evidence-linked improvement

First the test, then the release

A cycle is done when the failure has become a test the next release has to survive.

Improvement cycle · five stages

Switchback — the path turns at Improve and returns at Learn

  1. 01

    Detect

    Reviewer corrections rise in one applicant pool.

  2. 02

    Diagnose

    The files, the criteria version and the redaction log are read together until one of them explains it.

  3. 03

    Improve

    Version-stamp the change and attach the files that exposed it.

  4. 04

    Verify

    The affected cases run again, and a fail stops the release.

  5. 05

    Learn

    It becomes a standing test, and the review rubric changes with it.

  6. Learn → Detect

    The return edge. Detection next cycle is measured against the longer suite.

Typical build scope

Twelve workstreams across six weeks

The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, sources, reading workflow, evaluation, integration, then production validation and handover.

Workstream

Week 1Week 2Week 3Week 4Week 5Week 6

  1. 01Admissions workflow discovery and boundary definition.Week 1
  2. 02Application-platform and reader-tool assessment.Week 1, Week 2
  3. 03Published-criteria and redaction-rule mapping and rule mapping.Week 1, Week 2
  4. 04Application ingestion and transcript parsing.Week 2
  5. 05Reading logic and evidence-span binding.Week 2, Week 3
  6. 06Confidence scoring and second-reader routing.Week 3
  7. 07Admissions officer review.Week 3, Week 4
  8. 08Admissions- and CRM-system integration.Week 5
  9. 09Read-consistency cases.Week 4, Week 5
  10. 10Guardrails and review controls.Week 4
  11. 11Review-trail instrumentation.Week 5, Week 6
  12. 12Deployment, documentation and Agent Care handover.Week 6

12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallel

Final scope and sequence confirmed in discovery

Engagement tiers

What each tier includes

Rows are the capabilities named in each tier's scope. Higher tiers include everything below them.

Capability✓ in scope · — not at this tierPilotOne pool, one officeProductionProduction admissions systemsAdvancedMultiple campuses / systems
Introduced at Pilot
Reading to your published criteria✓✓✓
Officer review✓✓✓
Read-consistency baseline✓✓✓
Introduced at Production
Reporting by applicant pool—✓✓
Review workflow in your systems—✓✓
Approved write-back—✓✓
Application-system integration—✓✓
Introduced at Advanced
Multi-campus and multi-state rules——✓
Multi-stage committee review——✓
High application volume——✓
Enterprise review controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build price
Confirmed after discovery based on integrations, workflow complexity, application volume, review controls and deployment requirements.
Separate from build
Build pricing is separate from recurring Agent Care, which covers managed monitoring, evaluations, incidents and verified improvements after launch.

What we need from you

What you bring, and what we build with it

Each input maps to a piece of build scope and a week in the delivery timeline.

  1. 01Your published criteria and how they are applied

    Published-criteria mapping and read configuration

    Week 1

  2. 02Representative files from a past cycle

    Reading baseline, criteria extraction and evidence-span binding

    Week 2

  3. 03Your redaction list and where it has to hold

    Published-criteria and redaction-rule mapping

    Week 1

  4. 04Access to relevant APIs, feeds or exports

    Application, CRM and transcript assessment, then integration setup

    Week 2

  5. 05Reads that came out inconsistent

    Read-consistency cases and the evaluation suite

    Week 4

  6. 06What must reach a human reader before any decision

    Confidence scoring, second-reader routing, guardrails and review controls

    Week 3

  7. 07Named admissions officers to review reads

    Officer review workflow, then pilot and production validation

    Weeks 5–6

Nothing else is required

Deployment, documentation and Agent Care handover are ours.

Delivery timeline

Four phases across six weeks

Phases are drawn over the weeks they actually occupy, which is why week 5 doubles up rather than padding.

Phase

W1

W2

W3

W4

W5

W6

  1. DiscoveryW1
  2. BuildW2 – W3
  3. EvaluateW4 – W5
  4. Pilot & LaunchW5 – W6

Week focus

W1Admissions workflow discovery, criteria mapping and the automation boundary

W2Source integration and the reading baseline

W3Reading workflow, confidence logic and review controls

W4Evaluation suite, redaction checks and failure-mode testing

W5System integration, a pilot pool and targeted corrections

W6One application cycle read under the admissions office, then handover

Reading the band
A band spans the weeks its work is named in and no others. The doubled fifth week is real, not padding.
At the end of W6
The last checks clear on real applications and monitoring moves to Agent Care.
Duration
Six-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.

Next step · Education AI agent

Build an admissions assistant around your institution's review chain.

Show us your application platform, your published criteria and who reads a file. Your financial aid administrator names the point an aid question stops being data, and we map the review path from there, set the automation boundary and leave the decision with the officer.

Typical delivery
4–6 weeks
Deployment
Your admissions stack
Officer decides
Pre-decision
After launch
Agent Care available

Nestack Agents · Admissions assistance

AGT-ED-02 · Agent Care available after launch

Build an admissions assistant

Four questions so the call starts from your actual setup — then pick a time that suits you.

About you
Your applicants

No obligation. We’ll map the workflow, name the automation boundary and tell you if an agent is the wrong answer.