Main site

Education AI agent · Advising

Student-Support & Advising AI Agent

Answer student questions from the institution's own published sources, route anything touching aid, immigration or wellbeing to the named professional, and keep each conversation on the record.

Typical delivery
4–6 weeks
Deployment
Your stack
Named hand-off
Source-cited
After launch
Agent Care

What this agent does

Answers the question, not the determination

In

  1. 01

    Ingest the catalogue, the aid policy pages and the registrar's deadline tables from supported SIS.

  2. 02

    Normalise each passage and carry it forward with its source and the date it was published.

Reason

  1. 03

    Answer from the institution's own published text, quoting the passage the answer rests on.

  2. 04

    Apply the scope, disclosure and redisclosure rules the institution sets under its school-official agreement.

  3. 05

    Emit answers a keyboard and a screen reader can reach — an answer a student cannot read is a discrimination problem.

Decide

  1. 06

    Detect a question that turns on aid, immigration status or a wellbeing disclosure, and stop answering it.

  2. 07

    Route those questions to the named aid administrator, designated school official or counsellor.

Out

  1. 08

    Retain the question, the source it drew on, the routing and the outcome against the case.

  2. 09

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

Product statement

The agent answers from published sources; the named professional decides anything turning on the student's own record, and the institution keeps direct control of that record.

Example workflow

One question, message to hand-off

  1. 1Question receivedStudent portal, chat, email or the advising queue
  2. 2Context assembledCatalogue passages, policy pages and deadline tables, each with its publication date
  3. 3Answer draftedPlain-language answer, the quoted passage, referral flags and confidence
  4. 4Controls appliedSource-currency checks, scope and disclosure rules, aid and wellbeing flags and confidence threshold

No human action required

The first four stages run unaided, and none of them applies a rule to the student's own record — the advisor's lane opens at the confidence gate.

5DecisionBranches at the confidence threshold
High confidence

Goes to the student with its source named.

Low confidence

Waits for the assigned advisor first.

Advisor review

The answer is held with its quoted source, its referral flags and the confidence.

Approve · Edit · Refer to the office

Approved — sent to the student

  1. 6Advising record updatedOnly where write access and approval policy allow it
  2. 7Outcome evaluatedEdit distance, referral outcomes, source currency and corrections made after the fact

Edits

Every advisor edit is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required

8 items

  • Determining or stating aid eligibility or an award amount.
    • Advising on visa status, work authorisation or course load.
    • Approving a withdrawal, a drop or a leave of absence.
    • Responding to a disclosure of self-harm, crisis or abuse.

  • Automation boundary

    Agent acts unaided

    • ✓Quote a published, dated policy or deadline with its source named.
    • ✓Explain a general process without applying it to.
    • ✓Book an appointment with the student's assigned.
    • ✓Route the student to the correct named office, with its hours for the named owner.

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

    • Exercising professional judgement or resolving a verification conflict.
    • Granting a requirement substitution, waiver or exception.
    • Releasing a student's record to a parent or a third party.
  • Placing a student on, or removing one from, an intervention caseload.

Example output

One answer, annotated

Everything the agent answers is attached to the passage it was drawn from.

Advising output · single question

Illustrative example
Question
Withdrawal date
Answer line
The published last day to withdraw from a full-term course
Stated deadline
Autumn census date
Source of record
Academic calendar
Confidence
93%
Routing
No referral triggered

As received

Taken from the academic calendar as published — nothing on this side is written by the agent.

Sources used

  • Academic calendar
  • Registrar deadline table
  • Catalogue policy section

Why this answer

It restates the published date and stops there and a person still decides.

What the score decides

Below the configured threshold the answer waits for the assigned advisor before the student.

Action

ApproveEditRefer to the office

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 question

From the student

03Answering

Answer from published sources

Draw on the catalogue, the aid policy pages and the registrar's dated deadline tables.

01Approved path

Answer without the wait

Routine published questions are answered as they arrive.

02Human review

Send the rest to a person

Aid, immigration and wellbeing questions are flagged and routed to a named person — the agent does not assess them.

04

Build an evidence trail

The question, the source it drew on and the routing stay with the case.

Integrations

Typical integrations

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

  • Student information systems

    • Ellucian Banner
    • Workday
    • Student-record APIs

  • Advising and success CRM

    • EAB Navigate360
    • Salesforce Education Cloud

  • Admissions and enrollment

    • Technolutions Slate
    • Element451

Agent

Student support and advising

  • Reads the sources
  • Answers the question
  • Routes to a person

  • Aid and identity

    • CampusLogic
    • Blackbaud
    • Okta
    • ClassLink

  • 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 the student

Each control wraps the one inside it. What a layer does not catch is named in the failure-mode map below.

L6 · Outermost — last line of defence

Inward → L1 · closest to the model

L6Rollback / safe modePull the agent back to referral-only when evaluation or production signals degrade.Roll back
L5Version monitoringTrack model, prompt, source-index and scope-configuration changes.Track
L4TraceabilityRecord the question, the source quoted, the flags, the routing and the advisor's edits.Record
L3Advisor reviewHold answers for the assigned advisor; it governs release, not whether a released answer is right.Gate
L2Policy guardrailsTest answers against scope and disclosure rules, and test that transcripts are not used for training, profiling, selling or advertising; a failure returns the answer.Restrict
L1Confidence thresholdsRoute low-confidence answers to the advisor before the student sees them.Require review
Model coreAnswer produced — plain-language reply, quoted source, referral flags and confidence
L1 – L2
Test whether an answer may stand
L3
Puts the release in an advisor's hands
L4 – L5
Keep the answer and its source reconstructable
L6
Pulls the agent back to referral only when signals degrade

How Nestack evaluates it

Evaluate the advising workflow — not only the answer that came back.

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

Surface — the answer the student reads

  1. E1Final-output evaluationDid the answer match the institution's published text?
  2. E2Step-level evaluationDid the agent use the current catalogue, policy page and deadline table?
  3. E3Tool evaluationDid it read the right record and write nothing it was not asked to?
  4. E4Confidence calibrationDo low-confidence answers actually attract more advisor edits?
  5. E5Slice evaluationHow does performance change across specific student groups?
  6. E6Business outcomeHow many answers needed an advisor edit or a correction after the fact?

Floor — the outcome the student lives with

Failure modes

Where each failure originates in the agent

Seven failure modes, placed at the stage each one originates.

Agent lifecycle

Direction of processing →

  1. 01 · Retrieval

    1 mode

    • GU-03

      Superseded source quoted

      Last year's catalogue or deadline table answers as current.

    Stage gathers

    Catalogue, policy pages, with the source each came from

  2. 02 · Reasoning

    2 modes

    • GU-04

      General rule read onto one student

      A published rule is applied to a record the agent cannot see.

    • GU-06

      Course-load advice to a visa holder

      A workload answer ignores the full-course-of-study condition.

    Stage proposes

    The answer, the quoted source and confidence

  3. 03 · Tool / write

    2 modes

    • GU-02

      Registration touched, not explained

      A call changes a registration the student only asked about.

    • GU-05

      Disclosure written to a shared note

      Wellbeing content lands where the whole office can read it.

    Stage writes

    Only where write access and approval policy allow it

  4. 04 · Output

    1 mode

    • GU-01

      Answer without a source

      A confident reply arrives with no passage behind it.

    Stage returns

    The answer the student reads and acts on

  5. 05 · Change / Version

    1 mode

    • GU-07

      Silent policy regression

      A policy changes mid-term and the source index is not rebuilt.

    Stage tracks

    Model, prompt, source index and scope config

  • Sev-1 · acts outside the boundary
  • Sev-2 · a wrong answer reaches a student
  • Sev-3 · source degrades, answer routes to review
See the complete Education failure-mode catalogue

Affected slices

Overall accuracy can hide one student group

The metric is the share of advising turns carrying a wrong institution-specific fact. In aggregate it holds steady; by group Nestack reports it by slice rather than in aggregate..

Slice performance — reported separately, not only in aggregate

Illustrative example
SliceFailure rateLiftLift vs. thresholdStatus
International students on a visa4.8%3.0×Review
Aid verification and appeals4.0%2.5×Review
Students using assistive technology2.4%1.5×Watch
Continuing full-time students0.8%0.5×Normal

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

2 of 4 slices over threshold

Evidence-linked improvement

A cycle ends with a new test

Nothing closes on an explanation. The cycle ends when the failure exists as a regression case the next release has to pass.

Improvement cycle · five stages

Switchback — the path turns at Improve and returns at Learn

  1. 01

    Detect

    Error rate rises in one student group.

  2. 02

    Diagnose

    The advising lead reads the conversations and the sources behind them until one cause survives.

  3. 03

    Improve

    The fix is written against a version, with the conversations that motivated it attached.

  4. 04

    Verify

    Release is blocked until the affected regression cases pass again.

  5. 05

    Learn

    The case joins the permanent suite and the advising playbook.

  6. Learn → Detect

    The return edge. The next detection runs against a suite one case longer.

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, advising workflow, evaluation, integration, then production validation and handover.

Workstream

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

  1. 01Advising workflow discovery and boundary definition.Week 1
  2. 02SIS, CRM and content source assessment.Week 1, Week 2
  3. 03Catalogue, policy and deadline source mapping.Week 1, Week 2
  4. 04Source ingestion and passage normalisation.Week 2
  5. 05Answering logic and source binding.Week 2, Week 3
  6. 06Confidence scoring and referral routing.Week 3
  7. 07Advisor review workflow.Week 3, Week 4
  8. 08SIS and advising-CRM integration.Week 5
  9. 09Response regression cases.Week 4, Week 5
  10. 10Guardrails and referral controls.Week 4
  11. 11Conversation-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 campus, one queueProductionProduction advising systemsAdvancedMultiple campuses / systems
Introduced at Pilot
Answering from your sources✓✓✓
Advisor review✓✓✓
Response-quality baseline✓✓✓
Introduced at Production
Reporting by student group—✓✓
Review workflow in your systems—✓✓
Approved write-back—✓✓
SIS integration—✓✓
Introduced at Advanced
Multi-campus policy sets——✓
Multi-stage advising approvals——✓
High conversation volume——✓
Enterprise advising controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build price
Confirmed after discovery based on integrations, workflow complexity, transaction volume, approval 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 catalogue, policy pages and deadline tables

    Source ingestion and passage mapping

    Week 1

  2. 02Representative advising conversations

    Answering baseline, source binding and scope extraction

    Week 2

  3. 03Your escalation list and the named offices behind it

    Escalation, scope and referral-rule mapping

    Week 1

  4. 04Access to relevant APIs, feeds or exports

    SIS, CRM and content assessment, then integration setup

    Week 2

  5. 05Conversations you would not want repeated

    Response cases and failure-mode testing

    Week 4

  6. 06Where an answer must stop and wait for the advisor

    Confidence scoring, referral routing, guardrails and review controls

    Week 3

  7. 07Named advisors to review held answers

    Advisor 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

Each phase sits on the weeks it actually occupies, and week 5 carries both evaluation and launch work.

Phase

W1

W2

W3

W4

W5

W6

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

Week focus

W1Advising workflow discovery, scope mapping and the automation boundary

W2Source integration and the answering baseline

W3Advising workflow, confidence logic and referral controls

W4Evaluation suite, accessibility checks and group error-rate testing

W5SIS integration, a pilot advising queue and targeted corrections

W6A live advising queue answered under review, then Agent Care handover

Reading the band
Bands sit on the weeks the work is named in and nowhere else. The doubled fifth week is real.
At the end of W6
Validation closes on live conversations, and Agent Care picks up monitoring.
Duration
Six-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.

Next step · Education AI agent

Build an advising agent around your institution's referral chain.

Show us your catalogue, your deadline tables and the offices a student gets referred to. Bring one question that went wrong last term, and we will map the routing, set the automation boundary and name what stays with the advisor.

Typical delivery
4–6 weeks
Deployment
Your SIS and CRM
Named hand-off
Source-cited
After launch
Agent Care available

Nestack Agents · Student support and advising

AGT-ED-01 · Agent Care available after launch

Build an advising agent

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

About you
Your students

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