Sustainability-Reporting Copilot AI Agent

What this agent does

Assembles the evidence, not the sign-off

Ingesting meter data, fuel and invoice records and factor sets from supported energy, ERP or data-platform sources.

Normalising units, periods and site names, and carrying each datapoint forward with the record it came from.

Reason

Assembling the workpaper behind each figure — source record, method, factor version and period.

Applying the framework mapping, boundary and consolidation approach the organisation has configured.

Reconciling each total against the prior period and writing the movement against the datapoints that moved it.

Decide

Marking a market-based figure with the instruments it rests on and whether they have been retired.

Routing the assembled figure and its narrative to the named preparer for acceptance.

Out

Retaining the datapoint, the method, the preparer's amendments and the acceptance in the workpaper.

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

→ Product statement

The agent assembles the basis; the named preparer decides what is signed, and the organisation stays the reporting entity.

Example workflow

One figure, meter read to sign-off

AgentHuman

1Datapoint receivedMeter record, fuel or invoice line, factor set or an ERP extract

2Basis assembledSource record, period, boundary, method and factor version, each named

3Figure proposedFigure, movement, dual basis and confidence

4Controls appliedTraceability checks, the configured mapping rules, instrument checks and confidence threshold

No human action required

Stages 1 to 4 run unaided, and nothing is filed or published at any of them — the agent is assembling evidence, and the preparer's lane opens at the confidence gate.

5DecisionBranches at the confidence threshold

High confidence

Goes to the named preparer to accept.

Low confidence

Adds a data-owner check first.

Preparer sign-off

The figure is held with its source record, its method and the confidence.

Accept · Amend · Send to data owner

Accepted — released to report▼

6Reporting systems updatedOnly where write access and approval policy allow it

7Outcome evaluatedAmendment rate, restatements, evidence gaps and findings raised on review

Amendments

Every preparer amendment is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required8 items

Publishing or filing a disclosure of any kind.

Signing off a figure or a restated prior total.

Making an environmental marketing claim of any kind.

Deciding that a framework applies to the entity.

Automation boundaryAgent acts unaided

✓Collect each datapoint with its source record and method.

✓Apply the framework mapping the organisation has configured.

✓Reconcile against the prior period and explain the movement.

✓Hold the assembled workpaper for the named preparer.

Any write happens inside the boundaries agreed at implementation, never ahead of sign-off.

Changing a method, a boundary or an emissions factor.

Retiring or allocating a market-based instrument.

Stating a carbon-neutral or offset-based position.

Changes to mapping, thresholds or approval rules.

Example output

One figure in the workpaper, annotated

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

Disclosure output · single datapointIllustrative example

Site

Datapoint

Value

Source of record

Confidence

Method

Northern network depot

Purchased electricity for the reporting period

412,600 kWh

Meter register on file

93%

Location and market basis

As receivedTaken from the meter register and the supplier invoice — nothing on this side is written by the agent.

Evidence used Meter register read Supplier invoice Factor set version

Why this methodIt is the method configured for this boundary — not chosen per datapoint.

ActionAcceptAmendSend to data owner

What the score decidesBelow the configured threshold the figure picks up a data-owner check before it.

Value

Where AI adds value

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

Where the value landsValue 01 – 04

Every datapointFrom the source record

03Assembly

Build from the record

Draw on the meter, invoice and factor records and the mapping the organisation has configured.

01Approved path

Every figure keeps its source

Routine datapoints arrive already assembled with their basis attached.

02Human review

Send review to the thin evidence

Evidence gaps, unretired instruments and low-confidence figures are marked, so the preparer's read starts where the basis is weakest.

04Build an evidence trail

The datapoint, the method applied to it and the preparer who accepted it stay in the workpaper.

Integrations

Typical integrations

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

Energy and emissions dataMeter data · SCADA historians
Fuel, fleet and invoice records

Sustainability platformsWatershed · Persefoni
Sphera · Net Zero Cloud

Enterprise systemsSAP · Oracle · Workday
Snowflake · Databricks

Agent

Sustainability reporting

Reads the records
Assembles the basis
Holds for sign-off

Reporting and workflowWorkiva · disclosure tooling
Evidence and workpaper stores

Observability & evaluationOpenTelemetry · 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 disclosure

Each control encloses the last. Whatever slips past all of them is named below.

L6 · Outermost — last line of defenceInward → L1 · closest to the model

L6Rollback / safe modePull the agent back to data collection when evaluation or production signals degrade.Roll back

L5Version monitoringTrack model, prompt, mapping and factor-set version changes.Track

L4TraceabilityRecord the source, the method, the factor version, the amendments and the acceptance.Record

L3Preparer sign-offHold figures for the named preparer; it governs release, not whether an accepted figure is right.Gate

L2Policy guardrailsTest figures against the configured mapping and claim rules; a failure returns the figure.Restrict

L1Confidence thresholdsRoute low-confidence figures to a data-owner check before the preparer sees them.Require review

Model coreFigure proposed — value, source record, method, movement and confidence

L1 – L2Test whether a figure may stand

L3Puts the release in a preparer's hands

L4 – L5Keep the datapoint and the method applied

L6Cuts back to data collection when signals degrade

How Nestack evaluates it

Evaluate the assembly workflow — not only the finished disclosure.

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

Surface — the disclosure the reader sees

Depth of coverage ▼

E1Final-output evaluationDid each figure trace back to a source record and a stated method?

E2Step-level evaluationDid the agent use the right records, mapping and factor versions?

E3Tool evaluationDid it read the correct system, site and reporting period?

E4Confidence calibrationDo low-confidence figures actually attract more preparer amendments?

E5Slice evaluationHow does performance change across specific disclosure areas?

E6Business outcomeHow many figures needed an amendment or a restatement afterwards?

Floor — the outcome the organisation answers for

Failure modes

Where each failure originates in the agent

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

Agent lifecycleDirection of processing →

01 · Retrieval1 mode

LQ-03

Superseded factor set

An emissions factor read from a retired version.

Stage gathersMeter records, invoices , with the source each came from

02 · Reasoning2 modes

LQ-04

Untraceable figure

A value no source record or repeatable method produces.

LQ-06

Silent method drift

Boundary or factor vintage changes without a note.

Stage proposesThe figure, the method behind it and confidence

03 · Tool / write2 modes

LQ-02

Unsupported explanation

A movement is given a cause the evidence cannot carry.

LQ-05

Unretired instrument

A market-based figure rests on an unretired instrument.

Stage writesOnly where write access and approval policy allow it

04 · Output1 mode

LQ-01

Marketing claim in the draft

A neutrality or renewable claim written unbidden.

Stage returnsThe disclosure the preparer signs and the reader relies on

05 · Change / Version1 mode

LQ-07

Silent factor regression

A model or factor-set change moves a figure without a note.

Stage tracksModel, prompt, mapping and factor-set changes

Sev-1 · a figure that cannot be traced Sev-2 · a wrong figure reaches the draft Sev-3 · source degrades, figure routes to review

See the complete Energy & Utilities failure-mode catalogue →

Affected slices

Overall quality can hide one weak area

Scope 3 value-chain estimates absorb most of the amendments, and a clean overall figure will not show you that. Nestack reports the preparer-amendment rate by slice, not only in total.

Slice performance — reported separately, not only in aggregateIllustrative example

Slice	Failure rate	Lift	Status
Scope 3 value-chain estimates	6.1%	3.7×	Review
Market-based instrument claims	4.3%	2.6×	Review
Newly acquired or divested sites	3.3%	2.0×	Watch
Metered Scope 1 and 2 data	1.3%	0.8×	Normal

Bar: preparer-amendment-rate lift vs. metered Scope 1 and 2 baseline · scale 0–4.0× · tick marks the 2.0× review threshold 2 of 4 slices over threshold

Evidence-linked improvement

The loop closes on a test, not a note

The cycle does not end in a post-mortem. It ends in a case the next release must clear, and that suite is what the next disclosure is measured against.

Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn

01Detect

Preparer-amendment rate rises in a disclosure area.

02Diagnose

Which datapoints moved, and under which method? The workpapers are read back until the cause narrows to one.

03Improve

Each change carries a version and the disclosures that forced it.

04Verify

Release waits on the affected cases going green again.

05Learn

The case is kept for good, and the method notes are rewritten.

Learn → DetectThe 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, assembly workflow, evaluation, integration, then production validation and handover.

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

01Disclosure workflow discovery and automation-boundary definition.

02Meter, ERP and data-platform assessment.

03Framework mapping, boundary and consolidation approach.

04Datapoint ingestion and normalisation.

05Workpaper assembly and source binding.

06Confidence scoring and gap routing.

07Preparer sign-off workflow.

08Data-platform and reporting integration.

09Audit-evidence regression cases.

10Guardrails and claim controls.

11Workpaper-trail instrumentation.

12Deployment, documentation and Agent Care handover.

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 tier PilotOne reporting entity, one period ProductionProduction data platforms AdvancedMultiple entities / mappings

Introduced at Pilot

Assembly to your records and mapping✓✓✓

Preparer sign-off✓✓✓

Evidence-quality baseline✓✓✓

Introduced at Production

Reporting by disclosure area—✓✓

Preparer review in your systems—✓✓

Approved write-back—✓✓

Data-platform integration—✓✓

Introduced at Advanced

Multi-framework mapping rules——✓

Multi-stage disclosure approvals——✓

High datapoint volume——✓

Multi-framework disclosure controls——✓

Build price From $5,000 From $8,000 Custom quote

Final build priceConfirmed after discovery based on integrations, workflow complexity, transaction volume, approval controls and deployment requirements.

Separate from buildBuild 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.

You bringWe build with it

01Your reporting boundary and entity structure → Datapoint ingestion and source-record mappingWeek 1

02Representative prior-period disclosures → Assembly baseline, method extraction and source bindingWeek 2

03Your framework mapping and its named owner → Framework mapping, boundary and consolidation approachWeek 1

04Access to relevant APIs, feeds or exports → Meter, ERP and data-platform assessment, then integration setupWeek 2

05Claims you would not want published → Evidence cases and failure-mode testingWeek 4

06What a draft may never assert on its own → Confidence scoring, gap routing, guardrails and claim controlsWeek 3

07Named preparers to accept figures → Preparer sign-off workflow, then pilot and production validationWeeks 5–6

Nothing else is required Deployment, documentation and Agent Care handover are ours.

Delivery timeline

Four phases across six weeks

The bands sit on the weeks the work occupies, which is why the fifth carries two kinds at once.

Phase W1W2W3W4W5W6

Discovery W1

Build W2 – W3

Evaluate W4 – W5

Pilot & Launch W5 – W6

Week focus W1Disclosure workflow discovery, mapping and the automation boundary W2Source integration and the assembly baseline W3Assembly workflow, confidence logic and sign-off controls W4Evaluation suite, claim checks and failure-mode testing W5Reporting-system integration, pilot areas and targeted corrections W6One disclosure cycle drafted under the reporting team, then handover

Reading the bandA band covers the weeks its work is named in, and nothing else. The week 5 overlap is real, not padding.

At the end of W6The cycle closes the validation and Agent Care takes over monitoring.

DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.

Next step · Energy AI agent

Build a sustainability agent around your workpaper, not around your report template.

Show us your datapoints, the records behind them and the mapping you report against. The preparer named in your reporting policy is the one who signs, and we will name what never leaves their desk.

Discuss this agent →

Nestack Agents · Sustainability reportingAGT-EN-05 · Agent Care available after launch