Sustainability Claim Auditor
Finds the green claim you cannot evidence
5 of 8 sustainability claims need attention.
8 sustainability claims checked. 5 flagged. The largest gap is 1,245 days.
Start with SC-03. Soap has the most flagged.
Whether a claim misleads a reasonable buyer is for the regulator or a lawyer to say; the list checks only wording, certification and evidence age.
Why rows were flagged
- Vague green wording without certification50%
- Evidence older than 24 months33%
- Whole-product claim, partial evidence17%
Value flagged by Product
- Soap1
- Bottle1
- Candle1
- Box1
- Bag1
Items to act on, worst first
| Item | Product | Value | Days since the evidence | Why |
|---|---|---|---|---|
| SC-03 | Soap | 3 | 1,245 | Vague green wording without certification, Evidence older than 24 months |
| SC-01 | Bottle | 3 | 0 | Vague green wording without certification |
| SC-07 | Candle | 3 | 0 | Vague green wording without certification |
| SC-04 | Box | 2 | 1,019 | Evidence older than 24 months |
| SC-05 | Bag | 2 | 0 | Whole-product claim, partial evidence |
What to do this week
- Resolve SC-03 first: it is the most urgent on the list.
- Fix the data or the status on every flagged row, then re-run.
- Re-run this check every time the list changes, before it reaches a decision.
Do
- Fix the highest-risk item first, then run the check again on fresh data.
Don't
- Don't act on one row alone: open the source record first.
How to improve
- Add more detail per row (owner, date, source) so the next report can trace each item.
- Add a second period of data so the next report can show whether things are improving.
Demo
Overview
Sustainability reporting has moved from voluntary narrative to something regulators, customers and auditors examine, and the exposure is no longer reputational alone. Enforcement over unsubstantiated environmental claims has become routine in several jurisdictions, and the claims challenged are rarely deliberate deception — they are marketing copy written years ago by someone who believed it, never checked against a calculation.
The failures are all about evidence. A claim with no calculation behind it. "Carbon neutral" resting on offsets whose retirement nobody can produce a certificate for. A recycled percentage taken from a supplier's marketing page rather than a specification. A reduction claimed against a baseline that was quietly restated. A boundary excluding the largest part of the footprint without saying so — the most common and most consequential, because the excluded part is usually the supply chain.
And the mismatch nobody checks: the website says one thing, the annual report another, the tender response a third. All three are public, and a challenger reads all three.
This agent checks each claim against the evidence behind it and reports which are substantiated, which are unsupported, and where your own published statements contradict each other. It calculates no footprint, writes no claim, and gives no legal opinion.
Benefits
Unsupported claims found by you first
While correcting one is editing, not a response.
Consistency across everything public
Which is what a challenger tests.
A defensible evidence trail
Claim to calculation to source, written down.
What it does
Checks the boundary first
A footprint excluding the supply chain without saying so is the most common failure and the most consequential — the excluded part is usually the largest.
Traces every claim to its calculation
Marketing copy written years ago by someone who believed it, and never checked against a number.
Tests offsets to their retirement
"Carbon neutral" needs a certificate someone can produce. Often nobody can.
Detects restated baselines
A reduction against a baseline that quietly moved is the finding a challenger looks for first.
Compares your own publications
Website, annual report and tender responses. All public, all read by the same challenger.
Calculates nothing, claims nothing
It never produces a footprint figure or drafts a claim. It reports what your evidence does and does not support.
What this changes
What this changes about your week
- It takes over
- Tracing every published environmental claim back to a calculation.
- Done today by
- Nobody. The claims were written years ago by people who believed them.
- How often
- Never, until a regulator or a customer asks.
- Typical manual effort
- Each claim needs its boundary, method, source data and offset evidence checked.
Why Compliance & Risk in particular. The most consequential failure is a boundary that excludes the supply chain without saying so — and the website, the annual report and the tender response usually state three different numbers, all public.
Runs unattended
Started by you or by an event, and it finishes on its own. Nothing waits for someone to be at a desk.
The same standard every time
The two-hundredth item is held to the bar the first one was. Consistency is the part people cannot sustain.
It cannot act on its own
Sustainability Claim Auditor has no path to sending, spending or committing. That limit is why its output is safe to act on.
How it runs
This agent runs server-side through the PROMIVO runtime. Each run is logged step by step and every tool call is permission-checked before it executes.
- 1InputValidated against the agent input schema
- 2Modelclaude-opus-5 with automatic fallback
- 3Toolssearch_knowledge, extract_structured_data
- 4PermissionsRuns READ actions automatically; anything higher waits for approval
- 5OutputStructured result matching the output schema
- 6LoggingTokens, duration and every step recorded
Requirements
Integrations
No integrations required.
Before you start
- Your published environmental claims, from every channel
- The calculations and methodology behind them
- Supporting evidence: offset certificates, supplier specifications, assurance statements
- Prior years' reported figures and baselines
- Requires the All-Access plan or higher
Use cases
Before publishing a report
Every claim traced to its evidence.
Website and marketing review
Old copy nobody has revisited since it was written.
Tender and customer questionnaires
Whether your answers match your published position.
Before assurance
What an assurance provider will ask for.
Pricing
All-Access
Billed monthly through your PROMIVO subscription. Cancel at any time.
Runs consume your plan allowance for agent executions and tokens. See plan limits
FAQ
Does it calculate our footprint?
No. Calculating a footprint requires methodology decisions with accountability attached. It checks claims against the calculation you already have, and reports where there is none.
Is this legal advice on green claims regulation?
No. It reports whether a claim is substantiated by the evidence supplied. Whether a specific claim complies with a specific regime is a question for your own counsel.
Will it rewrite our claims?
No. It reports what the evidence supports and what it does not. A claim rewritten by an agent to sound defensible is the same problem in better prose.
Reviews
Reviews open once customers have run this agent.
Need this agent to work differently?
Tell us what to change and our team will scope a customised version for your business.
Customize this agent