Solutions · Policy + lawmakers

The evidence behind
every policy decision
deserves this scrutiny.

Policy is made on evidence that is contested, incomplete, or misrepresented — and the consequences of getting it wrong are public. Augle runs the adversarial review that a well-resourced opposition will run anyway, before the decision is made rather than after.

Policy analysts reviewing legislative evidence bases
Parliamentary researchers preparing briefings
Regulatory teams assessing impact methodology
Think tank researchers producing policy recommendations
Session configuration
Guardian modeAcademic + Legal
DepthStandard · Deep
Document ingestionBills · RIAs · Studies · Briefings
SVS checksRetraction DB · statutory version · jurisdiction scope
OutputEvidence-anchored finding · confidence grade · dissent flags · audit trail
The problem

Policy evidence gets challenged at the worst possible moment.

A regulatory impact assessment that looks solid under friendly review will look very different under opposition scrutiny. The discount rate in a 30-year infrastructure model. The replication status of the behavioural study your intervention depends on. The jurisdiction scope of the precedent your legal team cited. These things get found — the question is whether you find them first.

Questions policy teams run on Augle

Does this cost-benefit methodology adequately account for long-run climate-adjusted risk?
Which claims in this regulatory impact assessment are most exposed to opposition challenge?
Is the evidence base for this behavioural intervention replicable at the proposed scale?
Does the cited precedent apply to the jurisdiction and statutory context we're relying on?
What is the strongest argument against our proposed discount rate, and how do we address it?
Cost-benefit methodologies that don't survive scrutiny

The Methodologist evaluates construct validity across the entire evidence base — whether the methodology actually measures what the policy claims it measures. Standard CBA frameworks systematically undervalue tail risk over long time horizons. Augle surfaces that before the Treasury Select Committee does.

Behavioural evidence that doesn't replicate at scale

Many policy interventions are based on behavioural research conducted under controlled conditions with non-representative populations. The Contrarian identifies the generalisability objection — whether the effect size holds at population scale and in the real-world context the policy targets.

Legal citations with jurisdiction or version problems

The Guardian's SVS validates statutory citations against current version and jurisdiction scope. Overruled decisions, superseded statutes, and cross-jurisdiction misapplications are flagged at Moderate severity — automatically, before they enter a briefing or a bill.

The objection your opponents have already found

The Contrarian runs at maximum temperature to surface the adversarial framing an opposition researcher, a critical journalist, or a hostile expert witness will deploy. Unresolved Strong objections appear verbatim in the output — not softened, not summarised.

How it works in practice

Three sessions.
Three policy moments.

Each scenario below illustrates realistic deliberation behaviour across the policy research and legislative lifecycle.

Use case 01 of 03 · Policy + lawmakers
The Infrastructure Bill Review
Senior Policy Analyst, Treasury · Pre-committee scrutiny
Standard depth · document ingestion

Does the proposed infrastructure bill's cost-benefit methodology adequately account for climate-adjusted risk over a 30-year horizon?

CartographerSettled: standard CBA frameworks systematically undervalue tail risk. Contested: the appropriate discount rate for climate-adjusted infrastructure over 20+ year horizons. Unknown: no published methodology for integrating physical climate risk into UK Green Book appraisal at this scale.
MethodologistConstruct validity issue: the bill's 3.5% discount rate follows HM Treasury guidance but the IPCC AR6 evidence base supports a materially lower rate for long-horizon climate risk. Evidence ceiling set at Probable for 20+ year projections.
ContrarianStrong objection (Unresolved): "The methodology is defensible for 10-year projections but materially inadequate for 30-year claims. The Treasury committee will have the Stern Review rebuttal ready. The team does not."
PragmatistPrepare a two-page annex defending the discount rate choice with explicit reference to AR6. Alternatively, scope the 30-year projections with a stated sensitivity range. Either closes the committee's most predictable line of attack.
Session output
FindingProbable for near-term projections · Contested for 20+ year claims
Key objectionDiscount rate inadequate for long-horizon climate-adjusted infrastructure
SVSAll citations verified. Green Book version current.
Next stepDiscount rate annex or explicit sensitivity range on 30-year figures
The value

The team knew the discount rate was a potential weakness. They didn't know the committee had already briefed a Stern Review expert. They found that out from Augle — before the session, not during it.

Use case 02 of 03 · Policy + lawmakers
The Behavioural Intervention Assessment
Regulatory Impact Analyst · Department for Health and Social Care
Deep depth · expert review

Is the behavioural evidence base for the proposed sugar levy sufficient to support the projected public health outcomes at national scale?

CartographerSettled: fiscal interventions reduce consumption in study populations. Contested: effect size at national scale across all socioeconomic groups. Unknown: long-run substitution behaviour and reformulation effects beyond the first two years.
MethodologistExternal validity problem: primary evidence draws from Chilean and Mexican studies. UK population distribution, retail structure, and price elasticity assumptions diverge materially. Ceiling set at Probable for primary consumption effect, Contested for health outcome projections.
ContrarianModerate objection: "The RIA uses the Mexican elasticity figure without adjustment for UK income distribution. The effect is systematically higher in lower-income deciles — which is presented as a benefit but generates a regressive distributional impact that isn't modelled."
Session output
FindingProbable for primary consumption effect · Contested for health outcome projections
Key gapDistributional impact not modelled — regressive effect in lower-income deciles
Next stepCommission distributional analysis before RIA submission. Add regressivity section.
The value

The distributional objection wasn't in the RIA. It would have been in the Health Select Committee's written evidence within 48 hours of publication. Three weeks of additional modelling prevented a headline they couldn't walk back.

Use case 03 of 03 · Policy + lawmakers
The Parliamentary Briefing
Parliamentary Researcher · House of Commons Library
Standard depth

What does the evidence actually say about the relationship between stop-and-search powers and serious violent crime reduction — and what are the strongest objections to the published findings?

CartographerSettled: deterrence effect in the immediate operational area during active deployment. Contested: displacement effect vs. net reduction. Contested: effect persistence after deployment ends. Unknown: whether community trust degradation offsets crime reduction over 5+ year horizons.
ContrarianStrong objection (Unresolved): "The published studies measure crime displacement, not crime reduction. Net crime in the city-wide area is not measured in any of the primary studies cited. The briefing currently makes a claim the evidence cannot support."
SynthesizerThe evidence supports a localised deterrence effect during active deployment. It does not support claims about net city-wide crime reduction. These are different claims. The briefing currently conflates them.
Session output
FindingEstablished for localised deterrence · Gap for net city-wide crime reduction
Unresolved objectionStudies measure displacement, not net reduction — conflated in briefing draft
Edit neededScope claims to localised deterrence. Acknowledge the net reduction gap explicitly.
The value

A briefing that conflates localised deterrence with net crime reduction is a briefing that gets corrected in committee — publicly, and by the opposition researcher who already knows the distinction. It got fixed before it was published.

How Augle works for policy teams

Built for evidence that
will face adversarial review.

1
Upload your documents

Submit bills, regulatory impact assessments, policy briefs, research papers, and statutory references. The Guardian's SVS validates citations, checks statutory versions, and confirms jurisdiction scope before any agent receives the evidence.

2
The ensemble maps what's contested

The Cartographer classifies every evidence node as Settled, Contested, or Unknown. The Methodologist assesses construct validity — whether the methodology measures what the policy claims. Confidence bounds are set as hard constraints before deliberation begins.

3
Adversarial pressure is applied

The Contrarian runs at maximum temperature to surface the objections an opposition researcher, expert witness, or critical journalist would raise. Every objection specifies a resolution condition. Unresolved Strong objections cannot be softened.

4
You receive an auditable finding

The Synthesizer produces a calibrated finding anchored to the evidence nodes registry — not the discourse thread. Confidence grades, unresolved objections verbatim, and reopen conditions. The full audit trail is exportable for regulatory compliance or FOI purposes.

Policy session · configuration
Guardian mode
Academic + Legal — statutory citation validation, retraction database, jurisdiction scope monitoring
Document types
Bills · Regulatory Impact Assessments · Research papers · Hansard references · Statutory instruments
Contrarian focus
Opposition framing · generalisability objections · distributional impact gaps · discount rate challenges
Output package
Evidence-anchored finding · confidence grade per claim · unresolved objections verbatim · reopen conditions · exportable audit trail
Session depth
Standard for briefings and evidence reviews · Deep for major legislative packages with expert review at Phase 1/2 boundary
Why Augle for policy

The scrutiny that policy
evidence deserves.

Finds the objection before the opposition does

The Contrarian is designed to surface the adversarial framing that a well-resourced opposition team will deploy. It steelmans every claim before challenging it — which means it finds the strongest version of the objection, not a weak one you can dismiss. If the objection is strong and unresolved, it appears verbatim in your output.

Validates every source automatically

The Guardian's SVS checks retraction status, statutory version, and jurisdiction scope on every citation. A superseded regulation cited in a briefing, or a retracted study cited in an RIA, is flagged automatically — before it becomes a committee embarrassment or a FOI liability.

Produces an auditable evidence record

Every session produces a full audit trail — SVS verification outcomes, confidence downgrades, objections raised and resolved, and phase boundary evaluations. For regulated industries and parliamentary accountability, this is the record that demonstrates due diligence on the evidence base that informed a decision.

Find the objection
before they do.

Join waitlist and run a session on the evidence behind your next policy decision.