What the team wants to do
Investigate new policy options using earlier research, exact sources, known uncertainty and the judgement of experienced analysts as a starting point.
Policy analysts already work with complex evidence, deadlines, institutional knowledge and difficult judgement calls. They may wish to revisit earlier work when a new regulatory development, stakeholder question or implementation signal arrives—without reconstructing every source, assumption and unresolved issue.
Epistamate’s Research Workspace explores how Frontier AI-assisted investigation can build on preserved evidence and professional reasoning, so the next policy question can be pursued with continuity and inspectable limits—not as an automatic policy recommendation.
Imagine a policy team asked to reassess a manufacturing or trade-policy position after new official guidance and implementation information arrive. Its previous analysis was useful; the new task is to understand which earlier assumptions still apply, what additional questions arise and whether a revised briefing can inform the next decision in time.
Investigate new policy options using earlier research, exact sources, known uncertainty and the judgement of experienced analysts as a starting point.
Evidence may be scattered across successive reports and people; source authority, dates, legal status and applicability require renewed checking, consuming scarce research capacity.
A better-timed, appropriately qualified policy or strategic decision could justify the effort. Whether a maintained reasoning state adds value over established research methods must be tested, not assumed.
Apparent consensus can be one original result amplified through many papers, reports and commentary. Counting sources is not enough; independence matters.
Evidence can be strong and still fail to transfer to the jurisdiction, population, mechanism or implementation context of the policy question.
Disagreement is often professionally inconvenient, so synthesis resolves it too early. Epistamate treats contradiction and qualification as information rather than defects.
What the evidence does not establish may be more consequential than what it does. Gaps should survive the report and become future research targets.
A future reviewer should be able to distinguish AI-proposed priorities from claims an analyst actually inspected and judged.
Prior research should be reusable with provenance and revalidation rather than rebuilt from scratch or copied forward without checking recency and applicability.
Consequential propositions remain linked to source identity and the material that supports, qualifies or contradicts them. A bibliography is part of the output; the support chain is the more important object underneath it.
Unresolved needs remain visible and can drive Research Further. The system is allowed to say “the evidence is insufficient” rather than manufacture a complete-looking brief.
Frontier models can improve acquisition planning, review prioritisation and adversarial challenge. Their suggestions remain advisory; model agreement does not count as independent evidence.
The long-term Knowledge layer is intended to carry prior evidence, gaps and review history forward while checking currency, applicability and contradiction for each new policy question.
Researcher decisions are explicit events tied to the research state. A senior reviewer can reconstruct what evidence was available and what the analyst actually did, without treating approval as evidence strength.
Official instruments, implementation evidence, expert analysis and commentary can play different roles. The engine architecture supports domain policy packs rather than relying on prompt instructions alone.
A policy claim can be normatively attractive yet weakly evidenced on implementation feasibility or stakeholder effects. Those dimensions should remain separable.
Assumptions and transferability conditions should remain visible so a reviewer can challenge them instead of inheriting them from the synthesis.
We are interested in recurring policy questions where existing research and professional understanding could enable useful next decisions, with evidence traceability and reviewer authority preserved.
Start a conversation →