Help decide what PolicyWatcher should show next
PolicyWatcher is moving from static dashboards to goal-driven evidence workspaces. The next step is not more navigation. It is a clearer way to ask: what do you need to understand, how much evidence do you need, and what should the system hide until the source is trustworthy enough?
Adaptive workspace
Start from the question, not from the dashboard
PolicyWatcher 3.6.3 implements this track inside the live dashboard: users choose the purpose of the session and the depth of evidence they need, then the interface changes module priority, density, and context while source-quality warnings remain visible.
1. Choose the job
2. Choose evidence depth
For audit or publication. The UI exposes retrieval path, hashes, timestamps, source drift, and known limitations.
3. Generated view logicOpen this profile in the dashboard
Understand what changed and why it matters
A low-noise reading mode focused on policy changes, plain-language summaries, affected rights, and what should be verified at the source.
Citizen workspaceForensic
1QuestionUnderstand what changed and why it matters
2EvidenceChange cards, source status, short explanations, region impact.
3OutputReadable briefing and shareable change page.
Check logsHash chainPublic evidence gateFallback pathReview history
In the lane
What is already in motion
These items extend the Confidence work into the public product surface: they make the platform easier to inspect, easier to use, and harder to misread.
In progress
Adaptive Insight Profiles
Replace one-size-fits-all dashboards with views assembled from the user objective: citizen briefing, governance review, research comparison, or builder/API mode.
- Benefit
- Users start from the question they have, not from a static dashboard they must decode.
- Validation
- Usability test: can a first-time user find the right evidence path in under two minutes?
In progress
Source Remediation Workbench
Turn failed retrievals into an actionable admin workflow: URL repair, jurisdiction fit, duplicate source decisions, and source suspension review.
- Benefit
- Dataset confidence becomes a daily operating loop rather than a hidden maintenance task.
- Validation
- Every repaired source must show before/after QA status and retrieval evidence.
In progress
Community Signal Board
Let users signal which roadmap candidates matter most and describe their real workflow, evidence needs, and acceptable limits.
- Benefit
- Prioritization becomes traceable and grounded in actual use cases.
- Validation
- GitHub issues become structured roadmap signals with acceptance criteria.
Planned
Personal Evidence Workspace
Save preferred detail level, visible panels, comparison lenses, and export defaults locally so repeated work feels intentional instead of crowded.
- Benefit
- Power users get density; casual readers get clarity.
- Validation
- Preferences must be local, reversible, and never hide source-quality warnings.
Dataset QA, source suspension, review log, access log, renderer/VPS monitoring, public evidence gate, and quality badges.
Dashboard composer, intent/depth profiles, deep-link presets, contextual module priority, community roadmap, and public resource navigation cleanup.
API v1, signed webhooks, richer reports, multi-version diff, and stronger integration surfaces.
Governance mapping validation, source-confidence ledger, benchmark pack, and production database hardening.
Feature radar
Potential evolutions the community can rank
Each candidate needs more than a vote. The best signal explains the workflow, the expected evidence, the acceptable limits, and the reason the current product does not solve it yet.
Adaptive UIHigh value
Objective-based dashboard composer
A guided start screen asks what the user wants to understand and builds a dashboard from evidence modules, not from static templates.
Watch pointMust not hide QA warnings behind simplification.
Signal interestAPIEnterprise pull
Public API v1 and signed webhooks
Expose source-gated company, policy, change, and signal data with rate limits, object-level authorization, and HMAC-signed outbound events.
Watch pointNeeds careful schema versioning and replay protection.
Signal interestGovernanceResearch ready
Advisory framework mapping
Map policy changes to EU AI Act, ISO/IEC 42001, NIST AI RMF, OECD AI Principles, and PALO lifecycle evidence without issuing compliance verdicts.
Watch pointWording must remain evidence-oriented, not legal determination.
Signal interestDataset QATrust builder
Source confidence ledger
A public ledger for monitored source health: successful fetches, suspended sources, URL remediation, review decisions, and current publication state.
Watch pointShould avoid exposing operational secrets or private admin notes.
Signal interestResearchNarrative value
Market pulse atlas
A visual atlas of policy movement by sector, jurisdiction, source status, and time period, designed for researchers and journalists.
Watch pointRequires enough verified public evidence to avoid empty theatrics.
Signal interestReportsNear term
Board-ready evidence packets
Export a compact packet with source URL, snapshot hash, change summary, QA state, methodology limits, and recommended human-review questions.
Watch pointMust not imply certification or legal advice.
Signal interestAdminOperational
Bulk source onboarding
Add companies and policy URLs through a staged workflow: proposed source, official-source review, first baseline, QA gate, and publication decision.
Watch pointNeeds duplicate detection and safe re-baseline handling.
Signal interestSignalsCommunity ask
Custom watchlists
Let users track a subset of companies, policies, jurisdictions, or governance topics and receive focused updates.
Watch pointSubscription preferences need strong privacy defaults.
Signal interestExplainabilityCore trust
Why this score changed
Show which text passages, KPI fields, region impact rows, and review decisions influenced a change in score or category.
Watch pointNeeds explicit AI boundary and source quote handling.
Signal interestIntegrationsLater
Evidence export to GRC tools
Generate structured exports for Jira, Confluence, OneTrust-style workflows, and internal risk registers after the generic webhook layer is stable.
Watch pointDirect vendor integration should follow a generic signed-events foundation.
Signal interestUXDesign priority
Forensic workbench redesign
Move from crowded navigation to a command-driven, panel-based inspection surface with graph, table, timeline, and evidence modes.
Watch pointMust improve orientation without losing expert controls.
Signal interestQualityValidation
Community benchmark pack
A public set of known policy-source cases used to test retrieval, source-fit checks, source suspension, and dashboard behavior.
Watch pointNeeds stable fixtures that do not become fake public evidence.
Signal interestHow ranking should work
Signals should describe evidence needs
A popular request still needs feasibility, source-quality review, security review, and wording discipline. Roadmap ranking should guide prioritization, not replace product judgment.
Use case clarity
What question should PolicyWatcher help answer, and who is asking it?
Evidence requirement
Which source, check log, snapshot, region, KPI, or export is needed?
Implementation path
Can it be built without inventing data, hiding uncertainty, or overstating automation?
Release lane
Is it a feature drop, a confidence hardening release, or a research candidate?
Community input
Open a roadmap proposalTell us what you need PolicyWatcher to reveal
The most useful feedback is specific: the role you have, the decision you need to make, the evidence you trust, and the level of detail you expect.