Methodology
How we grade sources and analyze intelligence.
pulsEva ingests public-source intelligence from wire services, broadsheets, regional media, think tanks, government publications, and social channels. Every article passes through a multi-stage pipeline that classifies content across three independent axes, extracts entities, geocodes locations, and assigns a NATO-standard source grade before it reaches your feed.
The pipeline runs on 10-minute polling cycles. Content is deduplicated by SHA-256 hash, enriched with named-entity recognition and structured classification, and clustered into news cycles and story arcs by semantic similarity. The result is an intelligence feed where every item carries provenance, confidence, and analytical context — not just a headline.
Built on method
The PSESII framework
Every piece of evidence is classified into one or more of six analytical domains. PSESII is the backbone of intelligence structuring used by NATO-aligned analytical organizations — so you can tell what matters from the volume at a glance.
Political (P)
Elections, diplomacy, sanctions, protests, governance transitions, and legislative developments that shape the geopolitical landscape.
Security (S)
Armed conflict, military posture, defense spending, alliances, terrorism, organized crime, and state-level cyber operations.
Economic (E)
Trade policy, financial markets, energy commodities, supply-chain disruptions, currency movements, and corporate developments.
Social (So)
Migration flows, public-health emergencies, human-rights developments, demographic shifts, and humanitarian crises.
Information (I)
Disinformation campaigns, media freedom, civilian cyber security, technology and AI advances, espionage, and information control.
Infrastructure (In)
Critical infrastructure, transport networks, energy grids, telecommunications, water systems, and natural-disaster impacts.
NATO Admiralty Code
Source grading
Every source carries a dual-axis grade: reliability (A–F) measures the source's track record, and credibility (1–6) assesses the specific information in context. A composite like B2 means a usually-reliable source reporting probably-true information.
Source reliability (A–F)
| Grade | Label | Examples |
|---|---|---|
| A | Completely reliable | Reuters, AP, AFP |
| B | Usually reliable | BBC, FT, NYT, Al Jazeera |
| C | Fairly reliable | IISS, RAND, government press |
| D | Not usually reliable | Unvetted blogs, tabloids |
| E | Unreliable | Known propaganda outlets |
| F | Cannot be judged | Anonymous sources, new accounts |
Information credibility (1–6)
| Rating | Label | Criteria |
|---|---|---|
| 1 | Confirmed | Confirmed by independent sources |
| 2 | Probably true | Plausible, consistent with known facts |
| 3 | Possibly true | May be accurate, lacks confirmation |
| 4 | Doubtful | More likely false than true |
| 5 | Improbable | Contradicts established facts |
| 6 | Cannot be judged | Insufficient information |
Trust
The Source Review Board
A flat aggregator treats every feed as equally trustworthy. pulsEva does not. Every source's NATO Admiralty grade is editorially reviewed, with a recorded rationale, in an immutable review log — so a grade is never an unexplained label.
How a grade is reviewed
Eva, our analytical engine, produces a monthly scorecard for each source — measuring publishing yield, topic and geographic coverage, behavioral drift against its current grade, and how often its reporting is corroborated by independent sources. A human editor then approves, adjusts, or rejects the recommendation. A grade only changes through that review, and every change is written to a permanent log with the reason.
Who controls the source
pulsEva records ownership and state control — independent, public-service, state-controlled, state-affiliated, or private-commercial — and surfaces it. Listing a state broadcaster next to an independent wire service without that context hides the single most important fact about a claim.
On each source's grading you'll see a "Reviewed · {date}" stamp showing when it last passed editorial review — so the grade is never a black box.
Corroboration
Diversity you can read at a glance
Every event shows how many independent sources back it, the best grade among them, and how many of those sources are state-controlled — so corroboration and source diversity are visible before you act, not buried.
Example — the corroboration badge that appears on every clustered event.
Three-axis taxonomy
One event, three lenses
Every piece of evidence is classified along three independent axes, so you can filter and cross-reference intelligence from any angle.
Geography
ISO 3166 country codes, administrative regions, and geocoded coordinates. Both event location and relevant geographies are tracked — a conflict between two nations is relevant to both.
PSESII domain
The analytical framework above. Each article receives one to three PSESII classifications with confidence scores, enabling multi-domain analysis of complex events.
Consumer topics
Eleven reader-facing categories derived from PSESII: Conflict & Security, Cybersecurity, Geopolitical Risk, Political Instability, Economy & Trade, Energy, Technology, Climate, Health, Migration, and Organized Crime.
Analysis
How Eva works
Eva is pulsEva's analytical engine. She produces structured briefings, not casual summaries — leading with the most critical signal, quantifying when possible, and citing every source.
Briefing types
- Morning brief — daily digest of overnight developments, ranked by salience.
- Alert brief — triggered by critical monitor matches, delivered immediately.
- Weekly digest — trends, entity-frequency analysis, emerging topics.
- Country dossier — in-depth per-country assessment (Guru tier).
Generation process
- Salience scoring — evidence ranked by recency, source grade, corroboration count, and monitor relevance.
- Filter & select — top evidence chosen per your preferences and tier.
- Synthesize — structured generation with PSESII framing.
- Cite & verify — every claim attributed to a source with timestamp and grade.
Reach
Where the intelligence reaches you
The same graded, corroborated evidence travels to the tools you already use. Connect pulsEva as an MCP server and ask it inside Claude or any MCP-compatible AI assistant — every answer carries its source grades. Route alerts and briefings to Telegram or your own webhook. Available on Guru and up.
Coverage health
We tell you where we're thin
Honest intelligence names its blind spots. pulsEva tracks where source coverage is degraded — by category, region, and language — and surfaces a coverage-health view, so you know what the picture is missing instead of mistaking silence for calm.
Our sources
Curated across six categories
pulsEva curates sources across six categories. Each carries a NATO reliability grade and is monitored for availability with circuit breakers, polled on 10-minute cycles with SHA-256 deduplication.
Wire services
Reuters, AP, AFP, Interfax, Xinhua.
Broadsheets
BBC, FT, NYT, Guardian, Le Monde.
Regional media
Local outlets across many countries.
Think tanks
IISS, RAND, Chatham House, CSIS.
Government
Defense-ministry press, CERT advisories, foreign-affairs releases.
Social / OSINT
Verified social accounts and monitored channels.
Ready to start analyzing?
Get the intelligence feed with NATO-grade, editorially reviewed sources and source-aware briefings.