Methodology

A seven-wave multi-agent pipeline turns Russian, Uzbek, and Kyrgyz primary sources into a typed knowledge graph. Eleven specialised agents work in three parallel research waves, one synthesis wave, one adversarial audit, and one outreach wave. Cross-model verification on a strict twenty-dollar OpenRouter budget keeps every Tier-A claim independently re-checked.

What does each wave do?

Each wave produces a typed JSON artefact under state/. Every record carries a verification tag and a sources array. The merged knowledge graph at state/knowledge_graph.json is the single read view that downstream waves consume.

The seven waves of the research pipeline
WaveAgent(s)Purpose
0blueprint-architectStrategic plan, target lists, and the constraint inventory that scaffolds every later wave.
1legal-cartographer · case-tournamentCatalogue the decree corpus on lex.uz and cbd.minjust.gov.kg; tournament 100 global precedents for transferability to UZ and KG.
2institution-mapper · donor-pipeline · procurement-harvester · trend-triangulatorMap state bodies (8 tiers), donor programmes with named TTL, live tenders, sector trends.
3people-intelligence100+ decision-makers, including the 16 diaspora bridges who shape policy from London, Dubai, and Silicon Valley.
4initiative-synthesizer · solopreneur-mvp-synthesizer100 institutional B2G initiatives plus 200 solopreneur MVPs, scored on five weighted axes.
5reflexion-auditorAdversarial re-verification with a different model, minimum three HIGH-severity issues, public corrections.
6pitch-artificerTier-A and Tier-B outreach bundles. Private outreach scripts stay in the contributor vault.

How is verification enforced?

Every record carries one of six verification tags: VERIFIED (primary source plus one corroboration), L2_VERIFIED (primary source only), L3_VERIFIED (primary plus expert commentary), INFERRED (indirect evidence), UNVERIFIED, or CONTRADICTED. The reflexion-auditor calls a different model than the original agent — Sonar Pro re-checks Sonar Deep Research output, breaking the echo chamber. Twelve content quality gates block any deploy on a single H1 violation, internal ID leak, fabricated decree, or fabricated LinkedIn URL.

What is the source priority?

Uzbekistan: lex.uz, gov.uz, president.uz, norma.uz, then spot.uz, gazeta.uz, kun.uz, daryo.uz. Kyrgyzstan: cbd.minjust.gov.kg, president.kg, gov.kg, kabmin.kg, then 24.kg, kaktus.media, akipress.org. Donors: documents.worldbank.org, projects.worldbank.org, adb.org/projects, ec.europa.eu/international-partnerships. Every country claim cites at least one Russian-language source. Fifty-three percent of all sources in this run are Russian-language.

Reproduce this research yourself

The full pipeline is open-source. Clone github.com/avaluev/ca-b2g-research, copy .env.example to .env and add your OpenRouter key, then run make run. Total runtime: about ten hours wall-clock. Total OpenRouter spend (with the audit wave on paid Sonar Pro): under twenty dollars. Anthropic Claude usage runs on your own subscription.

Cite this research
BibTeX
@misc{valuev26cab2g,
  author = {Valuev, Alexandr},
  title  = {Central Asia B2G Intelligence: Methodology},
  year   = {2026},
  url    = {https://avaluev.github.io/ca-b2g-research/methodology/},
  note   = {Data vintage 2026-05, Apache 2.0}
}
APA   Valuev, A. (2026). Central Asia B2G Intelligence: Methodology. Retrieved from https://avaluev.github.io/ca-b2g-research/methodology/
MLA   Valuev, Alexandr. "Central Asia B2G Intelligence: Methodology." Data vintage 2026-05, https://avaluev.github.io/ca-b2g-research/methodology/.