ResearchThe science
The science
behind the intelligence.
Every result Cleo produces is traceable, measurable, and auditable. We decompose, evaluate, and publish our work openly.
Latest Paper
A Multi-Agent Pipeline Approach to Regulatory Intelligence
Cleo Labs, Neuilly-sur-Seine · 2026, Forthcoming
We formalize regulatory intelligence as a distinct computational problem and present a production system that, given a company domain, identifies applicable regulations across 19 regions and 16 sectors, discovers developments in 8 languages, scores findings on a risk matrix, and generates impact assessments, orchestrating 30+ specialized LLM calls and hundreds of web searches per run.
19
Geographic regions
16
Sector-specific domains
8
Languages monitored
30+
Specialized analyses per run
420–1,200
Search calls per run
0.81
F1 score (full pipeline)
The five-stage pipeline
Regulatory intelligence decomposed into five sequential tasks, each addressing a distinct capability gap.
1
Step 1
Profile & Map
2
Step 2
Discover
3
Step 3
Score
4
Step 4
Enrich
5
Step 5
Assess
Beyond keyword search
Regulatory intelligence requires four capabilities that keyword search cannot provide.
| Capability | Core question | Keyword | LLM | Pipeline |
|---|---|---|---|---|
| Entity Understanding | What does this company do? | |||
| Legal Knowledge | Which frameworks exist and interact? | |||
| Temporal Awareness | What changed this week? | |||
| Domain Reasoning | How does this affect this company? |
Filling the market gap
Existing tools cluster along the diagonal. Proactive, company-specific regulatory intelligence remains an empty quadrant.
Company-specific
Generic
Reactive
Proactive
GRC Platforms
Change Mgmt
Legal AI
Compliance Automation
Cleo
Search infrastructure
A single pipeline run decomposes into hundreds of targeted searches across jurisdictions and languages.
S_total = (20 + ε) + (37 × 4) + 5 · N_reg
where N_reg is the number of regulations passing the relevance filter, ε ∈ [0, 28] captures agentic follow-up searches
Streaming architecture
Batch (traditional)
Score
A1
A2
A3
A4
Enrich
A1
A2
A3
A4
Assess
A1
A2
A3
A4
T = Σ max(tij)
Streaming (Cleo)
A1
A2
A3
A4
T ≈ max(Σ tij)
The White Paper
Dive deep into the methodology, architecture, and evaluation behind Cleo's regulatory intelligence pipeline.
Latest Paper
2026, Forthcoming
A Multi-Agent Pipeline Approach to Regulatory Intelligence
We formalize regulatory intelligence as a distinct computational problem and present a production system that, given a company domain, identifies applicable regulations across 19 regions and 16 sectors, discovers developments in 8 languages, scores findings on a risk matrix, and generates impact assessments, orchestrating 30+ specialized LLM calls and hundreds of web searches per run.
Download White PaperInterested in our
research?
We're building in the open. Get in touch to discuss research collaborations.
