Pre-built AI Skills for execution.
Specialized agents that read the context graph, act inside your systems and explain every decision. Configurable per domain, always with a human in the loop.
Account Relationship Map
Reconstructs the full stakeholder map of a target account — champions, blockers, silent influencers — from meetings, emails and CRM history.
Pre-Meeting Brief
Delivers a decision-ready brief before every meeting: last interactions, open topics, competitive signals, next-best action.
Deal Risk Scoring
Scores every open opportunity against a live risk model: coverage gaps, stakeholder silence, competitor moves, deal slippage patterns.
Pipeline Health Review
Prepares weekly pipeline reviews with evidence-backed commentary on each deal — no more manual slide building for QBRs.
Account Expansion Scout
Detects upsell and cross-sell signals across the installed base — funding rounds, hiring, product usage — and routes them to the owner.
Churn Early-Warning
Combines support tickets, meeting sentiment, sponsor changes and product usage into a single churn-risk signal, weeks before renewal.
Competitive Intelligence Watch
Monitors competitor moves — pricing, product launches, hires, deal wins — and pushes battle cards into deal rooms automatically.
AML Alert Triage
Enriches transaction-monitoring alerts with counterparty context, network exposure and evidence — ranking real risk, declassing noise.
KYC Refresh
Runs periodic KYC reviews at scale — beneficial owner changes, sanctions updates, adverse media — with a full audit trail per customer.
Sanctions Screening
Screens counterparties and payments against EU, UN, OFAC and national lists — with explainable hits and lower false-positive rates.
Third-Party Due Diligence
Builds an evidence-backed dossier on any counterparty — ownership, litigation, sanctions, adverse media — in minutes instead of days.
Insurance Fraud Detection
Detects coordinated claims networks, staged incidents and repeat actors across policies, providers and geographies.
Regulatory Change Monitor
Tracks regulatory updates across jurisdictions, maps them to impacted processes and controls, and drafts change tickets automatically.
Export Control Check
Screens shipments against dual-use lists, end-user checks and jurisdictional restrictions — flagging risk before goods leave.
Supplier Risk Radar
Continuously monitors the supplier base for financial distress, sanctions, ESG events and single-source concentration.
Tender Integrity Monitor
Scans public and private tenders for collusion signals, hidden beneficial owners and abnormal bidding patterns.
Counterparty Network Map
Reveals hidden ownership chains, intermediaries and shared directors across a portfolio of counterparties.
Red Flag to Network
Turns a single red flag into a full network: shared addresses, phones, devices, counterparties — reconstructed as an interactive graph.
Case File Builder
Assembles a court-ready case file from fragmented evidence — timelines, actors, sources, chain of custody — with every claim cited.
Beneficial Owner Unmask
Traces beneficial ownership through nominees, holding structures and cross-border layers — with confidence scores per hop.
OSINT Brief Generator
Produces an OSINT dossier on a person, company or event — every source, every timestamp, every extraction preserved for review.
Adverse Media Sweep
Runs multilingual adverse media checks across news, court filings and gazettes — deduplicated, ranked and cited.
Configured for your domain. Executed on the context graph. Explained at every step.
Configure in Studio
Compose a skill from ontology entities, sources, prompts and policies — with your domain experts, not just engineers.
Run on the graph
Skills read the live context graph, call the tools they are authorized to use and write actions back into systems of record.
Explain every decision
Every output ships with entities used, signals cited, policies applied and reasoning — ready for review, audit and override.
Every skill is a template. Open it and make it yours.
Behind every AI Skill is a configurable agent in the Studio. Change the ontology, the sources, the prompt logic, the thresholds and the outputs — without writing code.
Configure, not rebuild
Start from a pre-built skill and tune it for your domain. Add entities, signals, policies and review steps in a governed environment.
Version and audit
Every change is versioned. Every execution is logged. Every recommendation is traceable back to the model, the data and the reviewer.
Human in the loop
Set escalation rules, review gates and override workflows. Compass executes fast; humans stay in control.
Can't find the skill you need? We build it with you.
Every domain has its own decisions. Bring us your workflow and we configure the skill on your context graph.