Your research expertise. AI workflows, put to work.
For hedge funds, family offices and in-house investment teams: combine research expertise with our AI workflow and Harness engineering experience to put proven methods to work.
Outputs identify live data, existing knowledge and inference.
02 / ENGINEERING SERVICES
AI research workflows for investment institutions.
Serving hedge funds, family offices and in-house investment teams.
Read the indicators. Understand the resonance.
Combine trend, momentum, volume, volatility and pattern indicators to reveal trend-strength resonance. AI helps interpret indicator contributions and key conditions. Configure MCP and Skills in your local model environment for local analysis.
INDICATORS → RESONANCE → LOCAL AI
Trend
Momentum
Volume
Volatility
Patterns
→
Trend-strength resonance
AI interprets contributions
→
MCP + Skill
Local model environment
Research workflow
Conceptual workflow · no live signals
From information flow, to research leads.
Track equities, commodities, rates, FX, safe havens, crypto and credit spreads. Filter X and RSS news by topic, region and source. AI briefs connect market themes, corroborating and conflicting evidence, and upcoming catalysts; rule-based metrics stay separately labelled.
NEWS STREAM → AI ANALYSIS → BRIEF
X / RSS
Source stream
Topics & regions
Filter news
Original records
Retain sources
→
AI synthesis
Connect related events
→
AI macro brief
Market themes
Evidence & divergence
Upcoming catalysts
One event · linked evidence
Compare research. Understand the differences.
Within your existing research subscriptions, AI extracts key arguments, forecast revisions and differences across brokers. Compare assumptions and periods on a consistent basis, with every summary traceable to the original report for team review.
LICENSED RESEARCH → AI COMPARISON
Report A
Assumptions
Period
Revisions
Report B
Assumptions
Period
Revisions
Report C
Assumptions
Period
Revisions
AI comparison
Align the basis · surface differences · trace sources
Assumptions · periods · forecast revisions
Describe a strategy. Let AI build the test.
Describe the universe, strategy rules and test conditions in natural language. AI turns them into a reproducible backtest, with out-of-sample splits, costs and checks for look-ahead and survivorship bias. Review drawdown, turnover and the test record before drawing conclusions.
HYPOTHESIS → AI BACKTEST → REVIEW
Natural language
Universe · strategy · conditions
→
Data & samples
Rules & costs
Bias checks
→
Team review
Drawdown · turnover
Reproducible record
Refine the hypothesis · test again
Connect documents. Build research memory.
Store sources, research and tests as AI-friendly Markdown documents. Agents can read and reference related documents within agreed permissions, helping build your own investment research knowledge graph. Keep the evidence and accumulated knowledge under your control.
MARKDOWN KNOWLEDGE GRAPH → AGENT RETRIEVAL
Sources.md
Views.md
Research.md
Tests.md
Methods.md
→
Agent retrieval
Read · reference · connect
Your research memory
Sources, views and tests stay connected
Concept demonstration · Research workflow and output logic.
Coverage follows the mandate.
The universe is agreed with the investment team before work starts.
Equities
single names, sectors, index constituents
Macro & rates
cross-asset macro, sovereigns, credit
FX
major pairs, crosses, emerging-market currencies
Commodities
energy, metals, agriculture
Funds & ETFs
holdings, flows, tracking error
Digital assets
major liquid instruments, within applicable limits
Lean orchestration. Deep domain skills.
Integration & controlled write-back
Standard APIs · audit logs · human approval
Through agreed interfaces; no direct database reads or writes.
Domain skills & memory
Research rules · analytical methods · working context
Knowledge stays with the client when the model changes.
Harness runtime · thin layer
Execution primitives only; domain logic lives in skills.
Foundation models
Proprietary · open-weight · locally deployed
Replaceable; validate before switching.
Client-owned assetsReplaceable infrastructure
Conceptual architecture. Model changes still require compatibility checks and task validation.
Your data. Your research knowledge.
Your institutional data and research knowledge remain yours. We design the workflow around your access requirements and agreed operating environment.
An agreed data boundary
Agree deployment, model-service access and data flows before implementation. Processing and support access follow the approved scope.
Controlled access and records
Define access roles, human review and execution records with your technology and compliance teams.
Knowledge that stays with you
The knowledge base belongs to your institution and supports full export. Research rules, sources and records remain independent of model interfaces, with handover arrangements agreed in writing.
News and insights
Perspectives on research workflows, AI engineering and knowledge that lasts.
