How Our AI System Works
Radical transparency into how we analyze companies and generate investment assessments.
Our AI Doesn't Predict — It Synthesizes
We combine multiple data sources and AI agents to help you understand a company's situation. The goal is to surface insights you might miss, not to tell you what will happen.
Where We Get Our Data
Our system ingests data from multiple sources to build a complete picture of each company.
Company Reports
News & Events
Market Data
Macro Indicators
The Two-Layer Architecture
Our AI works in two stages: first, specialized "domain experts" analyze specific data types. Then, an "investment team" synthesizes everything into a coherent assessment.
Layer 1: The Domain Experts
Think of Layer 1 as organizing all the puzzle pieces before solving the puzzle. Each agent focuses on a specific type of analysis.
| Agent | What It Analyzes | When It Runs |
|---|---|---|
Qualitative | Business model, competitive position, management quality, strategic risks | When a new report is downloaded |
Quantitative | Financial statements, KPIs, peer comparisons, valuation metrics | When new period data is available |
News Synthesis | Daily market news and 4-day aggregated trends | Daily and every 4 days |
Macro Synthesis | Interest rates, commodities, currency, economic indicators | Weekly |
Weekly Intel | Rolling window of company-specific events | When ≥3 events accumulate in 7 days |
Sector Analysis | Industry-wide trends using advanced taxonomy | Periodically |
The Decoupled Trigger System
Why "decoupled"? Traditional systems wait for all data to be ready before analyzing. Our system lets different types of analysis run independently, so you get insights faster.
Foundational Triggers
Deep, comprehensive analysis of the entire business and financial state.
Incremental Triggers
Rapid updates to layer in news, macro changes, and tactical events.
📄 Foundational Triggers
Triggered by new reports or data availability.
- Create deep, comprehensive analysis
- Take longer but produce complete picture
- Form the backbone of assessments
⚡ Incremental Triggers
Triggered by event accumulation or schedules.
- Keep analysis fresh between reports
- Faster, more frequent updates
- Capture breaking developments
Layer 2: The Investment Team (6 Agents)
Once Layer 1 has organized the data, Layer 2 agents work together like an investment committee to form a coherent view.
😊 Sentiment Analyst
Assesses overall tone across news, reports, and market signals.
"What's the mood?"
⚖️ Risk/Opportunity Analyst
Identifies top risks and opportunities with probability × impact scoring.
"What could go right/wrong?"
🔍 Data Quality Analyst
Evaluates freshness, completeness, and reliability of available data.
"Can we trust this analysis?"
🔄 Reconciliation Agent
Cross-checks qualitative claims against quantitative evidence. Exposes contradictions.
"Does the story match the numbers?"
📊 Charting Agent
Generates visual chart specifications to illustrate key thesis points.
"Show me the evidence"
🎯 Investment Orchestrator
Synthesizes all agent outputs into a final, coherent assessment. Makes the position call.
"The final decision"
How AI Outlooks Work
The Investment Orchestrator assigns one of five sentiment-based outlooks based on the combined analysis. These are not investment recommendations — they reflect our AI's assessment of the overall picture.
| Outlook | What It Means | Typical Conditions |
|---|---|---|
Strong Positive | Highly favorable data signals across multiple dimensions | Strong fundamentals, reasonable valuation, positive catalysts, high conviction |
Positive | Generally favorable outlook with solid supporting evidence | Good fundamentals, fair valuation, more positives than negatives |
Neutral | Balanced or mixed signals — no clear directional bias | Mixed signals, fair valuation, stable but uncertain outlook |
Negative | Concerning signals outweigh positive factors | Deteriorating fundamentals, elevated valuation risk, negative trends |
Strong Negative | Significant concerns across multiple dimensions | Material concerns, severe data gaps, structural issues, high risk |
Why sentiment labels? We use pure sentiment labels (Positive/Negative) instead of action words (Buy/Sell) to be clear that these are analytical assessments, not investment advice. Your investment decisions should consider your personal goals, risk tolerance, and circumstances.
Investor Profile Presets
Our Stock Screener includes pre-configured filter combinations that target different investment styles. Each preset combines AI analysis with relevant stock metrics to match your goals.
| Profile | What It Filters For | Best For |
|---|---|---|
| Value Investor | AI Positive + Good valuation vs peers + Strong financial health | Finding undervalued quality companies |
| Growth Seeker | AI Positive + High growth scores + Positive momentum | Prioritizing revenue/earnings growth |
| Income Focused | Dividend yield ≥3% + Strong balance sheet + No AI red flags | Dividend income and stability |
| Quality Hunter | AI Strong Positive + Excellent health + Above-average performance | Premium companies with high conviction |
| Momentum Trader | AI Positive + Strong recent returns + Bullish technicals | Trend-following strategies |
| Defensive | Large cap + Strong health + No AI concerns | Lower-risk, established companies |
How it works: Each preset applies multiple filters simultaneously. For example, "Value Investor" requires BOTH a positive AI outlook AND above-average valuation metrics. This ensures you're not just relying on one signal but getting confirmation from multiple angles.
Transparency: What the AI Considers
Here are the key factors that influence our assessments:
Recent financial performance vs. expectations
Comparison to industry peers (standard taxonomy)
Market sentiment from news and events
Technical price patterns and momentum
Data quality and recency of information
Explicit contradictions between narrative and numbers
Macroeconomic factors affecting the sector
Management quality signals from reports
How it accelerates your workflow
Idea Generation
Find companies matching specific criteria instantly. "Show me profitable tech companies in Norway "
Risk Assessment
Quickly identify red flags in recent earnings reports or negative market sentiment changes.
Earnings Summaries
Get the tl;dr on a 50-page Q3 report in seconds, highlighting only what matters for valuation.
Complex Comparisons
Ask it to compare margin metrics between DNB and Storebrand over the last 3 years.
Understanding the Limitations
While our AI system is powerful, it is an analytical tool, not a financial advisor. It uses LLMs configured specifically for financial tasks, which means it can still occasionally hallucinate or misinterpret nuanced data.
Always use the AI as a starting point. Verify critical numbers before making investment decisions. SignalInvest Haughom is an independent entity and does not provide financial advice.