Companion Document · April 2026

Gáldr × Viska sjóðir

Building an AI Intelligence Department
Prepared for: Guðlaugur Steinarr Gíslason, CIO From: hello@galdr.gg Date: April 2026
01
Why This Document

The roadmap describes what we propose to build. This document explains why we build it the way we do — the reasoning behind architectural decisions, the landscape of available tools, the security model that protects the fund, and why this is careful, phased work rather than a quick installation.

02
The Landscape: What Exists Today

AI-assisted trading and investment research is no longer experimental. As of April 2026, three categories of tools are available to any fund manager:

1. Cloud Automation

Anthropic released Claude Routines on April 14, 2026. A routine is a saved Claude session — a prompt, connected repositories, and MCP connectors — that runs autonomously on cloud infrastructure. Routines can trigger on a schedule (hourly, daily, weekly), via API call, or in response to GitHub events.

This is a real product with real capabilities. A fund could set up a Routine today that runs every morning and summarizes overnight market news, triggers when a TradingView alert fires and logs the signal, or scans merged code changes weekly and flags drift.

What Routines cannot do: coordinate multiple agents with different roles. A Routine is a single session — one agent, one prompt, one execution. No persistent memory across runs. No awareness of other Routines. No risk enforcement across sessions, no portfolio-level awareness, no team dashboard.

A Routine is a capable individual contributor. What we are building is a department.

2. Open-Source Skill Libraries

The open-source community has produced substantial trading skill libraries for Claude. The most mature repository offers 40+ pre-built investment skills:

CategorySkillsExamples
Market analysis11Sector rotation, breadth analysis, macro regime detection
Stock screening8CANSLIM, VCP patterns, dividend growth, pair trades
Strategy & risk12Backtesting, scenario analysis, bubble detection, position sizing
Research pipeline6Edge candidate generation, hypothesis testing, signal aggregation
Self-improvement3Automated skill scoring, daily improvement loops, idea mining

These skills are well-engineered. Most require only a free-tier financial data API (250 requests/day).

What skill libraries cannot do: reason about your fund. They are generic — designed for individual retail investors running one analysis at a time. No concept of Viska Crypto vs Viska Macro, no awareness of your portfolio, no connection to your broker research corpus, no compliance awareness for sub-threshold AIFM limits. They produce analysis for “a stock.” We produce intelligence for your fund.

3. Autonomous Trading Agents

Fully autonomous trading frameworks exist. One major open-source platform supports stock, crypto, and derivatives execution across multiple brokers with a three-layer pipeline: signal generation, LLM-based decision making, and automated order execution.

We do not build this. Here is why:

This is not a hypothetical risk. This is what happens when trading infrastructure is assembled from unvetted components without security architecture.

03
What We Build Instead

We build a coordinated intelligence department where every component has a defined role, enforced boundaries, and auditable behaviour.

Single Agent vs Coordinated Team

Stock ToolGáldr Build
One session with a prompt4–16 agents with distinct roles and defined scope boundaries
Each session starts freshPersistent knowledge graph — the system remembers what it learned
No awareness of other sessionsAgents coordinate: the analyst's thesis feeds the risk manager's evaluation feeds the operator's decision
Generic analysisTailored to Viska's two funds, portfolio composition, and operational cadence
Runs when triggeredStructured sessions: pre-market, midday, end-of-session, plus alert-driven

A Day in the System

Before the team sits down in the morning, the system has already been working for hours:

06:00 ET Overnight Synthesis Pipeline Central bank publications, broker research corpus, 800,000+ FRED series. 07:00 ET Daily Intelligence Brief Themed report: overnight developments, high-impact flags, sentiment shifts. Slack + Portal. 08:00 ET Watchdog Pipeline Activates Position monitoring at 5-minute intervals. Alert hierarchy: L1 informational, L2 action, L3 immediate. 08:30 ET Pre-Market Trading Session — Four Agents Convene Operator reviews intelligence • Analyst presents trade ideas • Risk Manager evaluates checklist • Execution validates Throughout the day — TradingView webhooks arrive, validated, enriched, logged to portal 12:30 ET Midday Session Position review, thesis update, new signal evaluation. 16:15 ET End-of-Session Performance attribution. Trade journal entries. Risk framework reconciliation. FRIDAY Weekly Report: QuantStats tearsheet, P&L attribution, narrative summary
Operational cadence — a coordinated system, not a list of triggers

Nothing in this cadence is possible with a single Routine or a library of generic skills. It requires agents that know their roles, remember their context, and operate within enforced boundaries.

What We Adopt from the Ecosystem

We are not building everything from scratch. The ecosystem has strong components — we evaluate them rigorously and adopt what passes our six-criteria framework:

ComponentSourceWhy We Adopt It
FRED MCPFederal Reserve800,000+ macro data series. Official source. No ToS concerns.
QuantOracleMCP ecosystem63 deterministic quantitative tools. Production-grade.
AlpacaOfficial APIPaper + live trading. 70+ tools. Official, maintained, ToS-compliant.
OllamaLocal inferenceGemma 4 on own hardware. No API costs for synthesis tasks.
TradingView WebhooksOfficialAlert-driven signal intake. Supported, no scraping.
QuantStatsOpen sourcePerformance tearsheets for weekly reporting.
Select backtesting toolsOpen source (evaluated)Walk-forward testing, multi-timeframe screening. 8 of 30 available tools — the rest filtered out.

What we do not adopt: browser automation tools (ToS violation, fragile), unvetted community packages (supply chain risk), autonomous execution frameworks (judgment error risk), full tool suites without filtering (token waste).

What We Build Bespoke

ComponentWhy It Must Be Custom
Agent coordination layerNo stock tool coordinates 4–16 agents with role boundaries. This is the orchestration that makes the same AI model perform 6x better (Stanford/Tsinghua, March 2026).
Risk enforcementSchema-enforced. Unsigned trades cannot proceed. A hard gate in the architecture, not a suggestion in a prompt.
Viska PortalEvery page designed for the fund's workflows. Not a generic dashboard.
Knowledge graphPersistent, queryable memory across all sessions. The system improves because it remembers.
Fund-specific contextViska Crypto and Viska Macro have different instruments, risk profiles, and reporting needs. Generic tools cannot distinguish them.
Compliance monitoringSub-threshold AIFM under Act 45/2020 has specific limits. No open-source tool monitors Icelandic regulatory thresholds.
Credential isolationAPI keys never enter the AI reasoning layer. Runtime injection via sandbox. The AI uses credentials but cannot see, extract, or leak them.
LP communications pipelineFormatted to your standards, grounded in your performance data, written in your voice.
04
Security as Architecture

Security is not a feature we add at the end. It is the foundation on which everything else is built.

The Threat Model for AI-Augmented Funds

ThreatReal-World ExampleOur Mitigation
Supply chain attackFebruary 2026: 1,184 malicious skills distributed wallet-stealing malware. 14,285 downloads before detection.Every dependency evaluated against six criteria. Package versions pinned to specific commits. No community marketplace — skills authored and reviewed internally.
Credential exposure21,000 AI agent instances found publicly accessible with unprotected API keys, wallet access, and chat logs.Credential isolation: keys exist only in a runtime sandbox. The AI layer never sees credential values.
Scope violationGeneric assistants prompted to exceed intended function — a research agent asked to execute trades.Mechanical scope enforcement. Each agent has a defined domain. The research agent literally cannot call the trading API.
Autonomous execution riskAutonomous trading bots executing without human review. LLM interpretation introduces judgment errors that compound.Human approval is permanent and schema-enforced. Every order requires explicit approval. This is a design principle, not a Phase 1 safeguard.
Data poisoningAI systems ingesting unvalidated data — fake news, manipulated sentiment, spoofed market data.Sourced data only. Broker research from known providers. Central bank data from official feeds. Market data from regulated broker.
Dashboard credential leakWeb dashboards embedding API keys in frontend JavaScript, exposing them via browser developer tools.Read-only frontend. A server-side proxy handles all authenticated requests. The browser sees rendered data only.

Credential Isolation in Practice

This is worth explaining because it is the question most CIOs ask: “How can AI trade on our behalf without seeing our API keys?”

AI REASONING LAYER Analyst Research & thesis Risk Manager 8-item checklist Operator Synthesis & decision “Place buy order for AAPL, 50 shares” CREDENTIAL ISOLATION BOUNDARY RUNTIME SANDBOX Execution Agent ✓ operator_approved ✓ buy_only ✓ market_hours ✓ size_validated Alpaca API key injected at runtime never visible to agents If this conversation were leaked, there are no credentials in it.
Credential isolation — the AI uses credentials but cannot see, extract, or leak them

The agent says “place this order.” The sandbox injects the API key into the outbound request. The agent never sees the key value. If the agent's conversation were leaked, exfiltrated, or logged — there are no credentials in it.

05
Why Six Months

Each phase builds on the previous. Skipping phases creates an intelligence system that has no foundation to stand on.

Month 1: Foundation — Macro Research Intelligence

What we build: The research corpus. Every subsequent agent depends on this — the trading analyst needs macro context, the risk manager needs economic data, the LP communications need sourced intelligence.

Why it takes a month: Broker research corpus must be ingested, indexed, and made queryable (400,000+ words). Central bank pipelines need validation against official sources. FRED integration needs configuration for Viska's relevant series. Daily intelligence brief needs calibration with the team.

End of Month 1: A queryable research corpus. A daily intelligence brief delivered every morning. Central bank data on autopilot. Macro data accessible from any workspace.

Month 2: Awareness — Multi-Agent Surveillance

What we build: Three autonomous surveillance agents running 24/7 — crypto, macro sentiment, geopolitical risk. Alert pipeline with L1/L2/L3 hierarchy.

Why it depends on Month 1: Surveillance agents need the research corpus as context. “BTC down 5%” is noise. “BTC down 5% ahead of FOMC meeting with hawkish expectations” is intelligence. The alert hierarchy needs Month 1's baseline of “normal.”

End of Month 2: Three agents watching markets around the clock. Anomaly detection. Sentiment scoring. Geopolitical risk monitoring. Prioritised alert pipeline.

Month 3: Operations — Trading War Room

What we build: Four-agent trading operation. Paper trading on Alpaca. Risk enforcement. 7-page dashboard.

Why it depends on Months 1–2: The Trading Operator synthesises surveillance output (Month 2) and research intelligence (Month 1). The Technical Analyst uses FRED data and QuantOracle for quantitative confirmation. The dashboard displays data that automation pipelines produce — building it first would show empty pages.

The 90-Day Paper Trading Gate

Paper trading begins in Month 3 and runs through Month 5. This is a hard gate: no live capital until the record demonstrates:

MetricThreshold
Minimum paper trading days90
Risk framework compliance100% (no bypassed gates)
System uptime>95% during market hours
Order accuracy100% (every order matches approved parameters)
Decision audit trailComplete (every trade traceable from thesis to execution)

During paper trading, the system operates exactly as it would with live capital. The team reviews trades, calibrates risk parameters, and identifies failure modes — all without financial exposure.

End of Month 3: An operational trading system in paper mode. A 7-page dashboard. Slack integration. The system is running — it just isn't touching real capital yet.

Month 4: Communications — LP & Content Pipeline

What we build: Automated LP letter generation, thought leadership content (2–3 pieces per week), meeting intelligence for fundraising.

Why it depends on Months 1–3: LP letters require performance data from the trading system and macro context from the research corpus. Thought leadership needs the team's investment thesis as input — this emerges from trading sessions, not from a prompt.

End of Month 4: First drafts of LP letters. 2–3 thought leadership pieces per week. Pre-meeting research briefs and post-meeting follow-up drafts.

Month 5: Intelligence — Scenario Modelling & Proprietary Signals

What we build: Overnight scenario analysis lab. Proprietary signal generator on Viska infrastructure.

Why it depends on Months 1–4: Scenario modelling requires 4 months of operational data to calibrate. Signal generation requires the backtesting framework and macro data. Signals are backtested, walk-forward tested, and validated before deployment.

End of Month 5: Overnight scenario reports with probability assessments and portfolio impact projections. Proprietary signals from Viska's own framework.

Month 6: Handoff — Distribution Intelligence & Ownership Transfer

What we build: Distribution partner surveillance, complete documentation, team training, and full ownership transfer.

DeliverableDetail
All source codeOn Viska's GitHub organisation. Every repository, every commit, full history.
Knowledge baseOn Viska's database instance. All ingested research, decision logs, agent memory.
AI subscriptionOn mimir@viskasjodir.is. No dependency on Gáldr accounts.
Dashboard & portalOn Viska's domain. DNS transfer, SSL certificates, hosting configuration.
Automation pipelinesOn Viska's automation instance. Self-hosted, auditable, full ownership.
DocumentationArchitecture guide, operational runbook, agent configuration reference, troubleshooting guide.
Team trainingDaily operations, agent management, pipeline monitoring, portal administration, system expansion.
Support periodPost-handoff support window during the team's transition to independent operation.

After Month 6, Viska operates the system independently. Nothing is locked in — no proprietary platform, no SaaS dependency, no vendor that must remain involved. The intelligence department belongs to the fund.

06
The Harness Engineering Thesis

Why does orchestration matter more than the AI model itself?

Stanford and Tsinghua research (March 2026) demonstrated that the same AI model delivers a 6x performance difference depending on how it is orchestrated. The model is a commodity — the same Claude, GPT, or Gemini is available to every fund. What determines performance is the harness: how agents are structured, what context they receive, how they coordinate, what boundaries they operate within.

1. Subtract Before You Add

One company removed 80% of its available tools and saw better results. An agent with 43 tools spends most of its reasoning capacity deciding which tool to use, not using it well. Our agents have focused, curated toolsets:

AgentToolsWhy These
Trading OperatorAlpaca, FRED, OllamaMarket data, macro context, local synthesis. Does NOT need screening tools — that's the analyst's job.
Technical AnalystAlpaca, FRED, QuantOracle, SQLiteData access and quantitative tools. Does NOT need order execution — different agent, different permissions.
Risk ManagerAlpaca, QuantOracle, SQLitePortfolio awareness and quantitative validation. Does NOT need research corpus — risk uses numbers, not narratives.
Execution AgentAlpaca, SQLiteOrder submission and logging. Narrowest toolset because most consequential action: moving capital.

2. Build the Layer That Survives

AI models are replaced every few months. Claude 3 → 3.5 → 4 → 4.5 — each generation more capable. Any investment in a specific model's quirks depreciates rapidly.

The orchestration layer — how agents are structured, what data flows between them, how risk is enforced — transfers across model generations. When a better model ships, we swap it in and the entire system improves. The harness compounds; the model depreciates.

3. Govern First, Optimise Second

Speed without governance produces faster mistakes. Every component has governance before optimisation:

The February 2026 supply-chain attack affected a platform that optimised for capability before governance. 21,000 instances with no authentication. 1,184 malicious skills. When the attack hit, there was no audit trail to determine which accounts were compromised, no scope boundaries to limit damage, no credential isolation to protect wallets.

We build governance into the foundation so that when — not if — something unexpected happens, the blast radius is contained and the audit trail is complete.

07
Capability Progression

What the team can do at each milestone. Once introduced, capabilities persist through all subsequent months.

MONTH 1 Foundation Research corpus Daily brief Central bank pipeline Workspace access MONTH 2 Awareness + Month 1 Crypto surveillance Sentiment monitoring Geopolitical alerts NLP scoring MONTH 3 Operations + Months 1–2 Paper trading (4 agents) Risk enforcement 7-page dashboard TradingView intake 63 quantitative tools MONTH 4 Communications + Months 1–3 LP letter drafts Thought leadership Meeting intelligence MONTH 5 Intelligence + Months 1–4 Scenario modelling Proprietary signals MONTH 6 Handoff + Months 1–5 Full ownership
Capabilities stack — each month builds on the foundation of all previous months
CapabilityM1M2M3M4M5M6
Query research corpus+·····
Daily intelligence brief+·····
Central bank data pipeline+·····
Workspace access+·····
24/7 crypto surveillance+····
Macro sentiment monitoring+····
Geopolitical risk alerts+····
NLP sentiment scoring+····
Paper trading (4 agents)+···
Risk enforcement (8 rules)+···
7-page trading dashboard+···
TradingView signal intake+···
63 quantitative analysis tools+···
Automated LP letter drafts+··
Thought leadership (2–3/wk)+··
Meeting intelligence+··
Overnight scenario modelling+·
Proprietary signal generation+·
Distribution partner surveillance+
Full codebase ownership+
Team training & documentation+

+ = introduced that month. · = persists from previous month.