Product Guide

Your AI
Department

17 products. 6 months. One system that compounds. Each product builds on the last — the knowledge base connects everything, the portal surfaces it, and the agents run 24/7.

This isn't a chatbot upgrade. It's a complete AI intelligence department — research, trading, communications, and operations — built for a team of 7.

17
Products
4
Live today
6
Months
100%
You own it
Build Timeline

6-Month Delivery Sequence

Live
Foundation
4 products
Month 1
Intelligence
2 products
Month 2
Agents + KB
3 products
Month 3
Trading
1 product
Month 4
Comms
3 products
Month 5
Advanced
2 products
Month 6
Handoff
2 products

Live Today

Operational

These systems are running in production right now. The foundation everything else builds on.

Mímir Research Assistant
AI analyst in Slack — search your entire broker corpus with natural language. 30K chunks, 29 brokers, sourced answers.

Ask anything about your broker research — "What does Goldman say about oil?" — and Mímir searches your private corpus, synthesizes across brokers, and responds with sourced citations.

Key capabilities
  • Natural language search across your full research corpus
  • Thread memory — follow-up questions understand context
  • Broker filtering with 38+ org name variants resolved
  • Coverage monitoring — spot rising topics before consensus forms
What makes it different from ChatGPT

ChatGPT knows what the internet knows. Mímir knows what your broker reports say. Every claim links back to the specific report, page, and date.

Daily Brief
Automated morning intelligence report from the last 24 hours. Thematic buckets, high-impact flags, portfolio outlook.

Every morning, Mímir clusters the day's documents by topic, ranks themes by broker consensus, and generates a structured brief prioritized for Viska's portfolio.

What you get
  • Portfolio outlook with cross-asset implications
  • Thematic buckets that adjust as topics emerge
  • HIGH IMPACT flags on findings that move the needle
  • Source count and broker attribution for every section
  • 48-hour events calendar

Why it matters: 238 PDFs arrive daily. The brief means the important insight on page 12 of a Deutsche Bank note reaches the people who need it — before the market moves.

Report Studio
Turn any research conversation into a polished deliverable — IC-ready, LP-ready, or social-ready — with one command.
Output formats
  • IC-ready — structured briefing with executive summary, key findings, source appendix
  • LP-ready — condensed insights formatted for investor updates
  • Social-ready — LinkedIn or newsletter format with professional tone

Type /report after any Mímir conversation. The system extracts key findings, preserves citations, structures for the chosen audience, and generates a permanent link.

Viska Portal
Bloomberg-style 8-section intelligence dashboard. F1–F8 command strip. Chat and Reports live — 6 more sections activating.
Sections
  • F1 Macro — Cross-asset macro intelligence
  • F2 TA — Technical analysis and chart signals
  • F3 Corpus — Broker activity, theme detection, coverage gaps
  • F4 News — Real-time news with financial relevance scoring
  • F5 Chat — Full Mímir chat with thread persistence
  • F6 Daily Reports — Archive of all briefs and reports
  • F7 Custom Reports — On-demand generation
  • F8 Products — This page

Month 1 — Intelligence Foundation

Building

Make the existing system bulletproof and add the interfaces that multiply access. Your corpus becomes available everywhere — not just Slack.

Mímir MCP
Access your research corpus from any AI tool — Claude Desktop, Cursor, or any MCP-compatible workspace. Not locked to Slack.

Your team already uses Claude or other AI tools. MCP means you can pull Mímir's research into any conversation — "What do our brokers say about semiconductor supply chains?" works from Slack, Claude Desktop, or an IDE.

MCP is an open protocol that lets AI assistants connect to external data sources. Mímir exposes its search as an MCP server. Any compatible tool can query it.

Macro Research Pipeline
Expand ingestion beyond broker PDFs — central bank minutes, earnings transcripts, policy documents, economic data feeds.
New sources
  • ECB, Fed, BoJ, BoE minutes and speeches
  • Corporate earnings transcripts
  • Economic data releases (GDP, CPI, employment, PMI)
  • Policy documents and regulatory filings

Impact: Cross-references become possible — "Goldman says inflation is cooling, but today's CPI print contradicts their view." The system connects broker opinion to primary data.

Month 2 — Multi-Agent Analysis + Knowledge Base

Building

From one bot answering questions to specialized agents running 24/7 surveillance — backed by institutional memory that connects everything.

Viska Knowledge Base
Institutional memory — not search. Understands decisions, tracks how thinking evolves, connects entities across your entire organization.
What it stores
  • Fund documents (LPA, side letters, DDQs, compliance) — structured, cross-linked
  • IC decisions with full decision trails — what was approved, rejected, and why
  • Entity relationships — LPs linked to meetings linked to follow-ups
  • Trade rationale — "Why did we enter this position?" with the actual decision chain
What you can ask
"What alternatives were considered when we chose the co-invest structure?"
"Has our thesis on European infrastructure changed since Q3?"
"Show me all IC meetings where BTC allocation was discussed"
"What was our reasoning when we increased energy weighting?"
How it's different from Mímir search

Mímir does vector search — find text similar to your question. The knowledge base adds temporal reasoning ("what did we decide before the rebalancing?"), relationship traversal ("all LPs who attended meetings about Fund X"), and decision archaeology ("what was rejected, and why?").

This is the difference between a search engine and institutional memory.

Analysis Agents
Three autonomous agents — Crypto, Macro Sentiment, Geopolitical Risk — running 24/7 surveillance. Under €200/month total.
Crypto Agent

On-chain metrics, exchange flows, funding rates, liquidation data. Reports anomalies — unusual accumulation patterns, whale movements. Writes findings to the knowledge base.

Macro Sentiment Agent

Cross-asset radar — FX, rates, commodities, equity indices. Daily conviction scoring. Flags divergences when data contradicts broker consensus.

Geopolitical Risk Scanner

Regulatory filings, sanctions, elections, policy shifts. Monitors jurisdictions relevant to your portfolio. Flags risk events before they become consensus trades.

Document Intelligence
Earnings call analysis and document comparison — track how broker views evolve, detect narrative drift over time.
Earnings Call Analysis

Feed any transcript, get structured output: key metrics, guidance changes, management tone shifts. Compare across quarters — "How has Meta's capex guidance changed over 4 quarters?"

Document Comparison

Track how a broker's view evolves — "How has Goldman's oil price target changed in 3 months?" with specific quotes and dates. Narrative drift detection — when language shifts from "cautiously optimistic" to "neutral," the system flags it.

Month 3 — Trading War Room

Building

Move from research to action. Live market intelligence, technical analysis, trade journaling, and mechanical risk discipline. Most of the automation layer is already built — Month 3 is deployment.

Trading Command Center
5-page Bloomberg-style trading interface — portfolio overview, trade journal, market page, session log, risk monitor. Plus Grok narrative tracking and 63 quantitative tools.
Dashboard Pages
  • Portfolio — equity curve, position tracking, P&L attribution
  • Trade Journal — decision chains, thesis blocks, entry/exit rationale
  • Market — real-time prices, volume, indicators
  • Session Log — tracking each trading day's activity
  • Risk Monitor — position sizing, exposure, consecutive-loss tracking
Grok Narrative Tracking

Real-time social sentiment from X via Grok — catches narrative shifts before they move price. Paired with Claude for deeper analysis.

Risk Framework
  • Position sizing rules, consecutive-loss gates, mandatory reflection triggers
  • Every trade requires human approval (schema-enforced)
  • 90-day paper trading period before any live capital — hard gate
Already built

4 agent repos, 7/8 n8n automations live, Alpaca brokerage integration, FRED economic data, QuantOracle (63 quant tools), risk framework approved, dashboard designed.

Month 4 — Communications & Content

Planned

Turn the intelligence system outward — LP reporting, thought leadership, brand building. The bottleneck isn't performance, it's communication bandwidth.

Investor Communications Engine
Automated LP letters, performance attribution, meeting briefings and follow-ups. You review and approve — never start from a blank page.
Monthly LP Letters

Drafted from portfolio data + market context. Performance attribution auto-generated. Consistent voice across every letter.

Meeting Briefing System
  • Before: Deep research on the prospect — portfolio, interests, board connections, recent news
  • During: Talking points generated from the research
  • After: Personalized follow-up referencing specific discussion points
Content Engine
2–3 polished pieces per week — newsletters, LinkedIn, short-form analysis. Icelandic + English. Your voice, not generic AI.

Viska's edge is macro thinking. The content engine solves the production bottleneck without diluting intellectual quality — AI drafts from your corpus, your team reviews.

  • Drafts from research corpus, daily briefs, and market positions
  • Your team's voice and thesis, not generic AI content
  • Review and approval before anything publishes
  • Content calendar with consistent cadence
  • Performance tracking — what's resonating, who's engaging
CRM Intelligence
LP relationships, meeting history, and follow-ups as entities in the knowledge graph. Intelligent relationship layer, not a spreadsheet.
What you can query
"Which LPs expressed interest in AI infrastructure?"
"When did we last meet with [family office]?"
"Who should we follow up with this month?"
"Prospects who attended our last event and haven't committed"

Feeds the meeting briefing system, the content engine (personalized outreach), and the knowledge base (relationship history as institutional memory).

Month 5 — Advanced Intelligence

Planned

Unique capabilities no off-the-shelf tool provides. The system starts thinking ahead — modeling scenarios, watching partners, identifying blind spots.

Scenario Modeling Lab
Deep overnight analysis of complex macro scenarios. Ask a question in the evening, get structured scenario analysis by morning.
Example queries
"What happens to crypto allocations in a stagflation environment?"
"Model the impact of an Iran oil shock on our Macro fund positions"

Claude's extended thinking mode processes your full research corpus, market data, and historical analogies overnight. Output: scenario description, probability assessment, portfolio impact, recommended actions, supporting evidence.

Distribution Partner Intelligence
Continuous monitoring of potential partners — regulatory filings, AUM shifts, personnel changes, news. Living intelligence, not one-time DD.
What it monitors
  • Regulatory filings and compliance status
  • AUM changes and fund flow data
  • Personnel moves — hires, departures, board changes
  • Media coverage and sentiment
  • Cross-references with your existing network

Weekly automated scan. Turns partner due diligence from a one-time exercise into continuous surveillance.

Month 6 — Autonomy & Handoff

Handoff

The system runs without me. You own everything — GitHub repo, all infrastructure, all documentation. 100% handoff.

Proprietary Signal Generator
Fine-tuned model on your macro framework. Turns qualitative conviction into quantitative signals. Runs on your infrastructure — IP protected.

Train a lightweight model on your team's research output, IC minutes, and historical positions. The model learns your analytical framework — what factors matter, how you weight them, what patterns you act on.

What it is NOT: A black box that trades for you. It's a tool that translates your thinking into systematic signals. Every signal requires human interpretation and approval.

System Handoff Package
Complete codebase on GitHub, architecture docs, runbooks, system health dashboard, and team training. Any developer can maintain it.
Deliverables
  • Viska GitHub — complete codebase, all agents, all configurations
  • Architecture documentation — how everything connects, data flows, dependency maps
  • Runbooks — how to operate, extend, and troubleshoot every component
  • System health dashboard — real-time status of all agents and pipelines
  • Knowledge transfer — team trained on operation and extension

After handoff: Optional maintenance retainer (ISK 250,000/month). The system runs independently — you can bring in any developer, or continue with support.