MOSAICFINANCEMOSAICFINANCEMOSAICFINANCE
Try Archivist CLI / MCP

AI for Financial Research

Ask Archivist a question, get answers grounded in exchange filings all over the world.

Company:Filing Type:Date Range:
  • NYSE…
  • NYSE American…
  • NASDAQ…
  • TSX…
  • TSX-V…
  • CSE…
  • NEO…
  • Borsa İstanbul…

CoverageLast Updated: …

… Symbols… Filings

Integrates withClaudeChatGPTGeminiLocal LLMsBacked byGoogle Cloud for Startups

What sets us apart?

Deep Coverage

Filings are the origination point of all financial information , we cut straight to the source with our ingestion and processing  across many exchanges. We process 1500+ types of filings whole .

We will find it

We shine when the answer is specific and buried: a covenant in a footnote, a metric few vendors extract. To achieve our edge we use every trick in the book  plus some of our own in our indexing and search algorithms. 

Every fact cited

Archivist reads the original filings themselves.  Every statement links to its passage, and one click opens the filing beside your answer, scrolled there and highlighted.  Just want the relevant text? Hover a citation to read the passage without opening anything. [6]

Crosschecked

Every answer is checked against both the filings and the web, and we keep what holds up. You always see exactly how far the evidence goes. 

Integrates

Research in the browser, or bring Archivist CLI / MCP into Claude Code, Codex and any agent you already use. Chat, grids across many companies and cited passages work the same everywhere, and every run is saved to your account for review. 

How It Works

  1. 1

    Ask

    Type a question about any public company in natural language. Add filters to your desire or not, Archivist will figure it out.

    Step 1: Ask
  2. 2

    Get Cited Answers

    Every answer comes with citation badges linked to the exact source. Hover any badge to preview the passage, click to open the filing.

    Step 2: Get Cited Answers
  3. 3

    Verify

    Click any citation to open the original filing. The PDF viewer highlights the exact section so you can verify every claim against the source document.

    Step 3: Verify

There is more to it for you to discover. Get started with your first 10 queries on us.

Our story

Built by people who read the footnotes.

We are a team with experience across a wide array of fields, from deal making and corporate finance to mining, energy, law and cybersecurity. All of it taught us the same thing: the market is loud with noise and opinion, while the facts sit quietly elsewhere.

Accuracy comes down to how many eyeballs get to check the work, so we put yours on every answer. Each one cites its source and takes you to the exact passage.

The companies we followed, with different motivations and questions, across different geographies and languages, required a better search tool that nothing quite answered. So we built the thing we wanted.

Tunc KaradutHakan AzakliogluMelody ZhangThe Mosaic Finance teamFounders of ArchivistMore about us

Behind the Architecture

We talk about what we're building in our blog. Transparency is the product.

Featured8 min
AI Misconceptions and Factual Realities: An Overview

A comprehensive overview of common AI misconceptions and the factual realities that should guide engineering decisions.

Deep Dive6 min
The 40% Failure Rate: Autonomous Agents and Error Compounding

The math on autonomous agents is brutal. Chain 10 steps at 95% accuracy each and your total success rate is 60%. The hype ignores exponential decay.

Deep Dive6 min
Beyond Magic Words: System Engineering for AI

If your system breaks because you changed an adjective, the problem isn't your prompt; it's your architecture. The mature approach is System Engineering.

Deep Dive5 min
Fine-Tuning is Brain Surgery: Why Context Wins

Fine-tuning is effective for teaching form but terrible for injecting facts. The 'domain-specific fine-tuned model' pitch is mostly marketing.

Deep Dive5 min
Lost in the Middle: Why Big Context ≠ Better Retrieval

Million-token context windows sound impressive. The reality: models struggle to retrieve information buried in the middle of long prompts.

Deep Dive6 min
The Blackbox Myth: Determinism in AI

The 'blackbox' narrative is convenient but wrong. AI models are sequences of math operations. Control the arithmetic, control the output.

Deep Dive5 min
Stochastic Parrots: Why LLMs Don't Think

LLMs predict the next token. That's it. They've mastered linguistic form without possessing communicative intent.

Deep Dive4 min
Code First: When AI is the Wrong Tool

If code can do it, code should do it. There's a concerning number of AI automations that shouldn't be AI automations.

Deep Dive5 min
Smaller, Cheaper, Better: The Economics of Accuracy

The industry conflates 'bigger' with 'better.' This ignores basic math. Running a cheaper model multiple times beats expensive single passes.

Featured8 min
AI Misconceptions and Factual Realities: An Overview

A comprehensive overview of common AI misconceptions and the factual realities that should guide engineering decisions.

Deep Dive6 min
The 40% Failure Rate: Autonomous Agents and Error Compounding

The math on autonomous agents is brutal. Chain 10 steps at 95% accuracy each and your total success rate is 60%. The hype ignores exponential decay.

Deep Dive6 min
Beyond Magic Words: System Engineering for AI

If your system breaks because you changed an adjective, the problem isn't your prompt; it's your architecture. The mature approach is System Engineering.

Deep Dive5 min
Fine-Tuning is Brain Surgery: Why Context Wins

Fine-tuning is effective for teaching form but terrible for injecting facts. The 'domain-specific fine-tuned model' pitch is mostly marketing.

Deep Dive5 min
Lost in the Middle: Why Big Context ≠ Better Retrieval

Million-token context windows sound impressive. The reality: models struggle to retrieve information buried in the middle of long prompts.

Deep Dive6 min
The Blackbox Myth: Determinism in AI

The 'blackbox' narrative is convenient but wrong. AI models are sequences of math operations. Control the arithmetic, control the output.

Deep Dive5 min
Stochastic Parrots: Why LLMs Don't Think

LLMs predict the next token. That's it. They've mastered linguistic form without possessing communicative intent.

Deep Dive4 min
Code First: When AI is the Wrong Tool

If code can do it, code should do it. There's a concerning number of AI automations that shouldn't be AI automations.

Deep Dive5 min
Smaller, Cheaper, Better: The Economics of Accuracy

The industry conflates 'bigger' with 'better.' This ignores basic math. Running a cheaper model multiple times beats expensive single passes.

Read All Articles