We only use essential cookies and local storage required for authentication, preferences, and core functionality. We do not use analytics, advertising, or third-party tracking technologies. Privacy · Terms
Research

Every ticker, argued from both sides.

You have a ticker. Deep Research puts it through 13 roles, a two-round Bull/Bear debate and a risk team before it answers; the Investment Committee scores it eight investors’ ways plus four quant analysts, with no model at all; and the Copilot answers your questions from the literal data on screen — or turns into an agent that does the legwork.

Launch VersatumThen validate the trade
Deep Research · Multi-Agent

A 13-role research pipeline that argues before it answers.

Drop a ticker. Get a structured market read with bias, key levels, and an executable plan.

A 6-stage pipeline orchestrates 13 distinct roles and 18 model calls. Five analyst agents — Market, Sentiment, News, Fundamentals, Earnings — run in parallel and gather the evidence; Bull and Bear researchers debate it in two rounds; a Research Manager synthesizes a thesis; a Trader proposes an action; a 3-debater Risk team debates the plan; and a final Risk Manager renders the decision. From idea to BUY/SELL/HOLD with confidence, a stop and a target — an institutional-grade report with full reasoning chains, every reasoning step visible, and a transparent, replayable workflow behind it.

  • Stage 1 · Analysts — Market, Sentiment, News, Fundamentals and Earnings run in parallel and gather the evidence
  • Stage 2 · Debate — Bull and Bear researchers argue the thesis out over two rounds
  • Stage 3 · Research Manager — reads both rounds, picks a side with a confidence and synthesizes a thesis
  • Stage 4 · Trader — proposes an action and turns the call into a plan
  • Stage 5 · Risk debate — a 3-debater Risk team argues the plan for two more rounds
  • Stage 6 · Final decision — a Risk Manager signs BUY / SELL / HOLD with confidence, a stop and a target
  • Runs on equities (13 roles), crypto (12 roles) and forex (6 roles)
Deep Research
Analyst Agents
Analysts
Debate
Synthesis
Trade
Risk
Decision
5 Analysts
Market
RSI at 62, above 50-day SMA. Volume +18% avg...
Sentiment
Social sentiment +72% bullish. Institutional flow net positive...
News
Earnings beat Q3 est by 12%. New product launch catalyst...
Fundamentals
P/E 28.4 vs industry 31.2. FCF yield 3.8%. ROE expanding...
Earnings
Beat 4 of last 5 quarters. Rev growth +14% YoY...
Bull vs Bear
Round 1
Strong momentum with RSI confirmation above 60. Volume expansion supports uptrend continuation.
82
Valuation stretched at 28.4x earnings. Mean reversion risk increases above 2 standard deviations.
71
Round 2
Catalysts: product launch + earnings beat pattern. Institutional accumulation accelerating.
88
Macro headwinds: rate uncertainty and sector rotation risk. Put/call ratio rising.
65
Synthesis
Bullish case stronger78%
Technical momentum
Fundamental value
Catalyst timeline
Macro environment
Final Decision
BUY
Confidence82%
Entry$261.50
Target$285.00
Stop$248.20
Momentum + fundamentals alignment
Earnings catalyst in 14 days
Risk/reward ratio 1:1.8
13 AI Agents|6-stage pipeline
1/4

Market Agent

Price action, technicals, market structure, support/resistance levels

Sentiment Agent

Social media pulse, options flow sentiment, retail vs institutional positioning

News Agent

Breaking news, narrative shifts, media momentum, event catalysts

Fundamentals Agent

Financials, valuations, growth metrics, competitive moat analysis

Earnings Agent

Transcript NLP, guidance changes, estimate revisions, surprise history

Risk Team — 3 debaters

Two rounds over downside scenarios, correlations and tail risk, then a Risk Manager signs the decision

Synthesis Engine

All thirteen role outputs are synthesized into one report with confidence, risk assessment, actionable trade ideas, and full reasoning chains — individual agent analyses included. Each stage has its own versioned prompt from a shared registry of 35, so you can see what every role was actually asked. Crypto runs the same shape with 12 roles and 4 analysts across 6 stages, risk-team debate included; forex runs a shorter 3-stage version, also with 4 analysts — 6 roles, ending in a debate synthesis over central bank policy, carry trade context, and session liquidity.

Adversarial Debate

Bull vs Bear — the case gets challenged.

Inside Deep Research, the analysts’ work goes through two rounds of adversarial debate before anything is recommended. A Bull analyst builds the case, a Bear analyst attacks it, and a Research Manager rules on it and synthesizes the thesis; a Trader proposes the action. The Risk team — three risk personas — then debates the plan for two more rounds before a final Risk Manager signs the decision.

Bull Analyst

Builds the strongest case for the trade — catalysts, upside targets, momentum signals

Bear Analyst

Stress-tests every weakness — overvaluation risks, competitive threats, macro headwinds

Research Manager

Reads both rounds, picks a side with a confidence, and hands it to a Trader who turns the call into a plan

Investment Committee · Zero Model Calls

Eight investors, and no model at all.

A second opinion on the same ticker, with no model in it. Eight investor personas — Warren Buffett, Michael Burry, Charlie Munger, Cathie Wood, Benjamin Graham, Bill Ackman, Peter Lynch and Philip Fisher — are each a set of published criteria turned into arithmetic (value, growth, contrarian, activist, GARP, quality), and each scores the same name independently under its own rule set. Alongside them, four quant analysts (fundamentals, valuation, sentiment, technicals) score it too. Twelve independent signals, and a portfolio manager rolls the eight verdicts and the four quant analysts up into one committee call: an action, a confidence and a position size.

Rule-based and reproducible, not generative: the committee scores the same name eight ways in rule code, so its numbers reproduce line for line, and it shows the rule-based scorecard behind each of its eight personas. Two personas are on by default and you pick the rest. Run it on one ticker, or put the top names from the Stock Picker past it. Equities only, on paid plans.

WB
Warren Buffett

Value investing, economic moats, long-term compounding

MB
Michael Burry

Contrarian deep value, macro shorts, asymmetric bets

CM
Charlie Munger

Quality at fair price, mental models, patience

CW
Cathie Wood

Disruptive innovation, growth at scale, thematic ARK bets

BG
Benjamin Graham

Margin of safety, intrinsic value, deep-value screens

BA
Bill Ackman

Activist conviction bets, catalyst-driven, concentrated positions

PL
Peter Lynch

GARP, invest in what you know, tenbagger hunting

PF
Phil Fisher

Scuttlebutt research, growth quality, long compounders

+ 4 quant analysts
8 + 4 = 12 signals → portfolio manager
Fundamentals
Valuation
Sentiment
Technicals

The portfolio manager rolls all twelve into an action, a confidence and a position size.

This part has to be said plainly

The committee makes zero model calls. The personas do not debate, they do not converse, and there is no language model anywhere in the run — it is deterministic scoring in the style of eight famous investors, which is why the same inputs always produce the same committee. Do not count these eight toward any tally of AI models; the only model-derived input that reaches the committee at all is cached news sentiment, and an article we never managed to tag is dropped rather than counted as neutral.

AI Copilot · JSON-Grounded

Ask your data anything.

Context-aware AI at four levels — widget, tab, page, or routed for you. Grounded in the JSON on screen — never hallucinated. Every widget, chart, and data point on the platform is queryable.

Ask Copilot anything about the chart, financials, options chain, or insider trades you are looking at. It answers using only the literal data on screen, with citations. The Copilot runs on the same text model as the rest of the platform — what makes it specific to you is the context we assemble for it: your current page, your watchlist, your trading style, and your portfolio.

  • Four focus tiers — widget, then tab, then page, then intelligent routing — auto-route context, with Agent Mode above them
  • Fed only the literal JSON of the widget on screen: no data, no answer
  • Every answer cites the literal JSON it consumed
  • Every board hands off to Copilot with its own scope, so an answer is grounded in what is actually on screen
  • Every widget is a self-contained AI surface — its own context-aware Copilot, its own prompt grounding, its own export
  • 16 widget sources and 42 page contexts wired in, across 85 dashboard widgets
  • Adapts responses to your trading style — Day Trade, Swing Trade or Long-term (Position)
  • Ask about any stock, option, forex pair, crypto asset, or signal in plain English
AI Copilot
No Focus
General Chat
Chat
Context:No active context
What's the market outlook for tech stocks this quarter?
Ask about stocks, markets, signals...
Capabilities
Capabilities
Stock AnalysisPrice, technicals, fundamentals
Chart ReadingPatterns, support/resistance
Options StrategySpreads, greeks, IV analysis
AI SignalsML scores, sentiment, signals
Risk AssessmentPosition sizing, stop-loss
Response confidence84%
Context-Aware AI|General mode
1/4
Stated, not hidden

Explain, analyse, alert — then hand off.

Ask it to explain an AI signal, request a custom analysis, or have it create an alert — a Watch can be set up by just telling Copilot in plain English. When a question warrants it, Copilot auto-triggers Deep Research mid-chat, and an unmeasurable number is disclosed as such instead of rendered as zero. For autonomous multi-step work — shell, files, vision — switch into Agent Mode.

The meter is stated, not hidden. Every tier gets the same 65,536-token output budget, and the free tier is capped at 20,000 tokens a day, 10 Copilot runs and 1 Chart Patterns run — counted atomically and reset at UTC midnight. Paid tiers lift the daily token cap.

Versatum CopilotAI
What's the bull case for NVDA right now?
From the last Deep Research run, 4 of the 5 analysts are constructive. Market Agent has a breakout above resistance at $142, Fundamentals flags margin compression, News Agent reads the supply headlines as already priced. The Bull/Bear debate resolved bullish with medium confidence — here is each step...
Show me options strategies for my swing trade style
For your swing profile (2-10 day hold): bull call spread at $140/$150 (Mar 21 exp), risk-reward 1:3.2. Trade Validator scores it 71/100, which lands in the BUY band, and IV percentile is 42% — favorable for debit spreads...
Copilot Agent Mode · Pro+

From chat into a tool-calling deep agent.

Toggle the AI Copilot from chat into an autonomous, tool-calling deep agent — autonomous research at the click of a toggle. It plans multi-step research, executes shell commands in a sandbox, generates downloadable files, and uses vision on attached charts, showing its plan, every tool call and its shell output as live cards while it works.

Conversations are stable, persistent threaded sessions that follow you across devices. Agent Mode is one of three Pro+ features, alongside the Autonomous Trader and the RL Training Lab — and, with the Autonomous Trader, one of the two agentic systems that take Versatum beyond explanation: one runs continuous strategies, this one plans and acts. Both are built to be left alone: eight of our long runs survive navigation, so a 30-to-90-second scan keeps working if you change page mid-run. The same 166 tools are open to external Model Context Protocol clients through MCP keys.

AgenticTool-CallingPro+
  • Multi-step plans visible as todo cards
  • Sandboxed shell + file tools
  • Downloadable file generation
  • Image input — vision on attached charts
  • 166 MCP tools available to the agent
  • Stable, persistent threaded sessions that follow you across devices
  • Available on equities, options, crypto and forex
Copilot · Agent Mode
Plan
Pull NVDA price + earnings datescompleted
Run Deep Research on NVDA (13 roles)completed
Compute IV rank & Greeks for Mar 21 chainin progress
4
Score top 5 bull-call spreads by R/Rpending
5
Generate trade plan PDF + entry checklistpending
Tool Calls
shell(fetch_quote("NVDA"))ok
last 142.62 · vol 28.4M
deep_research(symbol=NVDA · 13 roles)ok
BUY · confluence 87/100
options_chain(NVDA · 2026-03-21)running
fetching 482 contracts…
compute(iv_rank · gex · max_pain)pending
—
write_file(nvda_trade_plan.pdf)pending
—
Generated Files
Generated by agent4 files
nvda_trade_plan.pdf
142 KB
PDF
nvda_options_screen.csv
38 KB
CSV
deep_research_NVDA_2026-06-05.md
12 KB
MD
iv_surface_chart.png
64 KB
IMG
Click any file to download
Vision Input
Read this chart and tell me the pattern
Bull flagConfidence 86%
Higher highs, higher lows. Breakout above 60 with measured-move target around 78. Stop near the most-recent swing low at 48.
Drop an image · charts · screenshots…
Multi-step plans · sandboxed tools|Files · Shell · Vision
1/4
Research Data

The reference shelf behind every read.

Four surfaces for the homework around a ticker — the company’s books, filings and holders; what the Street thinks it is worth; the macro backdrop; and how it stacks up against another name. Equity fundamentals, financials, analyst work and macro come from FMP — see Markets for the full data map.

Market Data

Company Explorer

Company by company: financials, filings, insider trades, and institutional holdings in one explorer.

Market Data

Analyst Ratings

Aggregated Wall Street analyst ratings, price targets, and consensus recommendations — an analyst ratings consensus engine over the Street’s published work.

Market Data

Macro & Economy

Macro indicators — GDP, inflation, unemployment, Fed rates, treasury yields — the backdrop every single-name read sits in.

Analysis

Compare Stocks

Side-by-side, multi-dimensional AI analysis comparing fundamentals, technicals, sentiment, and valuation.

Argue the ticker first.
Then trade it.

Deep Research, the Investment Committee and a JSON-grounded Copilot — every read shows the work behind it.

Start FreeSee Pricing