Skip to content
Convexity
Start free

Analysts

Tuesday, October 20, 2026

The independent’s research desk. Filings, flow, and macro on one surface.

Sell-side analysts got a terminal. Independents got a browser bookmark bar. Convexity is the terminal built for the second group, and every number in it carries the primary source it came from.

Start freeSee pricing

Written for independent research practices, family offices and equity boutiques.

I. The Gap

The independent analyst’s job hasn’t changed in twenty years: read the 10-K, diff the risk factors, hear the call, check the insider ledger, triangulate macro, and write it up with citations a reader can follow back¹.

The tools around it have calcified into a stack. Full-text search surfaces the wrong filing, PDF tables get retyped into Excel, and a transcript gets scrolled for one half-remembered quote.

A Form 4 feed sits in one tab, a FRED chart in another, FOMC speeches in a third, and at night every citation is re-pasted into a Google Doc so the footnotes hold.

Convexity is built for the independent: not a Bloomberg replacement, but a research surface shaped around the work².

“The job hasn't changed. The tools have. Read the 10-K, diff it against last year, listen to the call, check the insider ledger, triangulate macro, write it up.– the thesis of this page, in one line
II. One Morning, Two Workflows

A typical morning, set against the same morning on Convexity. Same job, two different shapes of effort.

Before

A morning in twelve tabs

  1. EDGAR full-text search for the 10-Q you actually want.
  2. Copy tables out of a PDF and into Excel by hand.
  3. Scroll a transcript provider for one quote you remember.
  4. Cross-check a Form 4 against last quarter's cluster.
  5. Open a second browser for FRED, a third for FOMC speeches.
  6. Re-paste every citation into a Google Doc that night.
After

The same morning, one workspace

  1. EDGAR XBRL normalized across 10-K, 10-Q, and 20-F periods.
  2. 8-K timeline with item codes and a severity read per filing.
  3. Form 4 ledger with cluster and role weighting.
  4. FedSpeak NLP for policy tone and language shifts.
  5. Patent filings indexed by assignee, hiring signals alongside.
  6. Draft memo with every claim cited back to its source.
III. The Analyst's Day
  1. 08:00

    Morning brief.

    Overnight filings, insider moves, macro prints. Auto-curated at /market-brief.

  2. 09:30

    Open.

    Scan the 8-K timeline for every name on the watchlist. One surface, one scroll, item codes and severity on every filing.

  3. 11:00

    Cross-check.

    Form 4 cluster vs. insider ledger vs. 10-K risk-factor diff. Three sources, one ticker page, one thesis forming.

  4. 14:00

    Deep dive.

    XBRL compare across periods, plus patent and hiring cross-reference. Live at /sec.

  5. 16:30

    Memo draft.

    AI stitches primary sources into a cited draft. Luna / Sonnet / Opus routed by tier at /research.

  6. 19:00

    Distribute.

    Shareable memo link (Pro Plus) or PDF export. Send a clip, not a file. Citations resolve back to the exact paragraph.

IV. Workflows in Detail

Three surfaces, each designed around a specific part of the craft.

Filingspg. 04

10-K to model in an afternoon.

Filings are indexed and XBRL-parsed, so three periods of income statement compare without Excel. 8-Ks run as an event timeline, each tagged with its item codes and a severity read: inflection points, not a stack of PDFs.

Pro Plus adds semantic search across the filing corpus, on Voyage embeddings, so “every time this management team described margin pressure in five years” is a query, not a project.

Risk-factor diffs flag additions, deletions and tone shifts year over year, and the AI annotates the change, not the paragraph.

Signalspg. 06

Insider, 8-K, patent, hiring on one ticker page.

A thesis rarely lives in the income statement alone, so the ticker view carries Form 4 insider flow, 13F holdings, congressional trades, USPTO patents, H-1B talent flows, ATS job postings and 8-K events beside the financials.

Insider flow is read with context (clusters, officer roles, transaction types), so a CEO’s open-market purchase doesn’t look like a 10b5-1 plan sale.

FedSpeak NLP lays FOMC speeches, minutes and FRED series on the same surface, for the days a sector thesis is secretly a rates thesis.

Modelingpg. 08

A model row that already knows the answer.

The ticker page lands with the numbers modelers stitch together by hand: trailing and forward PEG, price targets, the grade table, EPS surprise history with its beat and miss streaks, revenue by product and geography, and a DCF baseline.

The peer set picks itself from FMP’s sector cohort, so there is no peer hunting.

Convexity Score is the proprietary signal: a Ridge composite forecasting the sector-neutral return over the next 180 trading days.

Its six features are momentum, insider net flow, smart-money positioning, low-vol beta, gamma and revenue-growth acceleration.

It refits nightly for large caps above a $25B floor, and every published vintage is scored against what the market did. The record and the methodology are public at /methodology/convexity-score.

Live at/stock/{ticker}Convexity ScorePEG · grades · EPSDCF · segmentation
Synthesispg. 10

Memo drafts that cite their sources.

The AI is routed by tier, GPT-6 Luna on Free, Claude Sonnet on Pro and Claude Opus on Pro Plus, with cross-vendor fallbacks for uptime.

Retrieval runs on Voyage embeddings over the filing corpus, so answers come from primary sources, and a claim without a citation isn’t made.

Pro Plus adds 20 deep-research runs a month: long, multi-source jobs across filings, the 8-K corpus and a curated news feed.

A risk-factor comparison checked against a two-week-old insider cluster becomes one prompt, not forty minutes on EDGAR.

V. The Honest Comparison

Convexity doesn’t replace a Bloomberg-class terminal for a rates trader, and doesn’t try to. Most independent analysts aren’t trading MMDs, though; they’re writing research.

10× the price

Bloomberg-class terminals

  • Real-time fixed-income, FX, and OTC pricing you likely don't need.
  • Per-seat contracts, annual commits, procurement friction.
  • Chat and messaging network effects irrelevant to a solo analyst.
$29 / $79

Convexity Pro & Pro Plus

  • The filing, insider, macro, and alt-data surface you actually use.
  • $29 or $79 per month. Cancel from the settings page.
  • AI memo drafting with citations, which the terminals don't have.
Free + spreadsheets

EDGAR plus six micro-SaaS

  • Free EDGAR has no sentiment layer, no normalized XBRL, no semantic retrieval.
  • Six micro-SaaS tools that don't talk to each other.
  • Every citation is manual; every number lives in a different tab.
One surface

Convexity Pro & Pro Plus

  • One surface, one ticker page, one bill.
  • A documented REST API and MCP server (Developer & Quant tiers) to feed your own model.
  • Shareable memo links on Pro Plus. Send a clip, not a PDF.
VI. What You Pay

Two tiers, both honest about their quotas. See the full pricing page for every feature flag. The numbers below are the ones that shape the workflow.

Pro · for the single-analyst practice

$29 / month · $290 / yr

Claude Sonnet · 150 AI queries / mo

Real-time market data, real-time insider flow, 25 watchlists of 250 tickers each, 25 smart alerts, morning brief, options flow, GEX charts, unlimited history. Enough surface for a single-analyst research practice.

Start free
RecommendedPro Plus · the whole stack

$79 / month · $790 / yr

Claude Sonnet + Opus · 1,000 queries (150 on Opus) + 20 deep-research runs

Everything in Pro, plus unlimited watchlists, unlimited alerts, unlimited workspaces, unusual flow alerts, backtest, shareable memo links, semantic search, and unlimited history.

Start free

Research faster. Cite everything.

Create an account and you land on the same surface we use ourselves. The Free plan is real: GPT-6 Luna, 10 queries a month, delayed quotes, and no card.

Start freeSee pricing