What are the peers really paying, and does the peer set hold up?

Paste the peers' trading data and enter your target. Your browser builds the comps as you type: margins and multiples for every peer, the quartile statistics, the outliers and the target's implied value. All free, before you sign in. Then the desk reviews the peer set the way a senior banker would, and every number it writes is checked against your table.

Each example comes with a saved review, one per verdict, so you can see the whole page for free.

Analysis title (optional)

As of (period, optional)

Sector (picks the metrics)

Peer table

CSV, tab-separated (straight from a spreadsheet) or a Markdown table. Money in $ millions, shares in millions, price in $. Needs Company or Ticker, and Revenue. Market cap can be given or built from price x shares; net debt can be given or built from debt and cash; growth can be given or built from prior-year revenue. "1.2bn", "(45)", "1,520", "NM" and "n/a" are all read. Up to 25 peers.

Drop a .csv, .tsv, .txt or a set .json saved from this page, or

Target

Target name

Ticker (optional)

Revenue ($m)

EBITDA ($m)

Net income ($m)

Free cash flow ($m)

Revenue growth (%)

Net debt ($m, cash negative)

Diluted shares (m)

Share price ($, if listed)

What you want to know (optional)

The comps (free, in your browser, no AI)

What the browser found

Operating statistics and financial metrics (untick a peer to leave it out of the statistics)

Valuation multiples

Implied valuation of the target

Where the target sits

Checks

Free: no account, no run.

Paste a peer table and the target's revenue to price the review.

anchor

peers called

suggested exclusions

flags answered

statements checked

disagreements

Valuation read

Anchor multiple

The peers, one by one

Call	Peer	Why

What the statistics say

Flags answered

Data to confirm

Notes and methodology

IC summary

Reconciliation with the table

Every number, peer, the anchor multiple, every metric, every flag and the verdict the review wrote were checked against the comps your browser computed. A disagreement means the review, not your table, is wrong.

Summary

Raw model reply

The reply did not parse as the structured result, so it is shown as it arrived.

Your recent reviews

What this does, and what it does not

The comps are plain arithmetic, laid out the way an institutional comps sheet is. Market cap is the share price times diluted shares, unless you give it. Enterprise value is market cap plus net debt. Margins are each profit line over revenue. EV / Revenue, EV / EBITDA and P / E are shown as NM when the denominator is zero or negative, and NM values are left out of the statistics. The statistics block (maximum, 75th percentile, median, 25th percentile, minimum) uses the same interpolation as Excel's QUARTILE function, and covers only the comparable metrics: growth, margins and multiples, never size. The target's implied enterprise value is its revenue, EBITDA or net income times the peers' quartile multiple, bridged to equity with its net debt. Outliers are values beyond 1.5 times the interquartile range from the quartiles and more than 20% from the median.

It does not fetch prices or filings, know what any company does, or adjust for one-off items, leases, minority interests, calendarisation or currency. The data are yours to source and date. The review explains and challenges. It does not tell anyone to invest. Derived from the agent skill @anthropics/comps-analysis (anthropics/financial-services-plugins, Apache-2.0). The example companies are fictional.