Find the mispricing with a reverse-DCF

Run a DCF on reported free cash flow with the growth rate you choose, then compare what the price implies with what the filings support.

Back out what the market is implying, see where the assumptions break, and defend a target you can take to the IC.

Jump to the code you can copy

The pain

A forward DCF is only as good as your guesses. The sharper question is the reverse one — what does the current price already assume? — but reconstructing that by hand for every name is slow and error-prone.

“I do not trust a DCF I did not build.”
Black-box intrinsic values hide the growth and discount assumptions.
“Where did this free cash flow number come from?”
Pasted inputs lose their source the moment they enter a sheet.
“I rebuild the same sensitivity table for every name.”
WACC and terminal-growth grids are repetitive work.

The solution

1
Solve for the implied expectations
create_report with report_type reverse_dcf backs out the free-cash-flow growth rate the current price requires; compute_dcf runs a two-stage forward DCF when you want an intrinsic estimate.
2
Ground the inputs in filings
get_company_fundamentals feeds the historical FCF base; get_peer_comparables calibrates the discount rate against real peer leverage — no hand-keyed assumptions.
3
Export something you can defend
generate_dcf_xlsx ships a sensitivity-heatmap workbook (15-min presigned download) you can drop into an IC memo.

Copy this

Real code and a ready prompt. Each block says what it needs before it runs.

APython SDK

No token needed: runs on the free sample

reverse-dcf-mispricing.pypython

from valuein_sdk import ValueinClient with ValueinClient() as client:  # no key: the free sample    # A five-year DCF on Apple's reported free cash flow. You choose the growth    # rate; the SDK never guesses one. Inputs trace to filings.    dcf = client.dcf("AAPL", stage1_growth_rate=0.06)    print(dcf.projection_frame())      # projected cash flows and present values    print(dcf.sensitivity_frame())     # value per share across WACC and terminal growth

Runs on the free sample with no token. You set the growth rate; the SDK never guesses one.

pip install valuein-sdk

BPrompt for Claude or ChatGPT

Works without a token on the free sample; your token unlocks your plan

prompt.txttext

Use compute_dcf for this company with my growth assumption, and get_valuation_metrics for what the market is paying today. Show my assumptions next to each output, quote figures exactly as returned, and do not offer an intrinsic value of your own.

Tools it uses: compute_dcf, get_valuation_metrics

CConnect your AI client

No token? Delete the headers block and it runs on the free sample

mcp configjson

{  "mcpServers": {    "valuein": {      "url": "https://mcp.valuein.biz/mcp",      "headers": {        "Authorization": "Bearer YOUR_VALUEIN_TOKEN"      }    }  }}

What you get

You see exactly where the market's assumptions are heroic — and walk into the IC with a target and a workbook behind it.

A DCF whose inputs are reported figures and whose assumptions are yours.
A sensitivity grid across discount rate and terminal growth.
A clear line between what the company reported and what you assumed.

Spread and comp any company in minutesSee how Screen 28,000+ names for your thesis in secondsSee how Backtests that can't see the futureSee how

Frequently asked

Does it do reverse-DCF or forward DCF?

Both. create_report with report_type reverse_dcf solves for the free-cash-flow growth the price implies; compute_dcf runs a two-stage forward DCF for an intrinsic estimate.

Can I get a workbook out of it?

Yes — generate_dcf_xlsx returns a formatted Excel model with a sensitivity heatmap via a short-lived presigned link (Pro+).

Try it on your own ticker.

The free sample needs no token and no card. One token works across your AI agent, your code and the Workspace.

Start free — no card See pricing