Skip to main content
A diligence report answers what a buyer would ask about a company, page by page, each figure from what PodData read and each page saying how it was built. Your own assistant writes it a page at a time, or PodData’s agent does.

Its shape

A report has a title, an overview and five pages, in this order: The overview has a bottom_line, three stat cards and the first_question to ask. Each page has:
  • state: empty, written, or waits when it can’t be written yet and its method says why
  • headline, which states the finding, and a lede
  • read: what was read, as figures, such as reviews read
  • questions: two, each with its ask, its answer in a line and up to three stat cards
  • exhibits: up to 12, each a saved question to a number tool
  • quotes: up to 30 quotes, reviews, passages or records it cites, by id
  • method: what was read, over which window (from, to), and what was left out and why
  • names: the companies, brands, places and sources it names, which the check reads as words

A figure and an exhibit

Copy never holds a typed number. It cites a figure in braces, {exhibit.figure}, and the figure comes from an exhibit on the page:
numbers is a number tool, company the target or a confirmed rival, and params the tool’s own arguments. Each time the report is read, PodData asks the tool again and puts its figure in place of the braces, so "Patients rate Northwind {customer-1.average} stars" reads "Patients rate Northwind 4.3 stars". See Number tools for each tool’s figures.

Write it

  1. POST /diligence-reports with company makes one, with five empty pages. The answer gives its id and rev.
  2. PUT /diligence-reports/{id}/pages/{page} saves one page, with rev and page; for the overview, overview is the page and the field. A page is saved whenever it fits the shape, whatever the check says, and the answer is the report filled, with what the check finds now.
  3. A 409 on a save means someone saved over the version you read. Read the report again with GET /diligence-reports/{id}, and change only what you were asked.
  4. POST /diligence-reports/{id}/check runs the check and marks the report checked when it refuses nothing.
Tools: start_report, save_report_page, check_report, get_report. get_report with page gives one page as saved, in JSON, to change only what you’re asked and keep the rest.

What the check refuses

The check refuses a report that would say more than PodData read. Among what it refuses:
  • a figure in braces that no number tool gave, or braces that don’t hold one
  • an exhibit with no evidence, or whose evidence comes through a link no one confirmed
  • a company compared that isn’t the target or a rival a person confirmed
  • a page that doesn’t say what was read and over which window, or that waits without saying why
  • an empty page, a page without its two questions, an overview without its three cards
It advises, without refusing, on an exhibit with no caveat when its tool’s answer gives one. Each problem comes with where it is (pages.0.exhibits.1) and why.

Read it

The answer is one JSON object: the report as stored (report), the same with each figure in its place (filled), each exhibit’s number tool asked now (answers), each item a page cites looked up by its id, at most 80 words (cited), and what the check says (check). Since each read asks every tool again, a saved copy is that moment’s.

As files

format downloads the report as files, every figure filled as it reads now:
  • ?format=md: one Markdown document, the overview and then each page, with its exhibits as tables, its quotes and how it was built.
  • ?format=zip: poddata-report-<company>-<day>.zip, holding report.json, report.md, a Markdown file a page under pages/, each exhibit’s rows and its figures as CSV and its answer as JSON under exhibits/, evidence.csv, cited.csv, and a README.txt of what each file is.
A draft downloads too, marked a draft with how many things the check refuses. In a file, a figure read through your team’s own licence is left out with why, and a source’s words stay at most 80 in a row. Each download is one call. No MCP tool hands over a file: get_report answers the report as JSON. GET /diligence-reports lists the team’s reports, newest change first, each with its status and where each page stands.

PodData’s agent

PodData’s own agent writes a first draft, or with message makes a change a person asks for: POST /diligence-reports/{id}/runs, from a key, an assistant signed in, or the workspace. PodData pays for its turns, up to the run’s cap (cap_usd), so an assistant asks the person before it starts one. GET /diligence-reports/{id}/runs lists a report’s runs, and GET /diligence-runs/{id} gives one with each agent’s turns and what it cost. Tools: start_report_run, list_report_runs, get_report_run. A run ends done, stopped, capped when it reached its cap with pages left, refused or failed.

Share it

A person signed in to the workspace can make a private link to a checked report, for someone outside the team, and turn it off. A key can’t: the link’s address is shown only once, in the workspace. A figure read through your team’s own licence never goes out by a link.