Use case · SalesCompanies

Build a target account list by industry, size and growth

Turn an ideal customer profile into filters, watch the list shrink as each one is added, and read only the companies that are left.

Who does this

The job this saves, and who it is for.

A founder or sales lead who has written down an ideal customer profile and needs the list of companies that fit it, sized before anyone starts writing emails.

How the search narrows

Each row adds one filter to the row above. Count before you read: each count costs 1 API Credit.

  1. Headquartered in the United Statesheadquarters.country eq "United States"100,000+banded above the threshold
  2. In software development+ industry match "software development"100,000+banded above the threshold
  3. 50 to 500 staff+ headcount gte 50, lte 5007,176row above is a band
  4. Headcount up 20% or more in a year+ headcount_growth_yoy_pct gte 201,567Your list22% of the row above

Bar length on a log scale

What comes back

The counts from the last replay. Your agent reads the records behind them on your key.

The 1,567 accounts, by headquarters state

Companies

  1. California508
  2. New York213
  3. Texas121
  4. Massachusetts67
  5. Washington40
  6. Other states618

The state the company lists as its headquarters. Other is the rest of the 1,567.

What your agent reads

The record fields the prompt asks for. This page shows field names and counts, never a record.

  • name
  • website
  • headcount
  • headcount_growth_yoy_pct
  • headquarters.city
  • headquarters.state
  • industry
  • last_funding.date

Then

Where the task goes after the list.

  1. Read the list

    Ask the agent to read the first 100 companies (about 24 API Credits) and write them to a table with website, headcount and growth. It asks before reading the rest.

  2. Find who is hiring

    Growth in headcount is one signal; open postings for the role you sell to are a sharper one. See the next use case.

  3. Find the people to contact

    For each account, search profiles by company and title to find the likely buyer, then unlock a work email only where you need one.

Run it

Three ways in. Each says what it costs before you start.

1 API Credit buys 25 search results or 5 full records; $1 buys 30 API Credits.

Run it in your agent

9 to 33 API Credits$0.30 to $1.10Fits in the 100 free API Credits

Your agent stops and asks before spending more than 40 API Credits.

Your agent follows the prompt step by step: it reads the rules, runs the counts, checks the definitions the prompt asks it to check, and writes the files and charts. Use an agent that can write files, such as Claude Code or Codex.

Set up onceKey, connection, and a free check. Skip this if your agent already reaches the Platform.
  1. 1Get a key

    Create a key on the Metix AI Platform →

    New accounts get 100 API Credits once, valid for 30 days. Set the key in the shell you start your agent from, or add the line to ~/.zshrc or ~/.bashrc so every new terminal has it:

    Shell
    export METIX_KEY=metix_xxxxxxxx
  2. 2Connect your agent

    Claude Code

    Registers the Platform for every project. Start claude in any folder and the ten metix tools are there.

    Shell
    : "${METIX_KEY:?run step 1 first}" &&
    claude mcp add --scope user --transport http metix \
      https://mira-api.metix.ai/mcp \
      --header "Authorization: Bearer $METIX_KEY"
    MCP setup guide →

    Codex

    Registers the same server. The key stays in your environment instead of the config file.

    Shell
    codex mcp add metix \
      --url https://mira-api.metix.ai/mcp \
      --bearer-token-env-var METIX_KEY
    MCP setup guide →

    Skills

    Four skills that teach any agent the Platform's endpoints and query rules, for agents without MCP. The installer starts with none ticked: press space on each, then enter.

    Shell
    npx skills add MetixAI-Official/metix-skills
    Skills install guide →

    Other MCP

    Point the client at this endpoint over streamable HTTP with both headers; without the Accept header the server answers 406. Older clients use /sse on the same host.

    Endpoint and headers
    https://mira-api.metix.ai/mcp
    Authorization: Bearer <your key>
    Accept: application/json, text/event-stream
    MCP setup guide →
  3. 3Check the setup

    Ask this first. It reads your balance and the field list, runs no search, and costs nothing:

    Prompt for your agent
    Use the Metix AI Platform to check my key status and read the contract; both are free. Then tell me my API Credit balance and which datasets I can query. Do not run any search.

4Paste the prompt

Start your agent in an empty folder, then paste. It writes its files there.

The question

Build me a list of US software companies with 50 to 500 staff that grew headcount 20% or more in the last year, using the Metix AI Platform. Work only through the public Platform (REST at https://mira-api.metix.ai, the MCP server, or the metix-skills) with the key in METIX_KEY, and never print the key.

  1. 01Read before querying

    Call GET /contract (free) and read the company fields headquarters.country, industry, headcount, headcount_growth_yoy_pct and headquarters.state. Check the balance with GET /auth/key/status (free) at the start and at the end, and stop and ask before the run passes 40 API Credits.

  2. 02Population

    Companies with headquarters.country eq "United States", industry match "software development", headcount gte 50 and lte 500, and headcount_growth_yoy_pct gte 20, all in one all node.

  3. 03Count each step

    Add the conditions one step at a time (country, industry, the two headcount bounds together, growth) and count each with size 1. Show me the four totals so I can see which condition narrows the list most.

  4. 04Budget

    Four counts, then five more to split the final list by state. Read records only after I have seen the counts.

  5. 05Split by state

    Count the final list in California, New York, Texas, Massachusetts and Washington, and report the rest as other.

  6. 06Read the list

    Search the final filter with size 100 and read those companies with name, website, headcount, headcount_growth_yoy_pct, headquarters.city, headquarters.state and last_funding.date. If the list holds more than 100, say how many are left and ask before reading more.

  7. 07Audit

    Flag companies whose website or name suggests they are not software companies, and tell me how many there are.

  8. 08Outputs

    A table of the companies with those fields, sorted by growth. Keep it to our conversation unless I ask for a file.

  9. 09Summary

    Tell me the median headcount and growth of the list, and which states hold most of it.

  10. 10Limits

    Say that industry is self-chosen, that some companies have no growth figure and drop out, and that headcount follows what each company publishes.

What you get

The aggregate files and the chart, a note on what the audits found and what they changed, and the API Credits the run spent, read from the balance before and after.

A call that returns 402 insufficient_quota means the key works and the balance is empty.

Reproduce the numbers

9 API Credits$0.30Fits in the 100 free API Credits

A short standard-library Python script sends the committed queries as counts and writes the aggregate files this page is built from. It needs Python and METIX_KEY set in the shell (step 1 of the agent path); your agent can run these lines for you as well.

Shell
curl -fsSL https://platform.metix.ai/casebook/source/build-target-account-list.tar.gz | tar xz
cd build-target-account-list
: "${METIX_KEY:?set METIX_KEY first}" && python3 cases/build-target-account-list/fetch.py

What you get

data/*.json and data/receipt.json. Run git diff cases/build-target-account-list/data to see what moved: the numbers should match, apart from what changed in the data since the snapshot.

Adapt it

Costs what your version reads. Write your own ceiling into step 1 of the prompt.

The prompt is the case. Change the parts in this table and your agent answers your question instead, with the same checks and the same way of reporting cost.

To change Edit For example
The industry Step 2 "financial services", "biotechnology"
The size Step 2 headcount gte 200 and lte 2000
The signal Step 2 last_funding.date gte now-12m instead of growth

What to ask before running it

  1. Which industries count, and is the company's own choice of industry good enough?
  2. Which size band is your sweet spot?
  3. Growth, recent funding, or both?

Questions

What people ask before running it.

Is headcount the company's real size?

It is the headcount on the company record visible through the Metix AI Platform, which follows what the company publishes. Treat it as an estimate.

Why does the first step say 100,000+?

Above a threshold the API returns a band instead of an exact total, so a broad filter reads 100,000+. Narrower steps are exact.

Method and limits

Who is counted, how, and what the counts miss.

Population
Companies visible through the Metix AI Platform on September 30, 2026, filtered by headquarters country, industry, headcount and year-over-year headcount growth.
Limits
Industry is the one the company chose, so a data company may list itself elsewhere. Growth is missing for some companies, and they drop out at the last step.

The last reproduction

What reproducing this case cost the last time the script ran, read from the Platform's own balance before and after.

Ran on
2026-09-30
Calls
9
Search results
9
Records read
0
API Credits
9

Search results are IDs returned by searches, one per count query and one per match on a full search. Records are postings or profiles read in full: this case reads none.

Making this case cost about 9 API Credits more: the agent's audits, trial queries, and earlier runs that the published replay replaced. You do not pay that again.