# Bootstrap prompt

Paste the prompt below into an agent that can reach the Metix AI Platform: one with the [metix-skills](https://github.com/MetixAI-Official/metix-skills) installed, the MCP server connected, or plain REST access with `METIX_KEY` set. Followed end to end, it costs about 9 to 33 API Credits: 9 counts, and about 24 more to read the first 100 companies on the list. It stops and asks before 40.

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

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

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

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

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

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

## Adapt it

| 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?