Find which of your accounts are hiring for a role
Count one role's open postings at every company on your list, next to all of its open postings, and call the ones that are hiring for what you sell first.
Who does this
The job this saves, and who it is for.
A seller of data infrastructure, or anyone whose buyer is a specific team. A company hiring several data engineers right now is building the thing your product helps with.
What comes back
The counts from the last replay. Your agent reads the records behind them on your key.
Open data engineer postings at ten accounts
Data engineer postingsAll open postings
Each bar is the open postings whose title matches "data engineer". The number on the right is all of the company's open postings, so a big hirer does not look like a strong signal only because it posts a lot.
What your agent reads
The record fields the prompt asks for. This page shows field names and counts, never a record.
company.nametitleposted_datelocation.city
Then
Where the task goes after the list.
Start with the strongest signal
Sort by the role count, then check the share of all postings. Five data roles out of 200 says more than ten out of 2,000.
Quote the posting
Ask the agent to read the matching postings and pull the tools and problems they name. An email that cites the posting reads as research, not spam.
Watch it weekly
Schedule the same prompt weekly and alert when an account's role count rises. 20 API Credits a run for ten accounts.
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
20 API Credits$0.67Fits in the 100 free API Credits
Your agent stops and asks before spending more than 30 API Credits.
Your agent follows the prompt step by step: it reads the rules, runs the counts, checks the definitions the prompt asks it to check, and writes the files and charts. Use an agent that can write files, such as Claude Code or Codex.
Set up onceKey, connection, and a free check. Skip this if your agent already reaches the Platform.
1Get a key
Create a key on the Metix AI Platform →New accounts get 100 API Credits once, valid for 30 days. Set the key in the shell you start your agent from, or add the line to ~/.zshrc or ~/.bashrc so every new terminal has it:
Shellexport METIX_KEY=metix_xxxxxxxx
2Connect your agent
Claude Code
Registers the Platform for every project. Start claude in any folder and the ten metix tools are there.
MCP setup guide →Shell: "${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"Codex
Registers the same server. The key stays in your environment instead of the config file.
MCP setup guide →Shellcodex mcp add metix \ --url https://mira-api.metix.ai/mcp \ --bearer-token-env-var METIX_KEY
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.
Skills install guide →Shellnpx skills add MetixAI-Official/metix-skills
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.
MCP setup guide →Endpoint and headershttps://mira-api.metix.ai/mcp Authorization: Bearer <your key> Accept: application/json, text/event-stream
3Check the setup
Ask this first. It reads your balance and the field list, runs no search, and costs nothing:
Prompt for your agentUse 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
Tell me which of my ten accounts are hiring data engineers right now, using the Metix AI Platform. The accounts are Stripe, Databricks, Snowflake, Datadog, Rippling, Brex, Ramp, Figma, Airtable and Notion. 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.
01Read before querying
Call GET /contract (free) and read the job fields company.name, title and is_open. Check the balance with GET /auth/key/status (free) at the start and at the end, and stop and ask before the run passes 30 API Credits.
02Population
For each account, open postings with company.name eq the account and title match "data engineer", in one all node.
03Context
For each account, also count all of its open postings (company.name eq the account and is_open eq true), so a company that posts a lot does not look like a strong signal only because of its size.
04Budget
Two counts per account, twenty in all, with size 1. Read no postings unless I ask.
05Check names
If an account returns zero open postings in total, its name may not match the postings. Tell me, and suggest the spelling to try.
06Clean
Reposts count as separate postings; say so.
07Rank
Order the accounts by data engineer postings, then by their share of all open postings.
08Outputs
A table with account, data engineer postings, all open postings and the share, with the snapshot date.
09Chart
Horizontal bars of data engineer postings per account, largest first, with the total open postings written beside each bar.
10Limits
Say that postings from every country count, that a title match also catches senior and lead roles and some analytics engineers, and that one day is not a trend.
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
18 API Credits$0.60Fits in the 100 free API Credits
A short standard-library Python script sends the committed queries as counts and writes the aggregate files this page is built from. It needs Python and METIX_KEY set in the shell (step 1 of the agent path); your agent can run these lines for you as well.
curl -fsSL https://platform.metix.ai/casebook/source/find-accounts-hiring-for-a-role.tar.gz | tar xz
cd find-accounts-hiring-for-a-role
: "${METIX_KEY:?set METIX_KEY first}" && python3 cases/find-accounts-hiring-for-a-role/fetch.pyWhat you get
data/*.json and data/receipt.json. Run git diff cases/find-accounts-hiring-for-a-role/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 accounts | The list in the question | Paste your own account list |
| The role | Step 2 | "account executive", "security engineer" |
| Recent postings only | Steps 2 and 3 | Add posted_date gte now-30d |
What to ask before running it
- Which accounts, spelled as they appear on their postings?
- Which role signals a need for what you sell?
- Any country, or only where you sell?
Tell me which of my ten accounts are hiring data engineers right now, using the Metix AI Platform. The accounts are Stripe, Databricks, Snowflake, Datadog, Rippling, Brex, Ramp, Figma, Airtable and Notion. 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 job fields company.name, title and is_open. Check the balance with GET /auth/key/status (free) at the start and at the end, and stop and ask before the run passes 30 API Credits. 2. Population. For each account, open postings with company.name eq the account and title match "data engineer", in one all node. 3. Context. For each account, also count all of its open postings (company.name eq the account and is_open eq true), so a company that posts a lot does not look like a strong signal only because of its size. 4. Budget. Two counts per account, twenty in all, with size 1. Read no postings unless I ask. 5. Check names. If an account returns zero open postings in total, its name may not match the postings. Tell me, and suggest the spelling to try. 6. Clean. Reposts count as separate postings; say so. 7. Rank. Order the accounts by data engineer postings, then by their share of all open postings. 8. Outputs. A table with account, data engineer postings, all open postings and the share, with the snapshot date. 9. Chart. Horizontal bars of data engineer postings per account, largest first, with the total open postings written beside each bar. 10. Limits. Say that postings from every country count, that a title match also catches senior and lead roles and some analytics engineers, and that one day is not a trend.
Questions
What people ask before running it.
Where does my account list come from?
From your CRM, or from the target account list use case. Company names must match the name on the posting; the agent checks each one with a count before the run.
What does it cost for 100 accounts?
Two counts per account, so about 200 API Credits. Drop the total count to halve it.
Method and limits
Who is counted, how, and what the counts miss.
- Population
- Open postings visible through the Metix AI Platform on September 30, 2026, for the ten companies in account-list.json. The role is a title match on "data engineer".
- Limits
- Postings in every country count. A title match includes senior and lead roles and can include analytics engineers who use the phrase. Reposts are not collapsed.
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
- 20
- Search results
- 18
- Records read
- 0
- API Credits
- 18
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 10 API Credits more: the agent's audits, trial queries, and earlier runs that the published replay replaced. You do not pay that again.