# Firmable Decisions

> Firmable Decisions answers yes or no questions about companies and people, from Firmable's own data. Every answer comes with a confidence score and the facts behind it, and with reasoning on, the source and date too.

- Web page: https://developer.firmable.ai/products/decisions
- Get a free API key: https://platform.firmable.com/sign-up
- Docs: https://docs.firmable.com/api-reference/overview
- Full API reference: https://docs.firmable.com/api-reference/overview

## What you can do

- Qualify every account against your ICP
- Clean stale contacts out of your CRM
- Check an email is likely to deliver before you send

Key facts: 1 cent per answer, 34 checks, Unknown answers free.

## One question for every record you hold.

A domain, a job title, a work email or a mobile number each raises a question before your agent acts: is the account a fit, would this person buy, are they still in the role, will the email land, can we call? Decisions answers each one with yes, no or unknown, and with reasoning on, the reason why.

Checks: `is_icp_fit`, `is_decision_maker`, `is_contact_current`, `is_email_valid`, `is_mobile_on_dnc`.

## How it works

1. **Ask.** Name a tool and who it is about. Through MCP, you can ask in plain English instead.
2. **Check the record.** Firmable runs the right tool against its record. No web search.
3. **Act.** Branch on yes, no or unknown. Act above your confidence floor.

Fields in every response:

- `decision`: Yes, no or unknown.
- `confidence`: How sure the answer is, 0 to 1.
- `details`: What was checked and found.
- `entity`: Who it's about, and how matched.
- `data_as_of, version`: Data date and tool version.
- `reasoning`: With reasoning on: reason, source, date, would_change_if.

## Why you can trust each answer

- **They come from structured data.** We crawl the web ourselves and store what we find as typed fields with a source and a date. Decisions read those fields, so your agent never reads a raw page.
- **The confidence is calculated.** It reflects how much of what the question needs is in the record. Ask again and you get the same number.
- **Every answer is dated.** data_as_of and the tool version come back with every answer. With reasoning on, would_change_if lists what would change it.
- **Naming the check makes it repeatable.** In a pipeline, call is_icp_fit or is_contact_current by name and the same tool runs each time.

## 34 questions Decisions can answer

Each check below is one yes or no question. Your agent can ask in plain English and Firmable picks the right check, or your code can name the check it wants. A few, like the ideal customer check, need you to describe what you're looking for.

### Is this account a good fit? (about a company)

- Does it match our ideal customer profile? Check: `is_icp_fit`.
- Does it belong in this campaign's audience? Check: `matches_campaign_audience`.
- Is its headcount in the range we want? Check: `matches_company_size`.
- Is it public, private, government or another type we want? Check: `matches_company_type`.
- Does it sell to other businesses? Check: `is_b2b`.
- Does it offer a particular service? Check: `offers_service`.
- Anything else? Write your own yes or no question. Check: `evaluate_custom_decision`.

### Where does it operate? (about a company)

- Is its head office, or any office, in a place we name? Check: `is_located_in`.
- Does it have staff in Australia or New Zealand? Check: `has_local_team`.
- Does it have more than one location? Check: `has_multiple_sites`.
- Does it operate in two or more countries? Check: `is_multinational`.

### Who exactly is this business? (about a company)

- Does this email domain belong to this company? Check: `owns_domain`.
- Are these two records the same business, by ABN, NZBN or root domain? Check: `is_same_business`.
- Is it listed on one of 16 stock exchanges? Check: `is_publicly_listed`.
- Does it claim an R&D tax incentive? Check: `claims_rd_tax_incentive`.
- Is it a government body or a nonprofit? Check: `is_public_sector_or_nonprofit`.
- Does it have a business phone number? Check: `has_company_phone`.

### Can we reach this person? (about a person)

- Can we reach them by email or a mobile we're allowed to call? Check: `is_reachable`.
- Will an email to them be delivered? Check: `is_email_valid`.
- Do they have a mobile number? Check: `is_mobile_valid`.
- Is their mobile on Australia’s Do Not Call Register? Check: `is_mobile_on_dnc`.

### Are they still there? (about a person)

- Are they still in this role? Check: `is_contact_current`.
- Have they changed jobs since a given date? Check: `has_changed_jobs_since`.
- Do they work at this company now? Check: `works_at_company`.
- Did they use to work at this company? Check: `previously_worked_at`.
- Are they new in their role? Check: `is_new_to_role`.
- Are they a newly appointed executive? Check: `is_new_exec`.
- Have they been in the role a long time? Check: `is_long_tenured`.
- Do they hold board or advisory roles elsewhere? Check: `has_other_current_roles`.

### Are they the right person to talk to? (about a person)

- Do they make the buying decision? Check: `is_decision_maker`.
- Are they at the seniority we want? Check: `matches_seniority`.
- Do they work in the department we want? Check: `matches_department`.
- Are they a founder or owner? Check: `is_founder_or_owner`.
- Do they list a particular skill? Check: `has_skill`.

## What teams build with it

### Sales teams: qualify accounts and find who to call

1. Check each account against your ICP.
2. Find the decision makers at the ones that fit.
3. Keep only the people you can reach.

Tools: `is_icp_fit`, `is_decision_maker`, `is_reachable`.

### RevOps teams: keep the CRM clean

1. Check every contact on each sync.
2. Flag anyone who has changed jobs.
3. Update or archive them before reps call.

Tools: `is_contact_current`, `has_changed_jobs_since`.

### Risk and onboarding teams: vet a business before you approve it

1. Match the applicant to a known business.
2. Check whether it is publicly listed.
3. Approve it, or send it for manual review.

Tools: `is_same_business`, `is_publicly_listed`.

### Sales development teams: route inbound sign-ups

1. Match the sign-up's email to its company.
2. Check the company fits your ICP.
3. Send it to the team that covers its location.

Tools: `owns_domain`, `is_icp_fit`, `is_located_in`.

### Marketing teams: build clean campaign audiences

1. Check each account belongs in the audience.
2. Drop contacts whose email is unlikely to deliver.
3. Launch with a list you can stand behind.

Tools: `matches_campaign_audience`, `is_email_valid`.

### Account-based marketing teams: reach buyers at the right moment

1. Check target contacts for role changes.
2. Flag new executives and people new in role.
3. Start outreach while priorities are being set.

Tools: `is_new_exec`, `is_new_to_role`.

## Use it in your agent

Paste this into your agent to connect Firmable, make a test call and save a rule for when to use it:

```text
Set up Firmable Decisions for me.

1. Connect the Firmable MCP server by following
   https://agents.firmable.com/developer/setup.txt
   Keep any MCP servers that are already configured.
2. If you need an API key instead of signing in, ask me for it. Keep it in an
   environment variable called FIRMABLE_API_KEY or our secret store, never in
   a file that gets committed.
3. Check it works: call make_decision with tool is_publicly_listed and
   domain stripe.com, then show me the decision, its confidence and the
   reason.
4. Add this rule to your project memory (CLAUDE.md, AGENTS.md or .cursor/rules)
   and tell me where you saved it:
   "For yes or no questions about a company or a person, call Firmable
    make_decision instead of searching the web. Quote the reason and
    source with each answer, and when the decision is unknown, ask me
    rather than guess."

What Firmable Decisions can do: https://developer.firmable.ai/products/decisions.md
```

### Ask your agent

```text
Use Firmable to check whether each company in accounts.csv fits our ICP:
50 to 500 staff, software, head office in the United States.
Show the decision, the reason and the source for each.
```

Works in any client with the Firmable MCP server.

### Pin the tool

```json
{
  "name": "make_decision",
  "arguments": {
    "tool": "is_located_in",
    "question": { "countries": ["SG"] },
    "domain": "grab.com",
    "withReasoning": true
  }
}
```

Naming the tool skips routing, so the same tool runs every time.

### Response

```json
{
  "success": true,
  "tool": "is_located_in",
  "result": {
    "decision": "yes",
    "confidence": 1,
    "details": {
      "location_checked": "head office",
      "location_held": ["SG"]
    },
    "entity": { "type": "company", "id": "f000001674020", "name": "Grab" },
    "data_as_of": "2026-11-11",
    "version": "2026-11-06",
    "reasoning": {
      "reason": "It has its head office in SG.",
      "source": "Firmable company data",
      "date": "2026-11-11",
      "would_change_if": []
    }
  }
}
```

The real response to that call, trimmed.

### Check a contact

```json
{
  "name": "make_decision",
  "arguments": {
    "tool": "is_contact_current",
    "question": { "title": "Head of Sales" },
    "work_email": "jane@example.com"
  }
}
```

To check up to 100 contacts in one call, put them in records.

### When it's unknown

```json
{
  "success": true,
  "tool": "is_icp_fit",
  "result": {
    "decision": "unknown",
    "confidence": 0,
    "entity": { "type": "company", "id": "f000000249171", "name": "McKinsey & Company" },
    "usage": { "billable": false },
    "reasoning": {
      "reason": "Firmable's record doesn't settle "Sells software to other businesses" either way.",
      "would_change_if": [
        "the record showed whether they meet: Sells software to other businesses"
      ]
    }
  }
}
```

A real response. The record didn't settle it.

## Pricing

| What | Credits | US$ |
| --- | --- | --- |
| Yes or no answer | 1 credit per 25 | $0.01 |
| With reasoning | 2 credits per 25 | $0.02 |
| Unknown answers and errors | Free | $0 |
| Listing the tools | Free | $0 |

Based on $0.25 a credit. Part-credits carry over between calls. Volume discounts apply.

## Questions

### What is Firmable Decisions?

An API and MCP tool that answers yes or no questions about companies and people from Firmable's own data. Each answer includes a confidence score and the facts behind it. With reasoning on, it also gives the source, the date and what would change it.

### How do I use it?

Connect the Firmable MCP server to your agent and ask in plain English, or call POST /decisions or make_decision with a tool name, such as is_icp_fit, and the company's domain or Firmable ID.

### How much does it cost?

One cent per answer, or two cents with the reasoning included. Unknown answers are free. New accounts start with $25 of free credit.

### Is unknown the same as no?

No. Unknown means Firmable doesn't hold the fact needed to answer, so your agent knows to look it up before acting.

### What does confidence mean?

How sure the answer is, from 0 to 1, worked out from the data we hold. Set a threshold and let your agent act above it.

### Why not use a model with web search?

A web search answer depends on the pages it finds that day. Decisions answer from Firmable's own records, such as job changes and email deliverability grades, and every answer carries the date of its data.

### Can I ask my own question?

Yes. Use evaluate_custom_decision to ask any yes or no question about a company.

### Where can I use it?

Through the REST API (POST /decisions) or the Firmable MCP server, with a developer API key or by signing in. It works with Claude, ChatGPT, Cursor and other MCP clients.

### Are answers about people firm facts?

No. Answers about people come back with advisory set to true: a guide, not a firm fact.
