Ramp
Enrich the company at ramp.com
Recorded
What went in
Enrich the company at ramp.com
What came back, unedited
Nimble's account enrichment agent populates a company record with the legal name, HQ, founding year, headcount, ownership, funding, current leaders and tech stack from the live web. Every value comes with the page it was read on and the date that page states.
We ran Nimble's ready-made account enrichment agent on the four companies below, at high effort. Each tab shows the exact input and the record it returned, unedited.
Enrich the company at ramp.com
Recorded
What went in
Enrich the company at ramp.com
What came back, unedited
Enrich the company at attio.com
Recorded
What went in
Enrich the company at attio.com
What came back, unedited
Enrich the company at gong.io
Recorded
What went in
Enrich the company at gong.io
What came back, unedited
Enrich the company at notion.so
Recorded
What went in
Enrich the company at notion.so
What came back, unedited
Want to run your own? Try the live demo
An example run of the account enrichment agent. The request sends the agent ID, an input such as "Enrich the company at attio.com" and an effort level. The response is the record as JSON, with a source URL on every value.
import os, time
from nimble_python import Nimble
nimble = Nimble(api_key=os.environ["NIMBLE_API_KEY"])
agent_id = "wsa_76fc85fc76ce46a4bcc2eec6194b5f8f" # Nimble's account enrichment agent
run = nimble.agents.runs.create(
agent_id,
input="Enrich the company at gong.io",
effort="high",
)
while run.is_active:
time.sleep(10)
run = nimble.agents.runs.get(run.id, agent_id=agent_id)
result = nimble.agents.runs.result(run.id, agent_id=agent_id)
print(result.output.content)import Nimble from "@nimble-way/nimble-js";
const nimble = new Nimble({ apiKey: process.env.NIMBLE_API_KEY });
const agentId = "wsa_76fc85fc76ce46a4bcc2eec6194b5f8f"; // Nimble's account enrichment agent
let run = await nimble.agents.runs.create(agentId, {
input: "Enrich the company at gong.io",
effort: "high",
});
while (run.is_active) {
await new Promise((r) => setTimeout(r, 10000));
run = await nimble.agents.runs.get(run.id, { agent_id: agentId });
}
const result = await nimble.agents.runs.result(run.id, { agent_id: agentId });
console.log(result.output.content);AGENT_ID=wsa_76fc85fc76ce46a4bcc2eec6194b5f8f # Nimble's account enrichment agent
RUN_ID=$(nimble agents:runs create \
--agent-id "$AGENT_ID" \
--input 'Enrich the company at gong.io' \
--effort high | jq -r .id)
# repeat while "is_active" is true, then read the result
nimble agents:runs get --agent-id "$AGENT_ID" --run-id "$RUN_ID"
nimble agents:runs result --agent-id "$AGENT_ID" --run-id "$RUN_ID"AGENT_ID=wsa_76fc85fc76ce46a4bcc2eec6194b5f8f # Nimble's account enrichment agent
curl -X POST "https://sdk.nimbleway.com/v2/agents/$AGENT_ID/runs" \
--header "Authorization: Bearer $NIMBLE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{"input":"Enrich the company at gong.io","effort":"high"}'
# poll until is_active is false, then read the result
curl "https://sdk.nimbleway.com/v2/agents/$AGENT_ID/runs/$RUN_ID" --header "Authorization: Bearer $NIMBLE_API_KEY"
curl "https://sdk.nimbleway.com/v2/agents/$AGENT_ID/runs/$RUN_ID/result" --header "Authorization: Bearer $NIMBLE_API_KEY"Recorded November 11, 2026.
{
"run": {
"id": "task_run_d3594fc40e254fc5a3b07a0cc7353f6c",
"status": "completed",
"effort": "high",
"started_at": "2026-11-11T10:37:56.872200Z",
"completed_at": "2026-11-11T10:40:23.276269Z"
},
"output": {
"type": "json",
"content": {
"domain": "gong.io",
"hq_city": {
"as_of": null,
"value": "San Francisco, California (201 Spear St, 13th Floor, San Francisco, CA 94105)",
"source_url": "https://www.linkedin.com/company/gong-io"
},
"industry": {
"as_of": "2026",
"value": "Revenue intelligence / revenue AI software (Revenue AI Operating System for sales, RevOps and customer success teams)",
"source_url": "https://gong.io/about"
},
"ownership": {
"as_of": "2021-06-03",
"value": "Private, VC-backed (company states it is a private company; LinkedIn lists it as Privately Held; last priced round was Series E in June 2021)",
"source_url": "https://gong.io/press/gong-raises-250-million-in-series-e-funding-at-7-25-billion-valuation"
},
"hq_country": {
"as_of": null,
"value": "United States",
"source_url": "https://www.linkedin.com/company/gong-io"
},
"last_round": {
"date": "2021-06-03",
"round": "Series E",
"amount": 250000000,
"currency": "USD",
"source_url": "https://gong.io/press/gong-raises-250-million-in-series-e-funding-at-7-25-billion-valuation",
"lead_investors": [
"Franklin Templeton"
]
},
"leadership": [
{
"name": "Amit Bendov",
"role": "CEO",
"as_of": "2026",
"title": "CEO & Co-Founder",
"source_url": "https://gong.io/about",
"linkedin_url": "https://www.linkedin.com/in/amitbendov/"
},
{
"name": "Eilon Reshef",
"role": "Chief Product Officer",
"as_of": "2026",
"title": "Chief Product Officer & Co-Founder at Gong",
"source_url": "https://gong.io/about",
"linkedin_url": "https://www.linkedin.com/in/eilonreshef/"
},
{
"name": "Tim Ritters",
"role": "CFO",
"as_of": "2026",
"title": "Chief Financial Officer",
"source_url": "https://gong.io/about",
"linkedin_url": null
}
],
"legal_name": {
"as_of": "2026",
"value": "Gong.io Ltd.",
"source_url": "https://gong.io/about"
},
"tech_stack": [
{
"tool": "Greenhouse",
"category": "Applicant tracking / recruiting (job board powered by Greenhouse)",
"evidence_url": "https://job-boards.greenhouse.io/gongio"
},
{
"tool": "Python",
"category": "Programming language (Senior Backend Engineer - AI Framework (Python) and Senior Backend Engineer (Python) openings)",
"evidence_url": "https://job-boards.greenhouse.io/gongio"
},
{
"tool": "Salesforce",
"category": "CRM (GTM tool; 'Experience with a major CRM (e.g., Salesforce, HubSpot)' listed in Tech Stack Analyst - GTM Tools job)",
"evidence_url": "https://jobs.thrivecap.com/companies/gong/jobs/65226995-tech-stack-analyst-gtm-tools"
}
],
"founded_year": {
"as_of": null,
"value": 2015,
"source_url": "https://www.linkedin.com/company/gong-io"
},
"total_funding": {
"as_of": "2021-06-03",
"value": "$584 million",
"source_url": "https://gong.io/press/gong-raises-250-million-in-series-e-funding-at-7-25-billion-valuation"
},
"employee_count": {
"as_of": null,
"value": "1,001-5,000 employees (LinkedIn company size range; 2,112 members shown on LinkedIn)",
"source_url": "https://www.linkedin.com/company/gong-io"
},
"missing_fields": []
},
"confidence": null,
"sources": [
{
"url": "https://gong.io/about",
"title": "About Gong"
},
{
"url": "https://craft.co/gong-io/executives",
"title": "Gong CEO and Key Executive Team - Craft.co"
},
{
"url": "https://job-boards.greenhouse.io/gongio?error=true",
"title": "Jobs at Gong.io"
},
{
"url": "https://jobs.thrivecap.com/companies/gong/jobs/65226995-tech-stack-analyst-gtm-tools",
"title": "https://jobs.thrivecap.com/companies/gong/jobs/65226995-tech-stack-analyst-gtm-tools"
},
{
"url": "https://wfh.team/companies/gongio",
"title": "https://wfh.team/companies/gongio"
}
]
}
}
This is the context an AI agent can use to call the account enrichment agent: its ID, the skill it already runs with, the request options and an example response. The same file is at account-enrichment-agent.md.
---
type: "nimble-agent"
agent: "account-enrichment"
agent_id: "wsa_76fc85fc76ce46a4bcc2eec6194b5f8f"
description: "Give a company domain. Get firmographics, current leaders, tech stack and funding, each with a source."
use_when: "Filling or refreshing firmographic fields for a list of companies, with a source on every value."
default_effort: "medium"
cost_per_run: "$0.10 at medium effort"
---
# Nimble: Account enrichment agent
Give a company domain. Get firmographics, current leaders, tech stack and funding, each with a source.
## Agent instructions
Run this ready-made agent by its ID. It already carries the research skill and output schema below, so the input only needs the company's domain.
- Agent page: [Account enrichment agent](https://online.nimbleway.com/web-search-agents/wsa_76fc85fc76ce46a4bcc2eec6194b5f8f)
- Agent ID: `wsa_76fc85fc76ce46a4bcc2eec6194b5f8f`
- Default effort: `medium`
- Docs: [Web Search Agents](https://docs.nimbleway.com/nimble-sdk/web-search-agents/overview)
## Skill
Where firmographics live:
- Legal name, HQ, founded year: the site's about, legal, imprint or terms pages; registries (Companies House, SEC EDGAR,
state registries).
- Employee count: LinkedIn company page range, or a dated statement from the company. Give the range as shown.
- Ownership types: public (with ticker), private, PE-backed (name the firm), VC-backed, subsidiary of X.
- Leadership: the company's team or leadership page, press releases announcing hires, LinkedIn profiles. A title is
current only if a recent page shows it; people move roles often, so a source older than two years needs confirmation.
- Tech stack means tools the company uses, not tools it sells. Good evidence: job posts that list required tools,
integrations pages, customer case studies published by the vendor.
- Funding: press releases, Crunchbase, investor portfolio pages. "Total raised" is whatever a source states; do not add up
rounds yourself unless the rounds are all cited.
Citations and evidence:
- source_url is one full public https URL: the page the value was read on. Never an internal file path or source id. A
value from two pages is two values.
- as_of is the date the source states or was published, not today's date.
- A value nobody published is null, listed in missing_fields. Not an estimate from memory.
- Entity drift is the most common error: a namesake, a parent, a subsidiary or a similarly named company. Match on domain,
registry number, HQ city or ticker before using a page.
## Request options
- `input` (string, required): the company to enrich, by its domain. Example: `Enrich the company at gong.io`
- `effort` (string): `low`, `medium`, `high` or `x-high`. Defaults to `medium`. The examples on the page ran at `high`.
## Request shape
Call `POST https://sdk.nimbleway.com/v2/agents/wsa_76fc85fc76ce46a4bcc2eec6194b5f8f/runs` with your Nimble API key. Poll `GET .../runs/{run_id}` until `is_active` is false, then read `GET .../runs/{run_id}/result`.
```json
{
"input": "Enrich the company at gong.io",
"effort": "high"
}
```
### Python
```python
import os, time
from nimble_python import Nimble
nimble = Nimble(api_key=os.environ["NIMBLE_API_KEY"])
agent_id = "wsa_76fc85fc76ce46a4bcc2eec6194b5f8f" # Nimble's account enrichment agent
run = nimble.agents.runs.create(
agent_id,
input="Enrich the company at gong.io",
effort="high",
)
while run.is_active:
time.sleep(10)
run = nimble.agents.runs.get(run.id, agent_id=agent_id)
result = nimble.agents.runs.result(run.id, agent_id=agent_id)
print(result.output.content)
```
### TypeScript
```typescript
import Nimble from "@nimble-way/nimble-js";
const nimble = new Nimble({ apiKey: process.env.NIMBLE_API_KEY });
const agentId = "wsa_76fc85fc76ce46a4bcc2eec6194b5f8f"; // Nimble's account enrichment agent
let run = await nimble.agents.runs.create(agentId, {
input: "Enrich the company at gong.io",
effort: "high",
});
while (run.is_active) {
await new Promise((r) => setTimeout(r, 10000));
run = await nimble.agents.runs.get(run.id, { agent_id: agentId });
}
const result = await nimble.agents.runs.result(run.id, { agent_id: agentId });
console.log(result.output.content);
```
### cURL
```sh
AGENT_ID=wsa_76fc85fc76ce46a4bcc2eec6194b5f8f # Nimble's account enrichment agent
curl -X POST "https://sdk.nimbleway.com/v2/agents/$AGENT_ID/runs" \
--header "Authorization: Bearer $NIMBLE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{"input":"Enrich the company at gong.io","effort":"high"}'
# poll until is_active is false, then read the result
curl "https://sdk.nimbleway.com/v2/agents/$AGENT_ID/runs/$RUN_ID" --header "Authorization: Bearer $NIMBLE_API_KEY"
curl "https://sdk.nimbleway.com/v2/agents/$AGENT_ID/runs/$RUN_ID/result" --header "Authorization: Bearer $NIMBLE_API_KEY"
```
### CLI
```sh
AGENT_ID=wsa_76fc85fc76ce46a4bcc2eec6194b5f8f # Nimble's account enrichment agent
RUN_ID=$(nimble agents:runs create \
--agent-id "$AGENT_ID" \
--input 'Enrich the company at gong.io' \
--effort high | jq -r .id)
# repeat while "is_active" is true, then read the result
nimble agents:runs get --agent-id "$AGENT_ID" --run-id "$RUN_ID"
nimble agents:runs result --agent-id "$AGENT_ID" --run-id "$RUN_ID"
```
## Response data
The result has `run` and `output`. The record is in `output.content`. Firmographic fields are `{ value, as_of, source_url }`; `leadership` is a list of `{ name, role, title, as_of, source_url, linkedin_url }`; `tech_stack` is a list of `{ tool, category, evidence_url }`; `last_round` holds the round, amount, currency, date and lead investors; `missing_fields` lists what no page could verify. `output.sources` lists the pages read and `output.trust` grades confidence per claim. Example (Gong, every list trimmed to 3 items, 5 sources):
```json
{
"run": {
"id": "task_run_d3594fc40e254fc5a3b07a0cc7353f6c",
"status": "completed",
"effort": "high",
"started_at": "2026-11-11T10:37:56.872200Z",
"completed_at": "2026-11-11T10:40:23.276269Z"
},
"output": {
"type": "json",
"content": {
"domain": "gong.io",
"hq_city": {
"as_of": null,
"value": "San Francisco, California (201 Spear St, 13th Floor, San Francisco, CA 94105)",
"source_url": "https://www.linkedin.com/company/gong-io"
},
"industry": {
"as_of": "2026",
"value": "Revenue intelligence / revenue AI software (Revenue AI Operating System for sales, RevOps and customer success teams)",
"source_url": "https://gong.io/about"
},
"ownership": {
"as_of": "2021-06-03",
"value": "Private, VC-backed (company states it is a private company; LinkedIn lists it as Privately Held; last priced round was Series E in June 2021)",
"source_url": "https://gong.io/press/gong-raises-250-million-in-series-e-funding-at-7-25-billion-valuation"
},
"hq_country": {
"as_of": null,
"value": "United States",
"source_url": "https://www.linkedin.com/company/gong-io"
},
"last_round": {
"date": "2021-06-03",
"round": "Series E",
"amount": 250000000,
"currency": "USD",
"source_url": "https://gong.io/press/gong-raises-250-million-in-series-e-funding-at-7-25-billion-valuation",
"lead_investors": [
"Franklin Templeton"
]
},
"leadership": [
{
"name": "Amit Bendov",
"role": "CEO",
"as_of": "2026",
"title": "CEO & Co-Founder",
"source_url": "https://gong.io/about",
"linkedin_url": "https://www.linkedin.com/in/amitbendov/"
},
{
"name": "Eilon Reshef",
"role": "Chief Product Officer",
"as_of": "2026",
"title": "Chief Product Officer & Co-Founder at Gong",
"source_url": "https://gong.io/about",
"linkedin_url": "https://www.linkedin.com/in/eilonreshef/"
},
{
"name": "Tim Ritters",
"role": "CFO",
"as_of": "2026",
"title": "Chief Financial Officer",
"source_url": "https://gong.io/about",
"linkedin_url": null
}
],
"legal_name": {
"as_of": "2026",
"value": "Gong.io Ltd.",
"source_url": "https://gong.io/about"
},
"tech_stack": [
{
"tool": "Greenhouse",
"category": "Applicant tracking / recruiting (job board powered by Greenhouse)",
"evidence_url": "https://job-boards.greenhouse.io/gongio"
},
{
"tool": "Python",
"category": "Programming language (Senior Backend Engineer - AI Framework (Python) and Senior Backend Engineer (Python) openings)",
"evidence_url": "https://job-boards.greenhouse.io/gongio"
},
{
"tool": "Salesforce",
"category": "CRM (GTM tool; 'Experience with a major CRM (e.g., Salesforce, HubSpot)' listed in Tech Stack Analyst - GTM Tools job)",
"evidence_url": "https://jobs.thrivecap.com/companies/gong/jobs/65226995-tech-stack-analyst-gtm-tools"
}
],
"founded_year": {
"as_of": null,
"value": 2015,
"source_url": "https://www.linkedin.com/company/gong-io"
},
"total_funding": {
"as_of": "2021-06-03",
"value": "$584 million",
"source_url": "https://gong.io/press/gong-raises-250-million-in-series-e-funding-at-7-25-billion-valuation"
},
"employee_count": {
"as_of": null,
"value": "1,001-5,000 employees (LinkedIn company size range; 2,112 members shown on LinkedIn)",
"source_url": "https://www.linkedin.com/company/gong-io"
},
"missing_fields": []
},
"confidence": null,
"sources": [
{
"url": "https://gong.io/about",
"title": "About Gong"
},
{
"url": "https://craft.co/gong-io/executives",
"title": "Gong CEO and Key Executive Team - Craft.co"
},
{
"url": "https://job-boards.greenhouse.io/gongio?error=true",
"title": "Jobs at Gong.io"
},
{
"url": "https://jobs.thrivecap.com/companies/gong/jobs/65226995-tech-stack-analyst-gtm-tools",
"title": "https://jobs.thrivecap.com/companies/gong/jobs/65226995-tech-stack-analyst-gtm-tools"
},
{
"url": "https://wfh.team/companies/gongio",
"title": "https://wfh.team/companies/gongio"
}
]
}
}
```
A ready-made Nimble agent for filling company records.
Give a company domain. Get firmographics, current leaders, tech stack and funding, each with a source.
A research agent that takes a company, usually by its domain, reads current public pages about it and returns a structured record: legal name, HQ, founding year, employee range, ownership, funding, current leaders and tech stack. Nimble's agent returns each value with the URL it was read on and the date that page states, and lists the fields no page could verify.
A database returns what it stored, refreshed on its own schedule. The agent reads the live pages when you ask, so each value carries the page and the date behind it and you can judge how current it is. When no page states a value, the field comes back empty and is listed in missing_fields rather than estimated.
From evidence that the company uses a tool: job posts that list required tools, integrations pages, and customer case studies published by the vendor. Tools the company sells are not counted as its stack. Each tool comes back with the URL of the evidence.
Yes. Paste this prompt into Claude, ChatGPT, Codex, Cursor or Grok: "Be my CRM enrichment assistant using Nimble. Follow https://docs.nimbleway.com/skills/account-enrichment/SKILL.md." The skill asks what you need, connects Nimble if it isn't connected yet, and runs the agent. Developers can call the same ready-made agent by its ID from the API, the Python or TypeScript SDK, or from Mastra, LangChain, the Vercel AI SDK and LlamaIndex.
Are you an AI agent? Read the agent guide for this use case.