--- type: "nimble-agent" agent: "account-signals" agent_id: "wsa_927116846fed492397662503d366b7ac" description: "Give a company and a start date. Get funding, leadership moves, launches, layoffs and pricing changes since then, each dated and sourced." use_when: "Finding what changed at an account since a date: funding, hires and departures, launches, layoffs, pricing and hiring pushes." default_effort: "medium" cost_per_run: "$0.10 at medium effort" --- # Nimble: Account signals agent Give a company and a start date. Get funding, leadership moves, launches, layoffs and pricing changes since then, each dated and sourced. ## 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 and the start date (YYYY-MM-DD). - Agent page: [Account signals agent](https://online.nimbleway.com/web-search-agents/wsa_927116846fed492397662503d366b7ac) - Agent ID: `wsa_927116846fed492397662503d366b7ac` - Default effort: `medium` - Docs: [Web Search Agents](https://docs.nimbleway.com/nimble-sdk/web-search-agents/overview) ## Skill What counts as a signal: - Funding rounds, acquisitions (either side), leadership hires and departures, layoffs, new offices or markets, product launches and major releases, pricing changes (new plans, removed free tier), and hiring pushes (many new roles in one function). Where to find them: - The company newsroom and blog, business press, LinkedIn company posts, the careers page or ATS boards for hiring, and archived versions of the pricing page for pricing changes. Pitfalls: - "Since a date" means the event date, not the article date. Re-reported old news is the most common false signal. - An empty result is a valid answer when nothing changed. since is the cutoff date the request gives, as YYYY-MM-DD. 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, with its domain, and the date to check from as YYYY-MM-DD. Example: `Check Mercury (mercury.com) for changes since 2026-08-13` - `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_927116846fed492397662503d366b7ac/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": "Check Mercury (mercury.com) for changes since 2026-08-13", "effort": "high" } ``` ### Python ```python import os, time from nimble_python import Nimble nimble = Nimble(api_key=os.environ["NIMBLE_API_KEY"]) agent_id = "wsa_927116846fed492397662503d366b7ac" # Nimble's account signals agent run = nimble.agents.runs.create( agent_id, input="Check Mercury (mercury.com) for changes since 2026-08-13", 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_927116846fed492397662503d366b7ac"; // Nimble's account signals agent let run = await nimble.agents.runs.create(agentId, { input: "Check Mercury (mercury.com) for changes since 2026-08-13", 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_927116846fed492397662503d366b7ac # Nimble's account signals agent curl -X POST "https://sdk.nimbleway.com/v2/agents/$AGENT_ID/runs" \ --header "Authorization: Bearer $NIMBLE_API_KEY" \ --header 'Content-Type: application/json' \ --data '{"input":"Check Mercury (mercury.com) for changes since 2026-08-13","effort":"high"}' # poll until is_active is false, then read the result curl "https://sdk.nimbleway.com/v2/agents/$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 $NIMBLE_API_KEY" ``` ### CLI ```sh AGENT_ID=wsa_927116846fed492397662503d366b7ac # Nimble's account signals agent RUN_ID=$(nimble agents:runs create \ --agent-id "$AGENT_ID" \ --input 'Check Mercury (mercury.com) for changes since 2026-08-13' \ --effort high | jq -r .id) # repeat while "is_active" is true, then read the result nimble agents:runs get --agent-id "$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 result is in `output.content`: `company`, `since` (YYYY-MM-DD), `events` (a list of `{ date, type, headline, summary, source_url }`) and `checked_sources` (the pages read). An empty `events` list means nothing changed. `output.sources` lists the pages read and `output.trust` grades confidence per claim. Example (Mercury, every list trimmed to 3 items, 5 sources): ```json { "run": { "id": "task_run_14a3eb72d7d340eebd83f4201624704f", "status": "completed", "effort": "high", "started_at": "2026-11-11T10:38:08.938921Z", "completed_at": "2026-11-11T10:41:07.517633Z" }, "output": { "type": "json", "content": { "since": null, "events": [ { "date": "2026-11-10", "type": "product launch", "summary": "Mercury Personal customers can add credit cards from other banks and ask Command, Mercury's AI agent, about spending across them (ranked charts from real transactions).", "headline": "See more of your spending in one place", "source_url": "https://mercury.com/releases" }, { "date": "2026-11-05", "type": "product launch", "summary": "New Agent Controls show every AI agent connected to a Mercury account, which user it is connected to, what it can do, and a record of its activity; users set permissions Mercury enforces on every agent request, and can disconnect agents in seconds.", "headline": "Mercury Agent Controls", "source_url": "https://mercury.com/releases" }, { "date": "2026-11-04", "type": "product launch", "summary": "Redesigned Mercury Treasury delivers a recommended portfolio built around monthly expenses, with U.S. Treasury ladders and automatic rebalancing as rungs mature; available for eligible customers with a $250K+ balance across Mercury accounts.", "headline": "Treasury, reinvented", "source_url": "https://mercury.com/releases" } ], "company": "Mercury", "checked_sources": [ "https://mercury.com/releases", "https://mercury.com/releases?page=2", "https://mercury.com/blog" ] }, "confidence": null, "sources": [ { "url": "https://mercury.com/releases", "title": "Mercury Release Notes | Latest Features & Product Updates" }, { "url": "https://businesswire.com/news/home/20261020220473/en/Mercury-Launches-AI-Native-Payroll", "title": "Mercury Launches AI-Native Payroll - Business Wire" }, { "url": "https://mercury.com/pricing", "title": "Explore Pricing | Mercury" }, { "url": "https://mercury.com/releases?page=2", "title": "https://mercury.com/releases?page=2" }, { "url": "https://mercury.com/jobs", "title": "Shape your career at Mercury | Job opportunities in Fintech" } ] } } ```