--- type: "nimble-use-case" name: "account-signals" description: "Nimble's account signals agent populates a timeline of a company's funding, acquisitions, leadership hires and departures, layoffs, launches, pricing changes and hiring pushes since a date you pick, from the live web. It reads the newsroom, business press, careers pages and LinkedIn posts, and gives each event its date, a summary and the source." use_when: "Finding what changed at an account since a date: funding, hires and departures, launches, layoffs, pricing and hiring pushes." not_for: "Intent data from ad networks, website visitor tracking, private deal or CRM activity." agent_id: "wsa_927116846fed492397662503d366b7ac" price_per_agent_run: { low: 0.025, medium: 0.1, high: 0.5 } updated: "2026-11-11" --- # AI web research agent for account signals (Nimble) Nimble's account signals agent populates a timeline of a company's funding, acquisitions, leadership hires and departures, layoffs, launches, pricing changes and hiring pushes since a date you pick, from the live web. It reads the newsroom, business press, careers pages and LinkedIn posts, and gives each event its date, a summary and the source. - Human page: https://www.nimbleway.com/use-cases/gtm/account-signals - Interactive demo: https://www.nimbleway.com/demos/account-signals - Agent context: https://www.nimbleway.com/use-cases/gtm/account-signals/account-signals-agent.md - Skill for agents: https://docs.nimbleway.com/skills/account-signals/SKILL.md - Docs: https://docs.nimbleway.com/nimble-sdk/web-search-agents/overview ## 1. Choose this when - You want to know which accounts to call this week, and why, from events you can cite. - You need event dates, not article dates, so old news re-reported last week does not show up as new. - You run the same check on a watchlist every week or month and want JSON you can diff. - You want "nothing changed" to come back as an empty list rather than filler. ## 2. Use something else when - You need intent data from ad networks or website visits. This agent reads public pages only. - You need a full picture of the company, not just what changed. Use the account brief agent. ## 3. Minimal request One run of the ready-made account signals agent (`wsa_927116846fed492397662503d366b7ac`). ```bash 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" ``` 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. ## 4. Use it from an agent Paste this into Claude, ChatGPT, Codex, Cursor or Grok: ```text Be my account monitoring assistant using Nimble. Follow https://docs.nimbleway.com/skills/account-signals/SKILL.md. ``` The full skill is in section 7 below. - Frameworks: `@nimble-way/mastra`, `langchain-nimble`, `@nimble-way/ai-sdk`, `llama-index-tools-nimble`, `nimble_python`, `@nimble-way/nimble-js`. ## 5. Example runs ### Mercury (recorded 2026-11-11) Input: Check Mercury (mercury.com) for changes since 2026-08-13 Run record: high effort, 3 minutes, 13 pages cited. Company: Mercury - 2026-11-10 · product launch · See more of your spending in one place: 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). https://mercury.com/releases - 2026-11-05 · product launch · Mercury Agent Controls: 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. https://mercury.com/releases - 2026-11-04 · product launch · Treasury, reinvented: 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. https://mercury.com/releases - 2026-10-20 · product launch · Introducing Mercury Payroll: Mercury launched AI-native Mercury Payroll: W-2 and 1099 contractor payroll, health benefits and 401(k) via Human Interest, and white-glove payroll compliance support, running from the Mercury account, in all 50 states, with AI capabilities via the Command agent; services provided with Check Technologies, Inc. and Check Payments LLC. https://www.businesswire.com/news/home/20261020220473/en/Mercury-Launches-AI-Native-Payroll - 2026-10-20 · pricing change · Mercury Payroll promotional then standard pricing: Mercury Payroll is free through December 31, 2026; from January 1, 2027 standard pricing is $100/month platform plus $50/month per person paid. The pricing page also lists the Payroll add-on fee and the Mercury Books fee ($35/mo) as 'waived until Dec 31, 2026'. https://www.businesswire.com/news/home/20261020220473/en/Mercury-Launches-AI-Native-Payroll - 2026-10-19 · product update · Apply for a Mercury account with a pending EIN: Businesses can now apply for a Mercury account using a completed Form SS-4 while their EIN is pending; once approved they can start using the account immediately and have 90 days from approval to provide the EIN. https://mercury.com/releases - 2026-10-15 · product launch · Take action on your Mercury account from ChatGPT and Claude: Customers can ask ChatGPT or Claude to move money, pay a recipient, or categorize transactions on their Mercury account, grounded in account data, with nothing moving until the user approves. https://mercury.com/releases - 2026-10-14 · pricing change · Priority Support now available for Plus and Pro customers: Customers on the Plus and Pro subscription plans now get faster, priority support; all Mercury customers retain 24/7 support access. https://mercury.com/releases - 2026-10-14 · product launch · All your accounts, connected: Multiple Mercury accounts can now be linked to move money between them directly; same-partner-bank transfers land in seconds, with auto-transfer rules between linked accounts and recurring transfers to accounts outside Mercury. https://mercury.com/releases - 2026-09-29 · product launch · Send real-time payments with the Mercury API: The Mercury API now supports real-time payments (realTimePayment paymentMethod), with funds arriving in seconds 24/7/365, on Business and Personal accounts provided through Column, N.A. https://mercury.com/releases - 2026-09-28 · product update · Authorize wire drawdowns for payroll: Wire drawdowns can be set up from Mercury accounts provided through both Column, N.A. and Choice Financial Group, letting payroll providers like Sequoia and Gusto withdraw funds directly. https://mercury.com/releases - 2026-09-16 · product launch · Introducing Mercury Books: Launch of Mercury Books, intelligent AI-powered accounting software built directly into Mercury. https://mercury.com/releases?page=2 - 2026-09-01 · product update · Create and send NDAs from Mercury: Users can now create and send NDAs from within Mercury. https://mercury.com/releases?page=2 - 2026-08-31 · pricing change · Invoicing API now available on all plans: Unlimited read/write access to the Invoicing API is now available to all customers regardless of subscription plan. https://mercury.com/releases?page=2 - 2026-08-25 · product launch · Send instant payments, 24/7/365: Real-time payments, free to send, rolled out on Business and Personal accounts provided through Column, N.A. https://mercury.com/releases?page=2 - 2026-08-18 · product launch · Introducing Treasury's exclusive new mutual funds: Mercury Treasury added exclusive new mutual funds built with two of the world's largest investment managers, with up to 4.11% yield and same-day access. https://mercury.com/releases?page=2 - undated · hiring push · ~80 open roles on the Mercury careers page: Mercury's careers page currently lists roughly 80 open roles across Engineering, Product, Sales, People/Recruiting, Risk/Compliance, Marketing and Data (including 18 Engineering roles and 6 recruiters), indicating an active hiring push; the page carries no dates. https://mercury.com/jobs ### Ramp (recorded 2026-11-11) Input: Check Ramp (ramp.com) for changes since 2026-08-13 Run record: high effort, 3.7 minutes, 18 pages cited. Company: Ramp - 2026-10-27 · product launch · Meet Inspect by Ramp, our collaborative coding agent: Ramp opened early access to Inspect, its collaborative coding agent. Ramp says 99% of its engineering/design/product staff used it in the past month, it accounts for 74% of merged PRs, and builders ship 6x as much code per person as a year ago. Co-CEO Karim Atiyeh announced it. https://ramp.com/blog/introducing-inspect - 2026-10-20 · acquisition · Vesto joins Ramp to give finance teams one place to manage cash: Vesto, a treasury/cash-management startup founded by Benjamin Döpfner, joined Ramp, bringing multi-bank account aggregation into Ramp Banking: connections to 12,000+ external institutions including Bank of America CashPro, J.P. Morgan Access, CitiDirect and Wells Fargo Vantage. https://ramp.com/blog/vesto-joins-ramp - 2026-10-20 · product launch · Introducing Ramp for Nonprofits: More time and money for the mission: Ramp launched a new vertical offering for nonprofits: recovery of eligible sales tax, real-time grant-balance tracking, and program-team cards with built-in controls. https://ramp.com/blog/ramp-for-nonprofits-launch - 2026-10-15 · funding round · Ramp Reaches $60 Billion Valuation as Annualized Revenue Tops $2 Billion: Ramp raised $1.85 billion in a primary financing round led by Dragoneer Investment Group and co-led by Thrive Capital, Founders Fund, Sands Capital and Avenir Growth (other investors included Fidelity, T. Rowe Price, GIC and Coatue), valuing the company at $60 billion — up from $44 billion in June 2026. Annualized revenue topped $2 billion (positive cash flow), 85,000+ businesses use Ramp, and annualized purchase volume exceeds $275 billion, up 175% year over year; total equity financing is now about $5 billion. https://www.prnewswire.com/news-releases/ramp-reaches-60-billion-valuation-as-annualized-revenue-tops-2-billion-302909315.html - 2026-10-13 · product launch · Introducing Glass: Learn things once: Ramp launched Glass, an AI workspace where knowledge compounds — skills, multiplayer sessions, Ramp Router model selection and project cost meters — turning one person's best AI work into reusable company skills. Co-CEO Eric Glyman introduced it; press coverage the same week (Oct 15) called it launched "earlier this month". https://ramp.com/blog/introducing-glass - 2026-09-22 · product launch · Introducing Ramp AR: Sales closes the deal. Ramp gets you paid.: Ramp entered a new category, Accounts Receivable: contracts and POs become ready-to-review invoice drafts, collections follow-ups are pre-drafted, incoming payments are auto-matched to invoices, and accounting records stay in sync. Over 100 businesses had already sent invoices at launch; it was Ramp's #1 customer request. https://ramp.com/blog/introducing-accounts-receivable - 2026-09-15 · new market · Today, Ramp is live in the UK.: Ramp went live in the UK, its first major operational expansion outside North America, enabled by UK and Swedish payments licenses secured through the acquisitions of travel platform Juno and payments platform Billhop. https://www.linkedin.com/feed/update/urn:li:activity:7505614676081201152/ - 2026-08-19 · product launch · Today we're launching Ramp Router.: Ramp launched Router to everyone at router.com — an OpenAI-compatible LLM router built on tooling Ramp has run internally for 3 years, powering AI products for 70,000 customers. Ramp says customers using the router spend roughly 40% less for the same work. https://www.linkedin.com/feed/update/urn:li:activity:7495922037308379136/ - undated · leadership departure · Nik Koblov, Head of Engineering, has left the company: Nik Koblov, Head of Engineering at Ramp, has left the company, per a movement entry posted October 13, 2026; the source states the posting date, not the exact departure date. https://www.theofficialboard.com/news/ramp ### Databricks (recorded 2026-11-11) Input: Check Databricks (databricks.com) for changes since 2026-08-13 Run record: high effort, 4.7 minutes, 14 pages cited. Company: Databricks - 2026-11-11 · expansion / hiring push · Databricks to Invest ~$3 Billion Across Europe and the Middle East to Accelerate Enterprise AI Adoption: Databricks announced its largest regional investment outside North America: approximately $3 billion across Europe and the Middle East over the next three years, growing local teams (EMEA headcount to grow ~50% over three years), expanding European R&D hubs (hubs in Amsterdam, Berlin, Belgrade and Aarhus all expanded over the past year, and four new EMEA offices opened in Amsterdam, Milan, Zurich and Frankfurt), plus plans to train nearly 500,000 students and professionals across EMEA by 2030. https://www.databricks.com/company/newsroom/press-releases/databricks-invest-3-billion-across-europe-and-middle-east - 2026-11-11 · product launch · DATA + AI LIVE: first look at the next generation of Genie, the data smart AI coworker: Databricks held DATA + AI LIVE on November 11 with co-founder and CEO Ali Ghodsi and OpenAI co-founder and President Greg Brockman, giving a first look at the next generation of Genie; the same day Gemini 4 Carbon also launched Day 0 on Databricks, scoring 66.7% on the company's OfficeQA Pro v2 benchmark in enterprise-document testing. https://www.linkedin.com/feed/update/urn:li:activity:7526010864475365377/ - 2026-11-10 · expansion / hiring push · Databricks to Invest More Than $500M in the Netherlands to Accelerate Enterprise Data + AI: Databricks announced (November 10, 2026) it will invest more than $500 million in the Netherlands over the next three years: doubling its Netherlands team, expanding its largest European R&D hub in Amsterdam, and a new 13,000 SQM 11-storey office in The Rock tower, Amsterdam; it also plans to train 40,000+ people in the Netherlands in data and AI skills by 2030. https://www.databricks.com/company/newsroom/press-releases/databricks-invest-more-500m-netherlands-accelerate-enterprise-data - 2026-11-09 · product releases / compliance · November 2026 Azure Databricks wave: Genie apps for Teams and Slack GA, FedRAMP High available: Azure Databricks November releases: Genie app in Microsoft Teams and Genie app for Slack GA plus Genie Search and Genie Ontology GA (Nov 9); Claude Fable 5.2 on Unity Gateway (Nov 9); FedRAMP High compliance available (Nov 5); metric view listings GA in Databricks Marketplace (Nov 5); Zerobus Ingest into default storage GA and OneLake external locations in Public Preview (Nov 2); Unity Gateway budgets now include AI Functions spend (billing change effective Nov 1); Unity Catalog wikis in Beta (Nov 6). https://learn.microsoft.com/en-us/azure/databricks/release-notes/product/2026/november - 2026-11-09 · product launch · Claude Fable 5.2 available on Databricks on Day 0: Anthropic's Claude Fable 5.2 became available on Databricks Day 0, with Unity Gateway governing, monitoring and securing every request alongside 70+ other models; it achieved state-of-the-art performance on Databricks' OfficeQA Pro v2 benchmark. https://www.linkedin.com/feed/update/urn:li:activity:7525637409653571584/ - 2026-11-05 · product launch · Introducing Apache Spark 4.3, now available in Databricks Runtime 19: Databricks shipped Spark 4.3 in Databricks Runtime 19, bringing real-time mode stateful capabilities (streaming aggregation, transformWithState), SCD Type 2 Auto CDC, Project Feather small-data performance, expanded Spark Connect, and a new quarterly feature-release cadence. https://www.linkedin.com/feed/update/urn:li:activity:7524138513643249665/ - 2026-11-04 · product launch · Kimi K3.1 Pro available on Databricks as a Day 0 launch: Moonshot AI's Kimi K3.1 Pro, its most capable open-weight model, became available on Databricks Day 0, governed alongside 70+ other models through Unity Gateway. https://www.linkedin.com/feed/update/urn:li:activity:7523847348972662784/ - 2026-10-29 · product releases · October 2026 release wave: Real-time mode in Lakeflow pipelines GA, native XML support GA, anomaly detection GA, external AI agent access GA: Databricks' October product releases (Oct 23-30) made generally available: real-time mode in Lakeflow pipelines, native XML file format, data quality monitoring anomaly detection with the system.data_quality_monitoring.table_results table (Oct 29); serverless GPU for clean room notebooks (Oct 28); request for access and default OAuth apps for external AI agents such as ChatGPT, Claude and Cursor via MCP (Oct 27-28); plus new Lakeflow Connect connectors (Microsoft Graph Logs, Xero, QuickBooks, Google Analytics), GPT-6.1 Terra on Unity Gateway, and DataFrame caching on serverless compute in preview (Oct 23). https://docs.databricks.com/aws/en/release-notes/product/2026/october - 2026-10-19 · office expansion · Databricks doubles down on New York with office expansion: CoStar News reported (October 19, 2026) that Databricks is doubling its New York office footprint at 5 Bryant Park, Manhattan. https://costar.com/article/1246335762/databricks-doubles-down-on-new-york-with-office-expansion - 2026-10-13 · partnership / customer win · Fox Corporation Selects Databricks as Strategic Partner for Next-Generation Data and AI Platform: Databricks announced a multi-year strategic partnership naming it FOX's platform for data, AI applications, and agents. https://www.databricks.com/company/newsroom/press-releases/fox-corporation-selects-databricks-strategic-partner-next - 2026-09-24 · acquisition · Databricks Acquires Row Zero, Bringing Live, Governed Spreadsheets to Genie: Databricks announced it has acquired Row Zero, the spreadsheet built for humans and agents to work with data. Founded by former AWS and Tableau engineers, Row Zero joins Databricks to add a native, fully governed spreadsheet experience to Genie across all major clouds, backed by Genie Ontology, Unity Catalog and Unity Gateway. https://www.databricks.com/company/newsroom/press-releases/databricks-acquires-row-zero-bringing-live-governed-spreadsheets - 2026-09-22 · product launch · Three new frontier models launched on Databricks Day 0: OpenAI GPT-6 Sol, GPT-6 Luna and Anthropic Claude Opus 5.5: Databricks announced OpenAI's GPT-6 Sol and GPT-6 Luna (strong performance at lower cost, higher Pareto frontier on the OfficeQA Pro benchmark) and Anthropic's Claude Opus 5.5 (better cost efficiency, strong enterprise document parsing) available on Unity Gateway with governance, budgets and cost tracking across models. https://www.linkedin.com/feed/update/urn:li:activity:7508283077748645890/ - 2026-09-22 · product launch · Databricks Genie One MCP is now generally available: Genie One MCP went GA, letting teams in ChatGPT, Claude, Cursor or custom agents access data, insights and answers from Genie One grounded in governed business context from Genie Ontology, with governance through Unity Gateway (fine-grained policies and audit logging). https://www.linkedin.com/feed/update/urn:li:activity:7508219875488825344/ - 2026-08-13 · funding · Databricks Grows >80% YoY, Surpasses $7B Revenue Run-Rate, Scales Lakebase, Genie, and Unity AI Gateway: On the cutoff date itself, Databricks closed a $5 billion strategic funding round at a $190 billion valuation, led by Coatue along with Blackstone, MGX and T. Rowe Price accounts and new investor Sixth Street Growth (other new investors: BOND, Clearlake Capital, Point72, Premji Invest, TPG). The company announced it crossed a $7 billion revenue run-rate with >80% YoY growth in Q2, surpassed a $100M run-rate for Lakebase, and has >1,000 customers consuming at over $1M run-rate. https://databricks.com/company/newsroom/press-releases/databricks-grows-80-yoy-surpasses-7b-revenue-run-rate-scales - undated · pricing · No pricing changes since 2026-08-13: A price-history tracker that has monitored Databricks' pricing page weekly since August 11, 2026 records 0 price movements across its 1 tracked tier (Standard, quote-based) — no new plans or removed tiers verified in the window. https://saaspricehub.io/tools/databricks/price-history - undated · layoffs · No layoffs since the cutoff — Databricks remains in net-hiring mode: No mass layoffs at Databricks in 2026: staffing-industry coverage updated August 27, 2026 states the company did not run a layoff in 2026 and had 840+ open roles heading into an expected second-half S-1 filing; the only reported cuts were small targeted role eliminations in early March 2026, before the cutoff. https://www.kore1.com/databricks-layoffs-2026 ### ServiceTitan (recorded 2026-11-11) Input: Check ServiceTitan (servicetitan.com) for changes since 2026-08-13 Run record: high effort, 2.4 minutes, 15 pages cited. Company: ServiceTitan - 2026-11-05 · earnings announcement · ServiceTitan to Announce Fiscal Third Quarter 2027 Financial Results on December 3, 2026: ServiceTitan announced it will report fiscal Q3 2027 financial results on December 3, 2026. https://seekingalpha.com/symbol/TTAN/press-releases - 2026-10-23 · product release · ST-82 release: The ST-82 release added Field Pro v2 (record, review and coach sales calls inside ServiceTitan), Voice Intelligence Job Creation Evaluation (Max-exclusive), Tags for Virtual Agents, Ramp Expense Management and Ramp Bill Pay integrations, and Field Mobile App 25.0 universal search, plus enhancements including spam screening for Chat alerts, deposits on sold online estimates, and MFA enablement for sensitive permissions. https://help.servicetitan.com/release-hub/docs/st-release-notes - 2026-10-13 · product launch / market expansion · ServiceTitan Launches Property Care for Enterprise Pest Control, Lawn Care, and Pool & Spa Markets: ServiceTitan announced ServiceTitan for Property Care, extending the platform into enterprise pest control, lawn care, and pool & spa markets; it brings AI-powered technology, portfolio-wide visibility, process standardization and automation to multi-location property care businesses, including a native Sentricon reporting workflow via a partnership with Corteva Agriscience. https://www.servicetitan.com/press/servicetitan-expands-into-enterprise-pest-control-lawn-care-and-pool-spa-markets - 2026-10-06 · product launch · ServiceTitan Announcing New and Expanded Capabilities at Pantheon 2026: At its Pantheon user conference in Orlando, ServiceTitan announced the AI-powered Max package is now available to every residential in-home contractor, launched a limited Max pilot for commercial and roofing contractors, launched the Atlas mobile app for owners, and launched Homh, a new consumer demand generation platform that makes contractors discoverable and bookable via AI tools (works with ChatGPT, Gemini, and Claude). https://www.servicetitan.com/press/servicetitan-announcing-new-and-expanded-capabilities-at-pantheon-2026 - 2026-10-06 · partner ecosystem expansion · New and expanded partner capabilities announced at Pantheon 2026: ServiceTitan expanded access for AI CSRs to Adaptive Capacity (AdCap) scheduling intelligence, announced a direct Ramp integration, a supplier self-service portal, and Financing Preapprovals with GreenSky Prescreen and Synchrony QuickScreen. https://www.servicetitan.com/press/servicetitan-announcing-new-and-expanded-capabilities-at-pantheon-2026 - 2026-09-30 · partnership · ServiceTitan Announces Strategic Partnership with Ramp to Automate Financial Workflows For Contractors with AI-Powered Tools: ServiceTitan announced a new strategic partnership with Ramp, the financial operations platform, to automate financial workflows for contractors with AI-powered tools. https://www.servicetitan.com/press/servicetitan-announces-strategic-partnership-with-ramp-to-automate-financial-workflows-for-contractors-with-ai-powered-tools - 2026-09-24 · product release · ST-81 Release: The ST-81 release introduced self-serve Automations and expanded Voice Agent with automatic unsold-estimate recovery, plus 33 additional new or improved features across core, pro, early-access, Fintech and mobile products. (The prior ST-80 release shipped September 3, 2026 with MFA enhancements and 26 new or improved features.) https://help.servicetitan.com/release-hub - 2026-09-08 · leadership hire · ServiceTitan Names Rikus Pretorius Next Chief Revenue Officer: ServiceTitan announced the appointment of Rikus Pretorius as its next Chief Revenue Officer. https://www.servicetitan.com/press/servicetitan-names-rikus-pretorius-next-chief-revenue-officer - 2026-09-08 · earnings / financial results · ServiceTitan Announces Fiscal Second Quarter Financial Results: Fiscal Q2 2027 (quarter ended July 31, 2026) results: total revenue $292.8M (up from $242.1M a year earlier, +21% Y/Y), GTV $26.8B (+17% Y/Y). ServiceTitan said it exceeded its goal of doubling Max locations during Q2 and now expects to end the fiscal year with over 700 enrolled Max locations; guidance for fiscal Q3 2027 revenue of $285–$287M and full fiscal year 2027 revenue of $1,139–$1,144M. https://investors.servicetitan.com/news-releases/news-release-details/servicetitan-announces-fiscal-second-quarter-financial-results-0 - undated · hiring · 68 open roles on ServiceTitan's Workday careers board: ServiceTitan's Workday job board listed 68 open jobs as of 2026-11-11, with fresh postings spread across functions in the two weeks prior — e.g. Sales Development Representative (Toronto, posted ~2026-11-10), Senior Analyst, Enterprise Sales Strategy & Operations (Glendale, CA), Head of Product, Fintech, Group Product Manager, Onboarding & Agentic Success, and Director of Billing and Collections — rather than a concentrated single-function hiring push. https://servicetitan.wd1.myworkdayjobs.com/ServiceTitan - undated · pricing — no change found · No published pricing change since 2026-08-13: ServiceTitan's pricing page shows three packages (Starter, Essentials, The Works) with no published prices ("Request Pricing") and no dated change history, so no pricing change since the cutoff is evidenced there; a third-party pricing tracker last verified pricing on July 11, 2026 (before the cutoff) at Starter $250, Essentials $398, The Works $498 per user/month with no free tier and a 2-year minimum commitment. https://www.servicetitan.com/pricing ## 6. Questions ### What are account signals? Public events that suggest a company may be ready to buy or that change how you should approach it: a funding round, an acquisition, a new executive, layoffs, a new office or market, a product launch, a pricing change or a hiring push in one team. ### How does the agent avoid old news? It filters on the date the event happened, not the date an article was published, because re-reported old news is the most common false signal. Every event comes back with its date and the page it was read on, so you can check it. ### How often should I run it? As often as your sales motion needs. A weekly run on a watchlist is common. Each run is one call with the company and a start date, so you can set the date to your last run and only see what is new. ### Can I run account signals checks from Claude, ChatGPT or my own agent? Yes. Paste this prompt into Claude, ChatGPT, Codex, Cursor or Grok: "Be my account monitoring assistant using Nimble. Follow https://docs.nimbleway.com/skills/account-signals/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. ## 7. Skill The skill the prompt points to, as published at https://docs.nimbleway.com/skills/account-signals/SKILL.md (copied 2026-11-11). ### Account signals Lists what changed at an account since a date: funding, exec moves, launches, pricing changes and hiring pushes, each dated and cited. #### What the user gets Only events dated after the since date, each with date, type, headline, summary and source. If nothing changed, an empty list and the sources it checked. #### Agent template This skill runs the Nimble gallery template `account-signals`. The agent's instructions, sources and output schema live in the template. Do not rewrite them in the run. Effort: this skill runs the template at medium effort (about 1-3 minutes), even when the template's default effort is different. That is on purpose. If the user asks for a specific effort (low, medium, high or x-high), run that one instead. #### Flow 1. Interview the user. 2. Connect Nimble if it is not connected already. 3. Run the agent and show the result. 4. Offer next steps. Ask every question with the host's question UI, never as plain text: `AskUserQuestion` in Claude Code, ChatGPT's interactive question form (clickable choices and a Submit button) in ChatGPT. ##### Get the inputs | Input | Required | Ask for | If skipped | | - | - | - | - | | Account | yes | Name and domain | - | | Since | no | A date in YYYY-MM-DD | last 30 days | | Signal types | no | For example "only exec hires and funding" | all signal types | * Skip anything the user already said in this conversation or in their request, and ask only for what is missing. Do not fill in answers from earlier conversations, with one exception: a stable fact about the user, such as what they sell, may be offered as the first option, labeled "(from before)". Never carry over the subject of the request, dates or rules from an earlier conversation. * Ask the required inputs first, in table order, one question at a time. Then ask the optional ones together, in one question-tool call, as many as the tool takes per call (a second call for the rest). * Put the whole question in the question tool, once. Never restate or introduce a question in text. Between questions, acknowledge the answer in a few words, and before the first question, at most one short sentence that acknowledges your role (the user's, if they named one), such as "Sure, I'll use Nimble to be your account monitoring assistant." Talk in plain, friendly words: never say "input", "required" or "optional", and use no field names. Use plain text only if the host has no question tool, in one short line. * Write 2-3 likely answers as options, based on what the user has already said. Fixed examples in the table are a guide to what the answer contains, not a list to copy. Offer only answers Nimble can act on with public web data, never ones that need the user's own data, such as their customers or CRM. * If you cannot guess likely answers, such as a company name or an industry, still use the tool and offer two or three examples as options, written as answers the user could really give. If the user picks one, use it as their answer. * Every question must let the user type their own answer, optional ones too. Claude's question UI adds its own free-text choice ("Something else" in Claude, "Other" in Claude Code), so add none there. ChatGPT's form does not, so add "Other" as the last option of every question, even one whose options look complete, opening a text field with a placeholder. In any other host, add "Other" unless you know its UI already has a free-text choice. Keep Skip and Other, when you add them, even if you must drop an answer to fit the option limit. * Use single-select only. For a range, such as a size or a date, offer a few options that do not overlap. * Optional questions can be skipped, and a skipped answer uses the "If skipped" value. Claude's question UI has its own Skip button, so add no Skip option there. In other hosts, include a Skip option that states the default in its label, for example "Skip (any location)", not in the question. When you acknowledge a skipped question, say the default you will use, for example "Any location.", not that it was skipped. Do not offer a "skip all" option. If the user asks to skip the remaining questions, use the "If skipped" values for all of them. * Do not ask about effort. Build the agent input from this pattern: ``` Check () for changes since ``` Example: `Check Mercury (mercury.com) for changes since 2026-09-21` * One account at a time. If the user names several, run the first and offer the rest next. * Always pass an explicit date in YYYY-MM-DD form. A skipped Since means the date 30 days before today. Take today's date from the host or by running `date`, and if you have neither, ask the user for the date. * If they only care about some signal types, add one line to the input. ##### Connect Nimble Do this after the interview. Until the questions are done, say nothing about connecting Nimble. Check the connection. If a Nimble tool is listed in this session, call `nimble_agents_list`. If the CLI is available, run `nimble --client-source nimble-agent-skills agents list`. A normal response from either, even an empty list, means the user is connected: say nothing and go on. If neither check succeeds (no tool is listed and the CLI is missing or fails, or a check returns an auth error or an authorization link), connect it in these steps. Your message is only these steps: no summary of what the user told you, no mention of the skill, the template or the workflow, and no plan for what happens after connecting (that belongs in the run notice). 1. Tell the user, in two short sentences at most: "Nimble searches the live web and links where every answer came from. Connecting takes one approval, and if you're new to Nimble you start with a free trial." 2. Connect it in the first of these ways that works, and stop at the first one that does: * Show the host's card to connect or install Nimble from nimbleway.com: the Connect card for the connector in Claude, the install card for the plugin in ChatGPT. * If you can't show a card and a check returned an authorization link, show that link to the user. * If you can do neither but can run commands, follow [https://docs.nimbleway.com/agent-onboarding.md](https://docs.nimbleway.com/agent-onboarding.md) and involve the user only for the sign-up and the approval. With only the CLI and no `NIMBLE_API_KEY`, an approval is not enough: follow the page's API key fallback and have the user set the key in their environment, never in the chat. That page is written for you: never link it or its steps to the user. * If none of these works, tell the user how to find Nimble in this app, with the clicks: in ChatGPT, open Plugins in the sidebar, search for Nimble, pick the one described as "Expert web search for agents" and install it; in Claude, open Customize, then Connectors, then Nimble, then Connect. Never send the user to nimbleway.com for this. 3. Ask with the question tool, with the options "I've connected Nimble" and "Not now". If the host has no question tool, end the message by asking them to reply "connected", and add nothing after that. Never ask the user to paste an API key into the chat. When they confirm, check the connection again and go on without comment. If it is still not connected, say so in one line and ask again. If they pick "Not now", say the skill needs Nimble and stop. Show no research until Nimble is connected, not from your own search and not from memory. ##### Run the agent Do not comment on the connection check or on creating or reusing the agent. The first thing the user hears is step 2. 1. Create the agent from the template: `nimble_agents_create(template="account-signals", agent_name="account-signals")`. A 409 "already exists" means it was created before, so go on. If the template is not found, tell the user it is unavailable and stop. Do not substitute another template. 2. Tell the user once, in one line, what you are researching and how long it takes at the effort you will use: "Researching \. Expected to take \