--- type: "nimble-use-case" name: "decision-maker-identification" description: "Nimble's decision-maker agent populates a list of the people in the roles you need at a company, with each person's current title, start date, past roles and public profiles, from the live web. It reads leadership pages, appointment press releases, interviews and LinkedIn profiles, and shows the source and how each match was made." use_when: "Finding who currently holds specific roles at a company, with their title, start date, history and a source." not_for: "Emails and phone numbers, org charts below the leadership level, people search across many companies at once." agent_id: "wsa_5cb77b8983124cf29be882b152a8792b" price_per_agent_run: { low: 0.025, medium: 0.1, high: 0.5 } updated: "2026-11-11" --- # AI web research agent for finding decision makers (Nimble) Nimble's decision-maker agent populates a list of the people in the roles you need at a company, with each person's current title, start date, past roles and public profiles, from the live web. It reads leadership pages, appointment press releases, interviews and LinkedIn profiles, and shows the source and how each match was made. - Human page: https://www.nimbleway.com/use-cases/gtm/decision-maker-identification - Interactive demo: https://www.nimbleway.com/demos/decision-maker-identification - Agent context: https://www.nimbleway.com/use-cases/gtm/decision-maker-identification/decision-maker-identification-agent.md - Skill for agents: https://docs.nimbleway.com/skills/decision-maker-identification/SKILL.md - Docs: https://docs.nimbleway.com/nimble-sdk/web-search-agents/overview ## 1. Choose this when - You know the roles you sell to and need the person in each one at a target account. - You need to know the person is current, from a dated source in the last year or a profile showing this company now. - Titles vary by company and you want the closest match with a note on how it was made. - You want roles nobody holds listed as missing rather than filled with a guess. ## 2. Use something else when - You need emails or phone numbers. Most are not on public pages, and the agent does not construct them from patterns. - You need a full org chart below the leadership level. ## 3. Minimal request One run of the ready-made decision-maker identification agent (`wsa_5cb77b8983124cf29be882b152a8792b`). ```bash AGENT_ID=wsa_5cb77b8983124cf29be882b152a8792b # Nimble's decision-maker identification agent curl -X POST "https://sdk.nimbleway.com/v2/agents/$AGENT_ID/runs" \ --header "Authorization: Bearer $NIMBLE_API_KEY" \ --header 'Content-Type: application/json' \ --data '{"input":"At Gong, find the current CTO, CMO, head of revenue operations and CFO","effort":"high"}' # poll until is_active is false, then read the result curl "https://sdk.nimbleway.com/v2/agents/$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`, `people` (a list of `{ target_role, full_name, title, started_role, as_of, match_note, source_url, linkedin_url, career_history, public_profiles }`) and `missing_roles` (roles nobody could be confirmed for, with the reason). ## 4. Use it from an agent Paste this into Claude, ChatGPT, Codex, Cursor or Grok: ```text Be my contact research assistant using Nimble. Follow https://docs.nimbleway.com/skills/decision-maker-identification/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 ### Gong (recorded 2026-11-11) Input: At Gong, find the current CTO, CMO, head of revenue operations and CFO Run record: high effort, 3.6 minutes, 6 pages cited. Company: Gong (Gong.io Ltd.) — San Francisco, CA - CTO: Liron Shtraichman, Chief Research & Development (R&D) Officer, since 2026-11. Gong's own leadership page (retrieved 2026-11-11) publishes no titled CTO; the Chief R&D Officer is the leader with CTO scope (global engineering, products and platforms). Announced Nov 4, 2026; previously led engineering at monday.com. A workforce-database row listing 'Patricia Gibson' as Gong CTO (London, since 2018) could not be corroborated on LinkedIn (profile 404, no search hit) and is treated as a data error, not a namesake confirmation. https://www.gong.io/press/gong-leadership-liron-shtraichman-chief-r-and-d-office - CMO: Emily He, Chief Marketing Officer, since 2024-05. Appointed Chief Marketing Officer per Gong press release dated May 15, 2024; still listed as Chief Marketing Officer at Gong in the LinkedIn-linked employee roster updated 2026-10-03. https://www.gong.io/press/gong-appoints-emily-he-as-chief-marketing-officer-2 - Head of Revenue Operations: Matthew Flotard, VP, Revenue Operations, since 2025-11. Gong has no 'Head of Revenue Operations' title; the most senior revenue-operations role is VP, Revenue Operations. Matthew Flotard's LinkedIn shows 'VP, Revenue Operations' at Gong as his current position (headline: 'VP RevOps @ Gong'), New York, started Nov 2025; the same role and start date appear in the LinkedIn-linked employee roster. He is the only VP-level revenue-operations leader in Gong's roster (other revenue-operations staff are managers/directors, incl. a regional Head of Revenue Operations EMEA at director level, Gerry Cunningham). https://www.linkedin.com/in/matthewflotard - CFO: Tim Ritters, Chief Financial Officer, since 2019-10. Listed as Chief Financial Officer on Gong's own leadership page (retrieved 2026-11-11); his LinkedIn profile confirms Chief Financial Officer at Gong.io as current position since Oct 2019 (headline 'Growth CFO'). Also shown as CFO on third-party org-chart and executive listings. https://www.gong.io/about Not confirmed: - CTO — Gong's own leadership page publishes no titled Chief Technology Officer (as of 2026-11-11); CTO scope sits with the Chief R&D Officer, Liron Shtraichman (appointed Nov 4, 2026). A workforce-database row naming 'Patricia Gibson' as Gong CTO could not be corroborated on LinkedIn and appears to be a data error. - Head of Revenue Operations — no 'Head of Revenue Operations' title exists company-wide; the most senior revenue-operations role is VP, Revenue Operations (Matthew Flotard, since Nov 2025). The only person with a 'Head of Revenue Operations' title is regional (Head of Revenue Operations EMEA - Director, Gerry Cunningham, Dublin, since Aug 2025). ### Datadog (recorded 2026-11-11) Input: At Datadog, find the current chief revenue officer, VP of sales, head of revenue operations and head of sales enablement Run record: high effort, 3.2 minutes, 5 pages cited. Company: Datadog (NASDAQ: DDOG) — New York, NY - Chief Revenue Officer: Sean Walters, Chief Revenue Officer, since 2022-01. Listed as Chief Revenue Officer on Datadog's own leadership page (retrieved 2026-11-11) alongside the current executive team (Pomel, Lê-Quôc, Obstler, Blitzer etc.), confirming he is current, not a former-bio artifact. Datadog's January 19, 2022 press release announced his appointment as CRO; he joined Datadog in 2018 and was previously SVP of Sales there. Same person across both sources (Rowan University background, Medallia/IBM prior). https://www.datadoghq.com/about/leadership/ - VP of Sales: Kenny Smith, Vice President, Sales - Americas (LinkedIn headline: "Vice President of Sales @ Datadog"), since 2023-01. Datadog publishes no company-wide "VP of Sales" title — the sales organization is led by the CRO with regional/segment vice presidents beneath him; Kenny Smith holds the broadest VP-of-sales scope, "Vice President, Sales - Americas", leading Datadog's 350+ person North America and LATAM Commercial Sales GTM. Current position on his LinkedIn profile (top position at Datadog, no end date, is_current_position true). Profile is at the Datadog company (urn:li:fsd_company:1066442) and describes NASDAQ: DDOG, so not a namesake. https://www.linkedin.com/in/kenny-smith-7063a64 - Head of Revenue Operations: Miika Groden, Vice President, Revenue Operations, since 2026-03 (VP role; at Datadog since 2018). The most senior revenue-operations leader at Datadog: promoted to Vice President, Revenue Operations in March 2026 from Senior Director, Revenue Operations. Top position on her LinkedIn profile is at Datadog (urn:li:fsd_company:1066442) with no end date, is_current_position true; a nine-year Datadog revenue-operations career ladder rules out a namesake. https://www.linkedin.com/in/miika-groden-a6b73153 - Head of Sales Enablement: Jessica Shyu, Senior Director, Sales Enablement (headline: "Senior Director, Global Sales & Customer Success Enablement @Datadog"), since 2025-03 (current role; at Datadog since 2022-09). Datadog has no published "Head of Sales Enablement" title; Jessica Shyu is the most senior enablement leader found — Senior Director, Sales Enablement with global scope over sales and customer-success enablement, current on her LinkedIn profile (Datadog, is_current_position true, no end date). She leads the Sales Enablement function Datadog's careers page names as a sub-team. The only other head-titled enablement person, Christian Lochner, is regional (Head of Technical Enablement EMEA & APAC), below her global scope. https://www.linkedin.com/in/jessicashyu Not confirmed: - VP of Sales (company-wide) — no such title is published; Datadog's sales organization is led by the Chief Revenue Officer (Sean Walters) with regional/segment vice presidents beneath him (e.g. VP Sales - Americas Kenny Smith, VP Commercial Sales APJ Adrian Towsey, Regional VP Enterprise Sales roles in EMEA/APJ/LATAM). Kenny Smith's Americas VP role is listed as the closest same-scope match. - Head of Sales Enablement — no head-titled global sales-enablement role is published; the most senior enablement leader is Jessica Shyu, Senior Director, Sales Enablement (global Sales & Customer Success Enablement), listed as the closest match. Christian Lochner holds a head-titled but regional and technical role (Head of Technical Enablement, EMEA & APAC). ### Shopify (recorded 2026-11-11) Input: At Shopify, find the current CTO, CISO, VP of engineering and head of IT Run record: high effort, 2.2 minutes, 8 pages cited. Company: Shopify (NYSE/TSX: SHOP) — Ottawa, Canada - CTO: Mikhail Parakhin, Chief Technology Officer, since 2024-09. Shopify announced him as CTO in 2024; TIME named him a 2026 Executive of the Year as Shopify's CTO (Sep 22, 2026). On Oct 19, 2026 BetaKit confirmed with Shopify that Parakhin is departing as CTO and transitioning to an advisor, with no successor named as of the Oct 20-21, 2026 coverage; no later source names a replacement, and his LinkedIn profile (retrieved 2026-11-11) still lists Shopify CTO as his current position. Same person as the former Microsoft/Yandex executive, not a namesake. https://betakit.com/shopify-cto-mikhail-parakhin-to-depart-after-two-years/ - VP of Engineering: Farhan Thawar, VP & Head of Engineering, since 2019-06. LinkedIn profile (record updated 2026-11-11) shows VP & Head of Engineering at Shopify as his current position since Jun 2019, with headline 'Head of Engineering @ Shopify'. The Shopify Toronto-based engineering leader, not a namesake; no other person holds this scope. https://www.linkedin.com/in/fnthawar - CISO: Andrew Dunbar, Chief Information Security Officer, since 2023-06. LinkedIn profile (retrieved 2026-11-11) lists Chief Information Security Officer at Shopify as his current position since Jun 2023; Infosecurity Magazine's Jun 24, 2026 interview is titled 'Shopify CISO Andrew Dunbar' and he leads Shopify's cybersecurity operation, having joined in 2012 as one of its first hundred employees. A TheOrg page naming John Asante as Shopify CISO is outdated — John Asante is at Bank of America, not Shopify. https://www.linkedin.com/in/andrew-dunbar-37605911 Not confirmed: - Head of IT — no public source names a current head of IT at Shopify. Shopify's leadership/board pages and third-party executive rosters (The Org, The Official Board) list no such role; Shopify's LinkedIn employee roster (2,107 records in the IT/engineering group, retrieved 2026-10-03) shows only non-leadership IT titles such as 'Senior IT Logistics Specialist', and LinkedIn title searches for 'Head of IT' and 'Director of Information Technology' at Shopify (2026-11-11) return no person holding those titles. The closest published scope was Andrew Dunbar's former 'VP of Security Engineering and IT' role, which he held 2019-01 to 2023-06 before becoming CISO; internal IT leadership today is not published. - CTO successor — Mikhail Parakhin is departing as CTO (confirmed with Shopify by BetaKit, Oct 19, 2026), but no successor had been named in any source as of Nov 11, 2026, and his own LinkedIn still lists the Shopify CTO role as current. ### Ramp (recorded 2026-11-11) Input: At Ramp, find the current CFO, controller, head of procurement and VP of finance Run record: high effort, 3 minutes, 6 pages cited. Company: Ramp (Ramp Business Corporation, ramp.com) — New York, NY - CFO: Will Petrie, Chief Financial Officer, since 2025-01. Same person across sources: Ramp's official blog (Jan 21, 2025) announced the promotion of Will Petrie to Chief Financial Officer, signed by co-founders Eric Glyman and Karim Atiyeh at Ramp Business Corporation (ramp.com, New York, NY); LinkedIn records list him as William Petrie, Chief Financial Officer at Ramp (LinkedIn company id 1406226), based in New York. He had been VP, Strategic Finance at Ramp since December 2022 before the promotion. https://ramp.com/blog/strengthening-our-leadership-bench - Controller: Melissa Montgomery, VP, Controller, since 2025-07. Confirmed by two independent sources on Ramp's own domain: the official author page at ramp.com titles her 'VP Controller, Ramp' and says she leads the accounting team at Ramp, and her LinkedIn profile lists 'VP, Controller' at Ramp (current position, started July 2025). Not a namesake: same Ramp Business Corporation entity (LinkedIn company id 1406226), San Francisco. https://ramp.com/authors/melissa-montgomery Not confirmed: - Head of Procurement — no one holds this title at Ramp. A search of Ramp's LinkedIn finance-department roster for every procurement-related person returns only entry-level roles: Andrew Lavine (Account Executive, Procurement & AP), Andrew Suiter and Gabriel Rogoff (Procurement Architect), Sebastien Goddijn (Procurement & Internal AI) and a Staff Software Engineer, Procurement (Kevin Chan); no head-level procurement role appears in any of these records or on Ramp's published org chart. Ramp sells procurement as a product line; its overall product suite is led by Chief Product Officer Geoff Charles. - VP of Finance — no current 'VP of Finance' title exists at Ramp as of the October–November 2026 records. The former VP, Strategic Finance (Will Petrie) was promoted to CFO in January 2025; the only VP-level finance titles on Ramp's finance roster today are VP, Controller (Melissa Montgomery) and Director of Financial Systems (William Simmons). Caution: a 'Head of Finance & Capital Markets' record still shows Chris Geoffroy at Ramp in the workforce data, but his own LinkedIn profile shows he left Ramp in October–November 2025 and now holds that title at another company ('Something New'), so he is not a current Ramp executive. ## 6. Questions ### How does an AI agent find decision makers? It reads the company's leadership or team page, press releases announcing appointments, conference speaker bios, podcast and webinar pages, and LinkedIn profiles. For each role you ask for, it returns the person who holds it now, their title, when they started, past roles and public profiles, with the page the match came from. ### What if the company does not use the title I asked for? Titles differ by company size: Head of, VP, Director and Chief can be the same job. The agent returns the person with the same scope and explains the match in match_note. In the Gong example, there is no titled CTO, so it returns the Chief R&D Officer and says why. ### How does it avoid former employees and namesakes? A person counts as current only with a dated source from the last year or a profile whose current position is this company. Same-name people at other companies are ruled out using company, location or other context on the page. ### Can I run decision-maker research from Claude, ChatGPT or my own agent? Yes. Paste this prompt into Claude, ChatGPT, Codex, Cursor or Grok: "Be my contact research assistant using Nimble. Follow https://docs.nimbleway.com/skills/decision-maker-identification/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/decision-maker-identification/SKILL.md (copied 2026-11-11). ### Decision-maker identification Finds the people who hold given roles at a company today, with current title, career history and the source that proves it. #### What the user gets For each role, the person who holds it now: name, exact title, start date, previous roles, public profiles and a dated source. Roles it cannot confirm are listed as missing. #### Agent template This skill runs the Nimble gallery template `decision-maker-identification`. 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 | | - | - | - | - | | Company | yes | Name and domain | - | | Roles | yes | Up to about 5, for example "CFO, head of RevOps, VP engineering" | - | | Region or business unit | no | For a large company, for example "EMEA" or "the payments team" | whole company | * 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 contact research 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: ``` At (), find the current , , in ``` Example: `At Gong, find the current CTO, CMO, head of revenue operations and CFO` * One company at a time. If the user names several, run the first and offer the rest next. * Use the title the company would use. "Head of RevOps" finds more than "Revenue Operations Leader". * If they ask for emails or phone numbers, say up front that it does not return them. * Leave out any part of the pattern the user skipped: leaving it out is the default. ##### 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="decision-maker-identification", agent_name="decision-maker-identification")`. 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 \