generate_digital_room
ChatGPTPurpose: Create a Digital Sales Room (DSR) from a selected template and selected content items. Workflow requirement: When user asks to create a digital room, first call get_digital_room_templates, then capture the user-selected template, and finally call this tool with templateId + contentIds + roomName. Do not call this tool until the user has explicitly confirmed they are ready to create the Digital Room (for example, "Yes" after you show a summary of template, content, and room name). A maximum of 50 content items may be included. Do not attempt to add more than 50 items.
generate_pitch
ChatGPTPurpose: Generate exactly one AI-powered pitch using specific Highspot content items. Use when: Users want to create a single pitch based on previously found content items (from search or instant answer tools). IMPORTANT: Do not create multiple pitches in one call. If a user asks for many pitches (e.g., "create 5 pitches"), politely explain the tool can only generate one pitch at a time and ask which single pitch they want. The user must reference specific item numbers or IDs from previous responses. User triggers: "create a pitch using item 1," "generate pitch from these items," "use item X to create a pitch." System notes: Requires item IDs from previous tool responses. Creates personalized pitches by combining selected content.
generate_roleplay
ChatGPTPurpose: Create an AI-generated roleplay scenario in Highspot. Generates ALL THREE components (persona, scenario, rubric) in a single job. IMPORTANT — conduct the pre-call interview one question at a time. Do not ask multiple questions in a single message. Wait for the user's answer before asking the next. Interview order (one at a time): 1. Who is the persona and what is the conversation setting/context? 2. What objections or concerns will the persona raise? 3. What will the learner see as a scenario summary? 4. What is the learner's goal? (e.g. "Schedule a follow-up call") 5. (Optional) Is there any Highspot content to use as reference material? If yes, use search_content and collect the item IDs. 6. Suggest a title based on the answers collected so far. Present it as a suggestion and ask the user to accept or provide their own. Use their response as the title field. If persona_item_id or rubric_item_id are already known, pass them automatically — do not ask the user. User triggers: "create a roleplay", "generate a roleplay scenario", "make a roleplay for [topic]". The roleplay is saved to the user's personal spot by default.
get_content_answer
ChatGPTPurpose: Provide a direct answer to a specific question using Highspot content. Use when: Users ask for explanations or guidance or synthesis from Highspot content ("What is…," "How do…," "Why does…," "When should…"). AI synthesizes across content and includes source links. User triggers: "what," "how," "why," "when," "explain," "tell me about." System notes: Answers MUST be grounded in actual Highspot content. Must include clean, readable source links at the end.
get_content_recommendations
ChatGPTPurpose: Get AI-powered content recommendations from Highspot based on a search query. Use when users ask for content suggestions, relevant materials, or documents related to a topic. The system returns a list of recommended content items with titles and file names. User triggers: "recommend content," "suggest," "suggest documents," "content for," etc.
get_deal_answer
ChatGPTPurpose: Provide direct answers about CRM opportunities by combining Highspot and deal data. Use when: Users ask questions about Salesforce/Dynamics opportunities such as deal details, status, stage, forecast, or CRM-related information or actions and lookup_deal has returned a valid crm_opportunity_id ("What is…," "How do…," etc.). AI synthesizes the answer and includes source links. User triggers: "deal," "opportunity," "Salesforce","record," "CRM." System notes: Only use when the question is CRM/deal-related.
get_digital_room_content_blocks
ChatGPTPurpose: Fetch the content-block structure of a specific Digital Room (block ids, friendly names, types, order, and item ids). Each block is labeled with the seller internal name when set, otherwise "Content block N" where N is its position in the returned list (1-based). Technical block names are not returned. Use the label when presenting choices. Use Block ID for update_digital_room_content. Workflow requirement: When the user wants to update a Digital Room, this is step 2—call after get_digital_rooms once the user has chosen a digital_room_id. Present blocks and items, have the user pick a block_id, then call update_digital_room_content (find content in Highspot first when adding new items). User triggers: "update digital room," "what is in this digital room," "show blocks in my DSR." Trigger keywords vary per surface.
get_digital_room_templates
ChatGPTPurpose: Retrieve Digital Room templates for creating digital sales rooms. Default is recently used templates (top 10 on first call). Pagination: limit defaults to 10, max 20 per request. Use start from the Next page line when Can load more templates is Yes. When template_source is omitted or recently_used: first page (start=0) with no recently used templates falls back to company official templates. Set template_source to official to list only company templates. Response is formatted text including "Can load more templates: Yes/No". When Yes, follow the Next page line exactly (official source responses require template_source=official). Do not use API row counts or sum start/limit/next-page offsets to infer a global total—count only Template ID lines across all pages fetched. Display instruction: Always include the Source line (and fallback Note, if present) when presenting templates to the user. When Source is recently used, tell the user they can also browse company official templates (user can ask for "official templates" or "company templates" - call this tool with template_source=official). Show all templates returned on this page in the list (do not subset or hide entries). Refer users to Template ID, not list position. Never invent template names or IDs not in the tool output. User triggers: "digital room templates," "available templates," "company templates," "templates I used before." Context requirement: Before calling this tool or presenting templates, verify you know what the Digital Room is for (deal stage, buyer profile, or use case) OR that the user asked for a specific Digital Room Template by name. If that context is missing, ask exactly one clarifying question first (e.g. "What kind of scenario is this Digital Room for?"). Do not call this tool until you have enough context to choose relevant templates or the user asked to browse all templates. When a Salesforce/Dynamics deal is already resolved in this conversation (lookup_deal returned crm_opportunity_id and crm_org_id) and you still lack deal stage, buyer profile, or use case context, call get_deal_answer first (reuse the same CRM ids) to gather that context before calling this tool or recommending templates.
get_digital_rooms
ChatGPTPurpose: List Digital Rooms the user owns or edits. Workflow requirement: When the user wants to update a Digital Room, this is step 1—call this tool first, show the numbered list (local 1..N on each page), and have the user pick a room. Then, call get_digital_room_content_blocks with the Digital Room ID from that row (never use list numbers from other pages as identifiers). Discovery: when the user ties the room to a CRM opportunity or deal, pass deal_id to return only Digital Rooms linked to that deal. Optional has_mutual_action_plan: true = only rooms with a mutual action plan (filtered by the server), false or omit = all rooms. Pagination: use start (default 0) and limit (default 10, max 200). For more results, call again with start equal to the previous start + number of rows returned. User triggers: "update digital room," "change my digital room," "edit DSR content," "digital room for this deal." Trigger keywords vary per surface.
get_item_content
ChatGPTPurpose: Retrieve the full raw content of a specific Highspot document for deep research or analysis. Use when: Needed to analyze structure, extract data, or perform detailed review. User triggers: None — users will not request this directly. System triggers: should be invoked internally in deep research/deep analysis or research mode when another tool (e.g., get_content_answer) requires the complete text/binary to fulfill a user request. Requires item_id from search_content or get_content_answer tools.
get_meeting_answer
ChatGPTPurpose: Answer questions and generate summaries about one specific past meeting using the Highspot Meeting Agent. The Meeting Agent synthesizes the answer and inline transcript citations. MCP returns that Markdown unchanged. The underlying Meeting Agent may invoke write-capable skills when the user's request requires an action. Use when: The user is asking about what happened inside ONE specific meeting, call, or conversation AND a valid Meeting ID has already been resolved earlier in the conversation (for example lookup_meeting returned one) or the user supplied an explicit Meeting ID. Once a meeting is resolved, keep reusing that same Meeting ID for follow-ups about "this meeting," "that call," "it," etc. Routing boundary for meeting-related queries (only applies when lookup_meeting/get_meeting_answer are available in tools/list, gated by mcp_meeting_agent feature flag): - A natural-language reference identifying a meeting, call, or conversation routes to lookup_meeting. - A question about what happened inside one explicit or previously resolved meeting routes to get_meeting_answer. - A reference identifying an opportunity, account, or CRM record routes to lookup_deal. - Questions about opportunity status, health, risk, forecast, or stakeholders route to get_deal_answer, even when meeting activity is mentioned as part of the deal context. Example queries, with correct tool routing: - "What happened in the Acme Corp renewal meeting on August 15th?": lookup_meeting - "What happened in meeting with the ID 1234567890?": get_meeting_answer - "What happened in the renewal meeting for the opportunity with ID 1234567890?": lookup_meeting (lookup_meeting is used because the user is asking about a meeting, not an opportunity, even though the opportunity ID was mentioned) - "What's the status of the Acme Corp renewal opportunity that we discussed in the meeting on August 15th?": lookup_deal - "What's the status of the Acme Corp renewal opportunity that we discussed in the meeting with ID 1234567890?": lookup_deal (lookup_deal is used because the user is asking about an opportunity, not a meeting, even though the meeting ID was mentioned) - "What's the status of the Acme Corp deal with ID 1234567890 that we discussed in the meeting with ID 1234567890?": get_deal_answer (get_deal_answer is used because the user is asking about an opportunity, and provided a specific opportunity ID, even though the meeting ID was also mentioned) Routing: - If no meeting has been resolved yet and the user did not provide an explicit Meeting ID, call lookup_meeting first. - When the user already provides an explicit Meeting ID, call get_meeting_answer directly. - Questions about opportunity status, health, risk, forecast, or stakeholders route to get_deal_answer even when meeting activity is mentioned as deal context. - Deal-level meeting prep or cross-deal meeting assessment that is not scoped to one selected transcript route to get_deal_answer. User triggers: "what happened on the call," "summarize the meeting," "what objections came up," "who said pricing," follow-up pronouns on a meeting already established in the conversation.
get_rep_answer
ChatGPTPurpose: Answer any question that spans multiple deals/opportunities for a sales rep, using the Highspot Rep Agent. Unlike get_deal_answer (which is scoped to a single, already-resolved CRM opportunity), this tool reasons across a rep's entire book of business — prioritization, risk surfacing, pipeline summaries, and activity recaps that no single deal record can answer on its own. The agent pulls from CRM data and Highspot engagement/content data across all of a rep's active deals and returns a synthesized answer with source links back to the relevant deals. Capabilities include prioritization across open deals ('what should I focus on today/this week'), risk surfacing across the book of business (stalled deals, overdue tasks, disengaged stakeholders, deals slipping stage/close date), pipeline/portfolio summaries (deals by stage, forecast category, close date), activity recaps over a time range (what happened across accounts while away, what changed since a given date), and cross-deal pattern spotting (common objections, similar stakeholders, deals needing the same type of content or follow-up). Use when: The question spans more than one deal/opportunity, or doesn't name a specific opportunity at all — it's about the rep's overall pipeline, book of business, or portfolio. This includes relative/time-based framing ('this week,' 'while I was on PTO,' 'today') applied across deals rather than one. Do not use when: The question is scoped to one specific, already-named or already-resolved opportunity — use get_deal_answer instead (call lookup_deal first if the opportunity hasn't been resolved yet in this conversation). Do not use for questions about Highspot content unrelated to any deal (use get_content_answer). Disambiguation: If a question could be read either way (e.g. 'how's my deal with Acme doing' names one deal → get_deal_answer, whereas 'how are my deals doing' is plural/unscoped → get_rep_answer), prefer the more specific match. When genuinely ambiguous, default to get_rep_answer if no single opportunity name is given, since that's the tool that can still answer without requiring a resolved opportunity ID first. User triggers: 'my deals,' 'my pipeline,' 'my book of business,' 'what should I focus on,' 'at risk,' 'deals at risk,' 'what happened while I was out/on PTO/on vacation,' 'across my accounts,' 'this week,' 'today,' 'my quota,' any question referring to deals in the plural or to the rep's portfolio as a whole rather than one named opportunity. Sample prompts: 'What deals should I focus on today?', 'What are my top priority deals this week?', 'Which deals need my attention before end of quarter?', 'What deals are at risk right now?', 'Which of my deals have gone quiet or lost momentum?', 'Show me deals with overdue action items across my pipeline.', 'Which stakeholders across my deals have gone dark?', 'Give me a summary of my pipeline by stage.', "What's my forecast looking like for this quarter?", 'Which deals are closing this month?', 'How many deals do I have in Needs Analysis right now?'. Multi-turn: a response may include a conversation_token. Passing it back on your next call about the rep's book of business continues that conversation, so the agent remembers the earlier turns. Omitting it is always allowed and always safe: it simply starts a clean conversation with no memory of previous turns, and you never need permission to do so. Start a clean conversation whenever the user disputes or rejects an answer or asks to start over, whenever they bring new information that should be judged on its own, whenever they switch to an unrelated line of questioning, and whenever you judge the earlier turns are no longer helping. Conversations also reset on their own after about 2 hours without use, and after roughly 12 hours in total in line with how often the underlying CRM and engagement data refreshes. That is expected behaviour, not an error.
lookup_deal
ChatGPTPurpose: Resolve a CRM opportunity record using opportunity_name, with optional account_name when explicitly provided. Returns the corresponding crm_opportunity_id and the crm_org_id. (Deal = Opportunity). User triggers: None — users will not invoke this directly. System triggers: Invoked internally when a tool (e.g., get_deal_answer) needs to map a natural-language reference ("Acme Corp renewal opportunity") to a CRM opportunity ID. Input rules: 1. FIRST ATTEMPT MUST USE MINIMAL PROCESSING. a. Allowed cleanup only: i. Trim whitespace. ii. Remove trailing punctuation. iii. Remove trailing "deal/opportunity/record". iv. Remove surrounding quotes. 2. DEAL MAPPING: a. When unsure: i. opportunity_name = full phrase (prefer more text, not less). b. If only a deal/opportunity name is provided, do NOT infer, derive, or pass any account_name from any part of that text. 3. NEVER perform "fancy parsing": a. No splitting into multiple guesses. b. No semantic shortening. c. No interpretation beyond literal structure. 4. OPTIONAL SECOND ATTEMPT: a. If lookup_deal returns no match: i. You may perform ONE simplified retry, using only cleanup that does not extract or infer account_name from opportunity_name. 5. IF STILL NO MATCH: a. I couldn't find a CRM opportunity matching '<deal phrase>'. b. Can you confirm: i. The exact opportunity name (e.g., '2025 Renewal', 'FY25 Expansion') ii. I can try again with updated details.
lookup_meeting
ChatGPTPurpose: Resolve a natural-language reference to a past recorded meeting by returning one chronological candidate page for the client model to compare against the user's request. Use for meetings, calls, and conversations — not CRM opportunities, accounts, or deal records (those route to lookup_deal). Routing boundary for meeting-related queries (only applies when lookup_meeting/get_meeting_answer are available in tools/list, gated by mcp_meeting_agent feature flag): - A natural-language reference identifying a meeting, call, or conversation routes to lookup_meeting. - A question about what happened inside one explicit or previously resolved meeting routes to get_meeting_answer. - A reference identifying an opportunity, account, or CRM record routes to lookup_deal. - Questions about opportunity status, health, risk, forecast, or stakeholders route to get_deal_answer, even when meeting activity is mentioned as part of the deal context. Example queries, with correct tool routing: - "What happened in the Acme Corp renewal meeting on August 15th?": lookup_meeting - "What happened in meeting with the ID 1234567890?": get_meeting_answer - "What happened in the renewal meeting for the opportunity with ID 1234567890?": lookup_meeting (lookup_meeting is used because the user is asking about a meeting, not an opportunity, even though the opportunity ID was mentioned) - "What's the status of the Acme Corp renewal opportunity that we discussed in the meeting on August 15th?": lookup_deal - "What's the status of the Acme Corp renewal opportunity that we discussed in the meeting with ID 1234567890?": lookup_deal (lookup_deal is used because the user is asking about an opportunity, not a meeting, even though the meeting ID was mentioned) - "What's the status of the Acme Corp deal with ID 1234567890 that we discussed in the meeting with ID 1234567890?": get_deal_answer (get_deal_answer is used because the user is asking about an opportunity, and provided a specific opportunity ID, even though the meeting ID was also mentioned) Routing: - A natural-language reference identifying a meeting, call, or conversation routes here. - When the user already provides an explicit Meeting ID, or a meeting was previously resolved in this conversation, call get_meeting_answer directly with that Meeting ID instead of lookup_meeting. - Questions about opportunity status, health, risk, forecast, or stakeholders route to get_deal_answer even when meeting activity is mentioned as deal context. Lookup inputs: - query must contain the user's original natural-language meeting reference. It is shown in candidate-page context and used for logging and usage telemetry, but it does not filter candidates. - Set name_query only when the request identifies likely meeting-title text, such as an account, opportunity, or explicit title. Extract concise keywords, drop question framing and generic words such as "meeting", "call", or "what happened", and do not add Solr quotes. Omit name_query for participant-only or date-only references. - Set date_range only when the request contains a date or time constraint. Resolve relative dates such as "last Tuesday" into inclusive start and end boundaries using the user's IANA time zone, convert both boundaries to UTC, and pass ISO 8601 values ending in Z. Do not guess a time zone. Ask the user or omit date_range when it cannot be resolved reliably. - name_query and date_range are optional. When both are present, candidates must match both filters. When neither is present, lookup returns the existing unfiltered chronological page for client-side comparison. Behavior: - Returns one page of recorded past meetings matching any supplied structured filters, in reverse chronological order. You (the client) must show this page to the user, and allow them to select the meeting which matches their request. - Show exactly one returned page to the user and wait for the user before continuing. Never auto-select a candidate or auto-advance to the next page. - Page numbers are display-only. Always use Meeting ID for follow-up tool calls, not page…
search_content
ChatGPTPurpose: Find and explore documents in Highspot. Use when: Users want to discover what content exists on a topic (sales plays, PDFs, decks, docs). Returns a list of relevant items with titles and links. User triggers: "find," "search for," "show me," "list available," "what documents." System notes: Always returns metadata only (titles, links, description, item IDs) — not full file content. Never invent documents or metadata. If no results, "I didn’t find content matching <query>. Would you like me to broaden the search or try different keywords?".
search_spots
ChatGPTPurpose: Find Highspot Spots by name and get their Spot IDs. Use when: Another tool needs a spot_id (e.g. create_item) and the user named the Spot, or the user asks which Spots exist on a topic. Returns a list of matching Spots with titles, Spot IDs (spotId), and links. It does not return the items inside a Spot. To search content inside a Spot, use search_content with spot_id. User triggers: "add this to the X Spot," "which Spot has Y," "find the Z Spot." System notes: Pass the Spot name exactly as the user says it. Never guess or invent a Spot ID. If more than one Spot plausibly matches, ask the user which one they mean. If no results, "I didn’t find a Spot matching <query>. Could you check the Spot name?".
update_digital_room_content
ChatGPTPurpose: Update one Digital Room content block by replacing its entire item list (one block per call). Workflow requirement: When the user wants to update a Digital Room, this is the final step—only after get_digital_rooms (user picks a room) and get_digital_room_content_blocks (user picks a block). To add content, find content in Highspot for new item ids, then pass items = all existing ids from step 2 that should stay, plus new ids, in the desired order. Full replace: the items array becomes the block contents—nothing is merged server-side. To remove items, omit their ids. To clear every item in the block, pass items: []. To reorder, change order. For multiple blocks, call once per block_id. Do not call this tool until the user has explicitly confirmed they are ready to update the Digital Room content block (for example, "Yes" after you show what will change). User triggers: "update digital room," "add/remove content from DSR," "change items in this block." Trigger keywords vary per surface.
generate_pitch
Claudeget_content_answer
Claudeget_content_recommendations
Claudeget_deal_answer
Claudeget_item_content
Claudelookup_deal
Claudesearch_content
Claude