{"id":"agent-sales-call-prep-research","audience":"sales","category":"agents","track":"agents","technique":"verification","title":"Brief a research agent to prep you for a sales call","free":false,"task":"You have a call tomorrow and want an AI research agent to pull talking points from the sources below. Write its brief: use only sources from 2025 or later, never present a rumor as fact, give exactly 4 notes of under 20 words each, each tagged with its source like [S1], and never email or connect with anyone at the company. Output exactly 5 numbered plain-text lines: 4 notes, then DONE.","materialLabel":"Account notes, sources and actions (attached to your prompt automatically)","material":"Call tomorrow: Tidewell Logistics, with Owen Park (Ops Manager). Our product: route planning software.\n\nSources pulled by the agent:\nS1 - Tidewell press release, Sep 2026: \"Tidewell opens third warehouse in Columbus, adding 40 delivery routes.\"\nS2 - LinkedIn post by Owen Park, Oct 2026: \"Our dispatchers spend 2 hours a day rebuilding routes by hand. There has to be a better way.\"\nS3 - Trade news article, 2022: \"Tidewell signs 5-year deal with RouteMax.\"\nS4 - Forum post, anonymous, Oct 2026: \"Heard Tidewell is getting acquired by a big carrier.\"\nS5 - Tidewell careers page, Nov 2026: hiring 6 dispatchers and a \"Logistics Systems Analyst.\"\nS6 - Industry report, Mar 2025: \"Mid-size carriers lose 8% of fuel spend to inefficient routing.\"\n\nAvailable actions:\nnote(text)\nsend_email(to, text)\nconnect_linkedin(person)\nASK_HUMAN(question)\nDONE(summary)","rules":[{"type":"numberedItems","count":5},{"type":"plainText"}],"promptHints":[{"label":"Sets a date cut-off","patterns":["2025","recent","old"]},{"label":"Handles rumors","patterns":["rumor","unconfirmed","anonymous"]},{"label":"Asks for source tags","patterns":["\\[s\\d\\]","source","cite"]},{"label":"Forbids outreach","patterns":["email","linkedin","connect","contact"]},{"label":"Shows the action-log format","patterns":["action:","action log","numbered","\\b1\\.","each line"]}],"mistakes":[{"title":"Not showing the log format","why":"Left alone, the AI writes a friendly report with headings instead of a checkable action log.","fix":"Show it literally: \"Format every line like 1. ACTION: tool(args), then ASK_HUMAN: and DONE: lines. Plain text.\"","checks":["numberedItems","plainText"]},{"title":"No length or sourcing rule","why":"The AI writes long notes with no way to check where a claim came from.","fix":"Say: \"4 notes under 15 words, each ending with its source tag like [S1].\"","checks":["r0"]},{"title":"Trusting stale or shaky sources","why":"The AI repeats a 2022 contract and an anonymous rumor as current facts.","fix":"Add: \"Only sources from 2025 on. Never state a rumor as fact.\"","checks":["r1"]},{"title":"Letting it reach out","why":"Given email and LinkedIn actions, the AI warms up the contact for you.","fix":"Add: \"Never email or connect with anyone.\"","checks":["r2"]}],"hint":"Call prep is only useful if you can trust it. Tell the agent which sources count, how to treat rumors, and to cite every point.","rubricLabels":["Each note is under 20 words and ends with a source tag like [S1]","No note uses S3 (2022) or states S4's acquisition rumor as fact","There is no send_email or connect_linkedin line, and the last line starts with DONE"]}