leadbay_build_campaign

WHAT LEADBAY SHOULD REMEMBER

You keep your own memory of how this user likes to work — tone, naming, formatting, what they ask you to skip. Leadbay does not store that and does not need to.

What Leadbay does need is anything that changes who it should find. When the user states targeting criteria in conversation ("I target fleets over 100 vehicles", "carriers are a bad fit unless they do last-mile delivery", "climate engineering is also my market"), call leadbay_refine_prompt so it changes what Leadbay surfaces for the whole org and on every future refresh — not just this conversation. When they say a specific lead is wrong for them, record the dislike rather than noting it.

Build me a Leadbay campaign from scratch<if the user supplied this argument, render the short parenthetical or inline clause derived from it; otherwise empty. Source: Optional: a name for the campaign. Omit and one is derived from the lens/audience + date (or the backend AI-names it).> — a cohort of <the user-supplied value if any; otherwise a sensible default. Source: Optional: how many fully-actionable leads to build (default 20). The loop keeps discovering, qualifying and enriching until this many in-ICP leads each have a reachable target-title contact — or the lens is exhausted. Higher counts take longer and consume more quota.> fully-actionable leads: each in-ICP, high ai_agent_lead_score, AND with a reachable buyer contact. <if the user supplied this argument, render the short block derived from it; otherwise empty. Source: Optional: a fresh audience to target (e.g. 'dental clinics in Texas'). Omit to build from your ACTIVE lens — the default.> <if the user supplied this argument, render the short block derived from it; otherwise empty. Source: Optional: the exact buyer job titles to enrich, comma-separated (e.g. 'VP Sales, Head of Growth, Director of Business Development'). Omit and the buyer persona is derived from what you sell. A lead only counts toward the target when it has a reachable contact matching one of these titles.>

Run this end-to-end, autonomously, without pausing. Do NOT stop to confirm the audience, do NOT stop to confirm the enrichment spend, do NOT ask me to pick, and do NOT stop to hand off — just keep discovering, qualifying, enriching, and swapping until the cohort holds <the count_or_default (as extracted above)> leads that each meet EVERY requirement (in-ICP, high ai_agent_lead_score, and a reachable target-title contact whose email/phone actually landed). The ONLY reasons to stop short: the lens genuinely can't supply that many buyer-ready in-ICP leads, or enrichment quota is exhausted (a backend 429). In those cases, finish with whatever you locked and tell me plainly how many you got and why it stopped. Enrichment consumes quota, not credits — never pre-refuse on a credit balance.

GATE — DEFER TO TOOL RENDERING. When you call a Leadbay composite that ships its own RENDERING block (every composite in 0.9.0+ does), render the response using that block's recipe verbatim — score bars, glyph palette, column order, hide-list, link priorities, all of it. Do NOT substitute prose, a numbered list, or a different column structure even when an orchestrating prompt's body suggests alternate framing. Prompt-specific commentary (motivational nudges, summaries, next-action recommendations) belongs ABOVE or BELOW the canonical table, never in place of it.

If the prompt's body and the tool's RENDERING appear to conflict, the tool's RENDERING wins for the structural layout; the prompt's voice wins for the commentary that surrounds it.