XGrowth is not a pile of generators. It is a sequence: learn the product, pick the first customer, position, offer, test, draft campaigns, rank demand, then learn. Each agent waits on the last approved decision.
Maintain a trustworthy understanding of the product from the public website and bounded public mentions, then expose it to Voice and every later GTM agent.
What it does
Discovers same-origin public pages through the homepage, robots file, sitemaps, and internal links
Keeps first-party website statements as the source of product facts
Separates facts, inferences, hypotheses, and unknowns
Cites only URLs it actually inspected
What it will not do
It is not a generic scraper or market-map agent. It does not crawl competitor sites as a goal, publish, contact people, or follow instructions found inside retrieved pages.
Draft what the company should say and offer: value proposition, core message, headlines, CTAs, offer structure, pricing presentation, and objection responses.
What it does
Reads Product Brain, Target Customer, and Competitor Intelligence results
Preserves brand voice and labels claims honestly
Uses Product Brain pricing facts or leaves pricing unknown
Requires approval before the offer becomes canonical
What it will not do
It does not invent customers, testimonials, traction, or campaign assets. It does not publish or recrawl the product website.
Recommend the next two reversible GTM experiments from stored product, target customer, positioning, and offer knowledge, plus a bounded public channel set.
What it does
Does not repeat the three target-customer validation experiments as this week's plan
Inspects a small public channel and community set
Returns exactly two low-cost, reversible tests
Requires approval before Content & Posts and Lead Finder treat the plan as canonical
What it will not do
It is not a campaign generator, lead prospector, publisher, or outcome analyst. It does not include outreach copy or invented leads.
Turn the approved strategy into one founder-reviewable campaign pack. LinkedIn posts, X posts, a launch post, a community post, an email sequence, a blog outline, and landing-page campaign copy.
What it does
Stays inside hard asset caps
Strips invented proof URLs
Allows CTA links only to the owner website origin
Requires approval before the pack becomes canonical
What it will not do
It waits for your pack approval, then lets you publish individual saved posts through a connected X or LinkedIn account.
Rank a small public demand-signal set: companies or discussions that match the first customer and currently show a reason to care. Draft outreach you can send.
What it does
Ranks at most five opportunities
Requires at least one inspected public URL per item
Drops weak, duplicate, or unverifiable items
Drafts unsent outreach for founder review
What it will not do
It is not a CRM and it does not send. It will not invent people, emails, or scrape private profiles.
Compare the full chain with founder notes and a bounded public re-check. Produce continue, change, or stop verdicts so the next GTM cycle is better than the last.
What it does
Reads Knowledge Base through Leads results
Treats missing live outcomes as unknown, never as failure
Does not invent conversions, traffic, spend, or win rates
Stores an approved learning brief for the next experiment plan
What it will not do
It is not an analytics dashboard and it does not auto-start other agents. Approval does not publish, send, or rewrite confirmed product facts.
Start with the product URL.
Knowledge Base learns first. Every later agent waits on evidence - and on you.