FiggBrain Deployed
you own the universe. put a team on it.
Seven agents running FiggCanopy inside your own Claude workspace. Point them at a thousand accounts and they screen, score, narrow to the ones worth pursuing, and plan them. They read and write your CRM, and they get sharper the longer they run.
it knows your company as well as it knows theirs.
That is the whole difference between this and running research one account at a time. The agents share two memories, so work compounds instead of restarting.
Your Company Brain
The seller model. What you sell, who you sell it to, which buying signals you hunt, and what you never say. Every agent reads it before it does anything, which is why the output sounds like you rather than like a generic tool.
An Account Brain
A living record of one target account, graded both on how complete the record is and on how winnable the deal actually looks, from L1 Cold up to L5 Wired. Feed it a call transcript and it extracts the signals, updates the fields, recomputes the scores, and logs what changed.
seven agents, one conversation.
You talk to the orchestrator in plain language. There is no dashboard to learn and no query syntax, and you never have to know which specialist you need.
Orchestrator
You talk to this one. It routes what you ask to whichever specialist should handle it.
Account owner
Holds the record for an account and decides when it has earned attention.
Prospecting manager
Works the universe down from everything to the accounts worth a look.
Scoring engine
Scores on stated criteria, and cites the signal behind every rationale.
Research
Pulls from public disclosures and earnings calls, and writes what it finds into the record.
Outreach
Drafts from the plan rather than from a template. It never sends.
Librarian
Keeps what the team knows, so the next run starts from it instead of from nothing.
and it refuses work, on purpose.
It drafts, you send. The system never contacts or emails anyone on its own, and it never will.
A draft that overreaches is held, not delivered. Every client-facing draft is compared against the data actually pulled for that account. If it asserts something your research does not support, you get told which sentence failed and which missing field would resolve it, rather than getting a confident sentence you cannot back up in the room.
Every score cites an external signal. Where something cannot be confirmed, it declines to score it and tells you exactly what is missing. It will not score any account at all until your Company Brain clears its readiness gate.
what is actually in the download.
One zip: the seven agents, the runtime templates, the connector packs, and the onboarding playbook it walks you through on first launch. Every customer downloads the same package. Your licence key personalises it after install, and your onboarding answers are what make the output yours.
Onboarding is four questions in plain sentences: who you sell to, who the buyer is, what tells you someone is in-market, and one thing you sell. That clears the gate and the system is usable immediately.
Connects to what you already use
The agents work through capability roles rather than named vendors, so you bind whichever tool you already use to each role: CRM, project management, comms, docs, email and enrichment. Ask for the outcome and the connector layer works out which product that means.
Anything you leave unbound falls back to local files, clearly labelled, so nothing fails silently. Binding your CRM writes FiggCanopy's fixed schema into it: 17 fields plus the pipeline stages.
Give it a company name and it returns a scored, evidence-backed intelligence package in roughly four to eight minutes.
agent packs.
Optional specialists on top of the core team, $100 a month each and none included in the base. Each pack carries its own 3 month minimum term, so we would rather you start on the base and add one once you know you want it.
Social Media
$100/mo
Pricing and Strategy
$100/mo
Sales Advisor
$100/mo
During beta a pack is hand-delivered by email rather than arriving with the download. We will be in touch to get yours set up.
FiggBrain Deployed installs into your own Claude workspace and runs there. During beta you need Claude Pro or above: Claude Code, the Claude desktop app, or claude.ai. It will not run on a free plan, and it is not a hosted service we run for you.
beta pricing, and you keep it.
These are beta rates and they will rise. Subscribe during beta and you keep your rate for as long as your subscription stays active.
Teams of 1 to 3
At launch$40/mo
Rising to $60.
Teams of 3 to 10
$250/mo
Rising to $1,000.
More than 10
Talk to us
We would rather size a plan correctly than watch you outgrow the Starter edition quietly.
The base subscription is month to month and the setup fee is waived during beta. Cancelling flips your licence inactive and starts a 90 day retention window on the activation record. Hands-on help beyond the basic service level is $150 an hour.
RevSpark AI never receives your customer data, CRM content, or connected tool data through FiggBrain Deployed. The agents run in your environment and your data stays there. We receive your signup information and a pseudonymous heartbeat that tells us an installation is active, and nothing else.
Questions? Email support@revsparkai.com
By subscribing, you agree to RevSpark AI's Terms of Service.
Already have a FiggCanopy account? View your account
just handed a list to work?
FiggBrain On-Demand runs a plan on an account you name, for about $20, with nothing recurring and nothing to install.