Pitch Box: The RFP Engine Built for Experiential Agencies That Are Done Starting From Scratch

Your Best BD People Are Spending Half Their Time on Retrieval, Not Strategy

Three RFPs land in the same week. Deadlines overlap. Somewhere around day two, the head of new business is not sharpening a point of view about the client's activation strategy. They are digging through a shared drive for the one case study that proves the agency has done this exact scale of program before, formatting it to fit a template nobody has updated since the last win, and hoping it still says what it said the last time someone opened it.

This is the actual failure mode behind declining win rates at experiential and creative agencies: not a shortage of talent, but a shortage of retrievable evidence. Pitch Box exists because that pattern repeats across bid seasons, at agencies of every size, regardless of how strong the underlying work is.

Founder Brian Morgan spent years on the subcontracting side of agency pursuits, delivering experiential programs before building Pitch Box, and watched the same bottleneck recur pursuit after pursuit: the proof already existed somewhere in the agency. Finding it, formatting it, and connecting it to the specific line in the RFP consumed the hours that should have gone into the argument itself. That observation, made inside live bids rather than inferred from market research, is the reason Pitch Box is built the way it is.

What Pursuit Spend Actually Looks Like When You Do the Arithmetic

Pursuit spend never shows up as a line item, which is exactly why it survives budget review unquestioned.

Here is the arithmetic. Take the blended annual cost of every senior BD and strategy salary that touches active pursuits. Estimate the share of their working hours consumed by pursuit work across a full bid season. Divide that number by the agency's average annual pursuit count. For a 50-to-150-person experiential agency running two to three senior people through 60 to 80 hours on a competitive bid, that per-pursuit figure typically lands between $18,000 and $38,000, embedded in salaries nobody thinks to attribute to new business.

Run the same math across a full year. An agency pursuing 12 to 18 contested RFPs annually is carrying $210,000 to $420,000 or more in pursuit spend that has never once appeared as a budget decision. It exists. It just hasn't been named.

Run this arithmetic against your own numbers before accepting any vendor's version of it, including this one. Win rate is an evidence problem before it's a writing problem, and evidence problems have a cost, whether or not anyone has calculated it yet.

The Blank-Page Problem Is an Architecture Problem, Not a Motivation Problem

Agencies that start every RFP from a blank document are not failing because the team lacks craft. They are operating without a system that compounds, which means every pursuit restarts the same retrieval process regardless of how many strong bids came before it.

Call it what it is: a knowledge problem, not a writing problem. The draft is easy once the right proof is in front of the writer. The hard part, the part that eats the hours, is finding that proof, confirming it is still accurate, and shaping it to answer the specific requirement in front of you.

Your best case studies are trapped in old decks and in people's heads. That's the real bottleneck, not the team's ability to write a compelling paragraph once the evidence is in hand. A library that only holds last year's greatest hits in an unsearchable folder is not a knowledge architecture. It is a filing habit that happens to be digital.

What Does Grounded Generation Actually Mean for an RFP Draft?

Grounded generation means every claim Pitch Box drafts traces back to a specific entry in the agency's own evidence library, never to a generative model's general training data. If the agency hasn't documented the proof, the system flags the gap instead of writing around it with plausible-sounding language. Nothing is invented. Everything is sourced.

Grounded generation is a drafting method where an AI system retrieves verified evidence before writing a single sentence, rather than generating language from pattern prediction alone. It works by tethering each generated claim to a specific source the agency has already validated, so accuracy compounds instead of decaying with paraphrase.

In practice, the process runs in five steps:

1. Ingest the incoming RFP and extract every requirement, evaluation criterion, and member of the buying committee.
2. Retrieve matching proof from the agency's own case-study library and self-building knowledge base.
3. Draft each section with claims traceable to that retrieved evidence, inventing nothing.
4. Run a Bid Qualifier go/no-go check so senior hours only go toward winnable pursuits.
5. Hand the sharpened draft to the pursuit team, who own the final version.

An AI that invents your proof points will lose you the pitch. Grounding isn't a feature; it's the whole game.

The Bid You Should Have Walked Away From: What a Go/No-Go Discipline Recovers

A loaded bid season creates a specific kind of pressure: more qualified RFPs arrive than the team has senior hours to work. Without a written qualification framework, the default is to pursue everything that clears a basic revenue threshold, which means a long-shot bid consumes a full senior cycle before anyone calls it.

The cost isn't only the hours spent on the bid that was never winnable. It's the hours that were unavailable for the pursuit the agency was actually positioned to win. Recovering even two marginal go/no-go calls a season back can return roughly 120 to 160 senior hours to the pipeline.

Pitch Box's Bid Qualifier applies that discipline before the proposal team is activated, not after three weeks of work already sunk into a bid that should have been declined in week one. Qualified RFPs get declined by default when the team is out of hours, not out of fit. A go/no-go call made early is a budget decision. Made late, it's a post-mortem.

Built by Someone Who Lived the RFP Grind From the Inside

Pitch Box comes out of Sandbox Group LLC, founded by Brian Morgan, a designer, coder, and operator with 15 years in brand experience and experiential marketing, with a background in fine arts from Penn State and building on the web since 2001. Before Pitch Box, Morgan spent years on the subcontracting side of experiential agency pursuits, delivering programs for enterprise clients, which put him inside the actual bid process rather than observing it from a market-research distance.

"The RFP grind is a capacity problem, not a talent problem. Your best people aren't slow; the evidence is scattered," said Brian Morgan, Founder of Sandbox Group LLC.

That observation, made across dozens of live pursuits, is the product thesis: the fix isn't a faster way to generate sentences. It's a system that keeps what an agency already proved, retrievable at the speed a pursuit actually moves.

Recovered Capacity Is a Budget Decision: Redirecting Pursuit Spend Toward Pursuits You Can Win

If pursuit spend at your agency is running $210,000 to $420,000 a year, and a meaningful share of that is retrieval, formatting, and bids that should have been declined in week one, the reallocation question is the actual pitch here, not a feature list.

For the managing partner, the question isn't what a pursuit engine costs. It's what the current architecture already costs, expressed in senior hours that never reached the pursuits the agency was built to win. For the stretched BD lead staring down three overlapping deadlines, the question is simpler: start from a sharp draft, or start from nothing, again.

Pitch Box connects into the tools your team already runs, including Google Drive, Box, Slack, HubSpot, Salesforce, Asana, and Canva, with a built-in workflow layer for task and reviewer management, and unlimited seats so bringing the right collaborator into a pursuit never becomes a licensing conversation. You don't need a faster blank page. You need your own wins, retrievable at pursuit speed.