Starting RACE Programming from day one
No legacy constraints. No existing rituals. Build the RACE Programming system right: people only to complete one Pit Crew, then growth through the machinery.
Why greenfield is the best starting point
Greenfield and brownfield differ by the starting point. Here the project starts from nothing; brownfield starts with a lot already in place, including processes that do not fit the new reality. This guide lays out the path from this start and the options along it.
Greenfield is where RACE Programming's economics are strongest: no legacy constraints, no team rituals to unlearn, no brownfield coordination overhead. From day one the bottleneck is specification quality and Team Principal availability, not code volume.
What we see now on the project triangle: ~3× the scope, ~⅓ the cost, or 2-5× faster, worked out from two team shapes. Measured in the agent-to-agent data imports case, against our estimate for a team that already works with AI tools: the cost of production came to about a third, the same scope took 7.1 times less human effort, and end-to-end speed stayed about the same.
The failure mode in greenfield AI projects is scaling prematurely, adding engineers before the Pit Wall is proven, before the flow of Executable User Stories is stable, before Team Principal availability is locked. The six-stage model below prevents it.
The six scaling stages
Add people only to complete one Pit Crew: the Quality Engineer at the MVP, the Pit Crew Software Engineers as the backlog requires. Past that, the stages raise the share of the backlog the machinery clears. Each stage is a complete, functional delivery system, not a partial team waiting to be filled.
Start with the Pit Wall alone
The Pit Wall (Forward Deployed Engineer + AI Product, two roles, normally two people; one person carrying both is an exception) acts as both Pit Wall and Pit Crew. At this stage there is no Pit Crew and no separation between specification and execution yet; both arrive with the Quality Engineer at Stage 2. They take the client's problem apart, author EUS, build prototypes, set the frame of the solution and execute up to the MVP. Short engagements can run start to finish at this stage.
When to move on: the product reaches MVP and its happy path works → add the Pit Crew Quality Engineer first. Moving to alpha and beta testers needs a critical eye on quality that neither the Forward Deployed Engineer nor AI Product has.
Split roles, add crew
The Quality Engineer joins first. The Pit Crew Software Engineers follow as the backlog requires, forming the Pit Crew: Quality Engineer + 2 Pit Crew Software Engineers, working with the Silicon Software Engineer. At low throughput that roster is fractional (the Quality Engineer at 50%), never incomplete: the wall between specification and execution exists from the first Pit Crew. The Forward Deployed Engineer shifts to Pit Wall only and steps down to part-time oversight as the frame of the solution stabilizes.
When to move on: Still not enough throughput → do not add a second Pit Crew under the same Pit Wall. Raise the share of the backlog the machinery clears.
Raise the machinery's share
Machinery comes after the frame. The Forward Deployed Engineer decides when to start and how much to build; nobody has to build it before solving the client's problem and setting the frame.
The Forward Deployed Engineer owns the delivery machinery of the project: the swarm of agents, its integrations with every system the project uses, and the workflows, guardrails and pipelines that clear backlog correctly. The Pit Wall keeps tuning the project environment, the flow of requirements in and results out, and the machinery, so the engagement takes more of what the Team Principal pushes into the backlog.
The number to watch is the share of the backlog the machinery clears. The rest is cleared by hand: the Forward Deployed Engineer pulls it onto themselves, or passes it to the people in the Pit Crew. How far the machinery goes depends on model maturity and on how ready the project is.
Call in a RACE Engineer
If building the machinery absorbs the Forward Deployed Engineer → do not split the backlog into streams. Call in a RACE Engineer, part-time and on request, the way DevOps works today, to help raise the share of the backlog the machinery clears.
Genuinely separate products are separate engagements, each with its own Pit Wall and its own goals; one TPM can carry more than one, part-time on each. Splitting one backlog does not make a new engagement. See How RACE Scales.
People are added only to complete one Pit Crew. Past that, each stage raises the share of the backlog the machinery clears, not headcount.
Who you need, and when
Pit Wall (Stage 1 minimum)
- Forward Deployed Engineer (the engineer on the Pit Wall). Architecture decisions (ADR), feasibility of the prototypes the Pit Wall builds, Pit Wall execution oversight.
- Both directions, not just downward. The Pit Wall does not only turn intent into a spec. It brings 2 or 3 working prototype options to every decision, so the Team Principal chooses between things they can see, and it owns the Team Principal's review throughput, bringing automation and the agent into UAT so acceptance does not become the constraint. On a greenfield engagement this is what keeps the client from becoming the bottleneck in month two.
- AI Product. Gherkin acceptance tests (owned here; the Quality Engineer automates them), EPB management, EARS NFR, client communication.
- Silicon Software Engineer (the AI agent). Prototyping and spec authorship alongside the human roles. Not headcount: the AI teammate.
- Both human roles required. The norm is two people; one person covering both is possible as an exception.
- Qualification threshold: AI Fluency at senior level. Prototype build time ≤ 2 days. EUS acceptance rate > 80% first pass within 2 months.
Pit Crew (after the MVP, Quality Engineer first)
- Pit Crew Quality Engineer first, then 2 Pit Crew Software Engineers as the backlog requires, with the Silicon Software Engineer (the AI agent, not headcount).
- No standups; the retrospective is the one ceremony RACE kept. Stories flow on Kanban, each pulled when ready. Inner cycle 2×/day.
- Rule: do not add people inside a Pit Crew and do not add Pit Crews under the Pit Wall; raise the share of the backlog the machinery clears.
- Qualification: AI-native execution. All 4 DoD gates green before every Pit Stop, non-negotiable.
TPM (joins at the MVP)
- TPM (Technical Program Manager). Assigned by leadership at the MVP, when the Quality Engineer joins and the Pit Crew starts; usually part-time on a single greenfield team. Until then the Pit Wall holds the plan and the budget. From the MVP the TPM is accountable for the project goals within the project budget: the plan to the first release, the sponsor's and stakeholders' expectations around the Team Principal, the risk register and escalation.
- Understands RACE and puts it in place on the project: the staffing and sequence above, each person arriving when the work needs them, and a red flag raised early when the project needs something more. Leadership assigns the people.
- Does not decide what to build or how: the roadmap and the Executable User Stories stay with the Pit Wall and the Team Principal.
The first story
Team Principal: what you must lock in before the first story
- Availability SLA in writing. Team Principal responds to prototype review and UAT within 1 day. An engagement-level SLA, not a courtesy ask. Missing feedback blocks Pit Wall and compounds. The Pit Wall agrees it with the Team Principal and their sponsor at the start; from the MVP the TPM holds it.
- Feedback calibration. "I don't like it" is not feedback. Train Team Principal to answer: Is this what I meant? What business rule is missing? What would my user say? Calibrate on the first stories.
- No direct Pit Crew contact. If Team Principal bypasses Pit Wall and tasks Pit Crew directly, intervene immediately. First occurrence: address. Second: escalate as engagement risk; the TPM (before the MVP, the Pit Wall) logs it in the risk register and takes it up with the Team Principal.
Metrics from week one
See the Framework overview for full role and artifact specifications. If your team is migrating from Scrum, the From Scrum guide covers the transition mechanics in detail.