How GeneWorks Works

Requirement. Design. Build. Deploy. Verify.

Six stages. Two human sign-offs. Thirty-two specialist agents in between. A walkthrough of how a single ServiceNow story flows through the GeneWorks delivery loop — and why the loop never closes.

01The continuous loop

One story. Six stages. Two places where the work stops.

Every story — a catalog tweak, a business rule edit, a scoped app feature — runs through the same six stages: Requirement, Design, Task Planner, Execute, SN Deploy, Verify. The agents drive all of them. At two points, the loop pauses for a human: design sign-off before anything is built, and verification sign-off before it ships.

1
Agent

Requirement

Requirement Agent

You talk to the Requirement agent. It turns whatever you bring — a Jira story, a CSV from a workshop, a Visio swim-lane, or plain English — into a structured, versioned Functional Requirements Spec, and asks clarifying questions where the requirement is thin. Too ambiguous to specify? It bounces back with a structured list of what's missing.

InputStory brief, CSV, Visio, plain English
OutputVersioned requirements spec (PDF)
Typical timeMinutes
2
Sign-off

Design

Design Agent → your sign-off

The Design agent produces a full Solution Design — data model, dependencies, ACL implications, integration shape, and the exact ServiceNow Fluent artifacts to build. It reads from the workspace's accumulated context, so it matches your team's conventions. Then your architect reviews and signs off — nothing builds until this happens.

InputVersioned requirement
OutputApproved solution design + artifact list
ReviewerSenior architect / platform owner
3
Agent

Task Planner

Planner Agent

The Planner agent breaks the approved design into a granular, ordered implementation plan — every table, role, group, system property, ACL, business rule, and test as its own task. You can regenerate or adjust the plan before a single line is built.

InputApproved solution design
OutputOrdered build plan (e.g. 28 tasks)
Typical timeMinutes
4
Agent

Execute

Main Agent + Specialists

The Main agent builds the tasks in parallel waves, writing real ServiceNow Fluent code (React + TypeScript) you can read in the built-in IDE. ATF and functional tests are authored alongside the build — not after the fact. Each task is marked done or flagged, and every agent sees the others' work in the same workspace.

InputOrdered build plan
OutputWorking Fluent app + tests + docs
Typical timeMinutes to hours
5
Agent

SN Deploy

Deploy

GeneWorks installs the app into your instance as a safe, non-destructive update. Any changes made on the instance since your last deploy are merged in first, so your work never overwrites theirs. Every step is checkpointed — the whole deploy is fully reversible. GeneWorks never deploys straight to production.

InputBuilt Fluent app
OutputInstalled scoped app (reversible)
Typical timeMinutes
6
Sign-off

Verify

ATF + FT → your sign-off

GeneWorks runs ATF (server + client) plus live-browser functional tests against the deployed app — on our own test runner, so you never license ServiceNow's ATF cloud runner. Failures get one-click auto-fix where the pattern is known. Then your team signs off on the evidence. No theater: if 73 of 100 stories completed clean, it says exactly that — with a handoff for the rest.

InputDeployed app
OutputSigned-off evidence + CAB-ready package
ReviewerDelivery lead + CAB
02Why the sign-offs matter

Two checkpoints. Both human. Both non-negotiable.

The gates aren't ceremony. They're the contract. Every change record points to a named human who approved the design and a named human who approved the evidence. Audit trail by construction, not by reconstruction.

Sign-off 1 · Before build

Design sign-off

The agents have specified what they will build, why, and how it touches the rest of the instance. Now a human says yes or no. No code has been written yet. Reversing course here costs minutes — reversing it after build costs days.

What gets reviewed
  • Data model changes & ACL implications
  • Dependency map & blast-radius assessment
  • Integration boundary & auth flow
  • Test coverage plan (ATF + functional)
  • Explicit "what I'm assuming" list
Sign-off 2 · Before it ships

Verify sign-off

The app is deployed and verified — ATF plus live-browser functional tests, on our own runner (no ServiceNow ATF cloud-runner license). The agents produce an evidence package per story: what passed, what's flagged, what's blocked. A human signs off before anything goes to CAB. No story is "done" because an agent says so.

What gets reviewed
  • ATF (server + client) run results
  • Live-browser functional-test results
  • Before/after configuration diffs
  • Flagged items needing human follow-up
  • CAB-ready change package
03The agent roster

Thirty-two specialists. One coordinated team.

GeneWorks isn't one model wearing different hats. It's a roster of specialist agents — each scoped to a discipline, each with their own tooling, each with the prompts and patterns that produce reliable output for their artifact type. Gene is the orchestrator that routes work between them.

Group 1

Strategy & Design

5 agents
Functional ConsultantSolution ArchitectPlatform ArchitectProcess DesignerIntegration Lead
Group 2

Build

11 agents
ITSM SpecialistITOM SpecialistCSM SpecialistHRSD SpecialistSecOps SpecialistGRC AnalystServiceNow DeveloperScoped App EngineerFlow Designer SpecialistIntegrationHub EngineerService Portal Developer
Group 3

Quality

5 agents
ATF TesterSelenium TesterQA EngineerUAT AnalystPerformance Engineer
Group 4

Documentation & Compliance

5 agents
GenewriterGeneDocsCompliance AdvisorRelease ManagerChange Coordinator
Group 5

Operations & Knowledge

6 agents + Gene (orchestrator)
CMDB StewardKnowledge CuratorEvidence CollectorSelf-Healing AgentDependency MapperWorkspace CoordinatorGene · Orchestrator
04Why the loop gets faster

Week 1 looks good. Month 6 looks unrecognizable.

Cold-start automation is harder than mature automation. The first month, the agents are learning your instance — your idioms, your ACL patterns, your naming conventions, your integration map. By month three, the failure log and the design pattern library are doing real work. By month six, the agents read like the team.

PhaseWindowEffort reductionWhat's happening
Cold startWeek 1–425–35%Agents learn the instance, team idioms, infrastructure map.
Context maturingMonth 2–340–50%Failure log and design pattern library accumulate in workspace.
Compounding gainsMonth 4–655–70%Agents propose like the team. Reviewer flags drop.
Steady stateMonth 6+~65%Plateau. The remaining work is genuinely hard.

This is the future. The future is Now.