Same SDLC. Half the hours.
32 specialist agents. Two human sign-offs. 600 developer hours — now 290.
GeneWorks is a coordinated team of 32 specialist AI agents that runs ServiceNow delivery as a continuous loop — Requirement → Design → Task Planner → Execute → SN Deploy → Verify. Two human sign-offs are non-negotiable: nothing builds without design sign-off, nothing ships without verification sign-off.
ServiceNow implementations are slow, expensive, and brittle.
Every enterprise running ServiceNow faces the same three walls. GeneWorks eliminates all three.
Every change needs a specialist
Adding an SLA, writing a business rule — each requires a certified developer, a ticket, a review cycle, and days of lead time.
⟶ avg. 3–5 days per small config change
No one knows what will break
ServiceNow platforms accumulate thousands of interdependencies. A change to one field cascades into SLAs, notifications, and integrations — invisibly.
⟶ "it worked in dev" is a $250K incident
Institutional knowledge walks out
The architect who designed the routing logic left two years ago. No one knows why the business rule fires twice. Every new hire starts from zero.
⟶ unrecorded knowledge = compounding risk
Requirement. Design. Build. Deploy. Verify. Repeat.
Six stages. Two human sign-offs. Thirty-two specialist agents in between — the same SDLC your CAB and your auditor expect, run in a continuous loop.
Requirement
Agent turns input into a versioned spec.
Design
Design agent drafts it; your architect signs off.
Task Planner
Planner breaks the design into ordered tasks.
Execute
Main agent builds Fluent code in waves.
SN Deploy
Non-destructive, fully reversible install.
Verify
ATF + functional tests; you sign off.
Out of 100 stories, GeneWorks completed 73. Here's a clean handoff for the remaining 27.
No theater. No "AI did everything." When ACLs, API limits, or judgment calls stop us, we say so — and we hand you a runbook for the rest. The two human sign-offs exist exactly because some work belongs to humans.
Week 1 looks good. Month 6 looks unrecognizable.
The longer the agents run on your instance, the more your idioms, ACL patterns, and integration map land in the workspace. By month six, the agents read like the team.
| Phase | Window | Effort reduction | What's happening |
|---|---|---|---|
| Cold start | Week 1–4 | 25–35% | Agents learn the instance, team idioms, infrastructure map. |
| Context maturing | Month 2–3 | 40–50% | Failure log and design pattern library accumulate in workspace. |
| Compounding gains | Month 4–6 | 55–70% | Agents propose like the team. Reviewer flags drop. |
| Steady state | Month 6+ | ~65% | Plateau. The remaining work is genuinely hard. |
The longer GeneWorks runs, the harder it is to replace.
Every build adds context to the workspace. Every Impact Analysis populates causal dependencies. Over months, GeneWorks accumulates a unique, instance-specific intelligence that no other vendor, no consultant, and no off-the-shelf tool can replicate.
GeneWorks builds the platform. Moveworks serves the people using it.
They don't compete — they complete each other. One for builders, one for users.
GeneWorks
Architects, codes, tests, and deploys — from business rule to packaged Update Set.
Moveworks
Answers questions, routes requests, and handles self-service across every system.
How they work together
P1 SLA breach in production
Moveworks detects the breach, alerts the on-call engineer in Slack, creates the major incident, routes the approval. GeneWorks updates the SLA definition and breach escalation logic — blueprinting, running impact analysis, and deploying a tested Update Set.
500 employees joining
Moveworks handles each new employee's day-one experience across Slack and Teams. GeneWorks built the onboarding catalog items, approval workflows, and fulfillment flows that Moveworks triggers — and maintains them as rules change.
Engineering wants CAB automation
GeneWorks designs and deploys the full CAB workflow — risk scoring, approval routing, bypass logic, audit trail — tested with ATF. Moveworks surfaces CAB approvals to managers in Slack and handles follow-up.
Why not just use what already exists?
There are several ways teams try to solve the ServiceNow delivery problem. None of them compound. GeneWorks does.
vs SI Consultants — faster, cheaper, and it doesn't go on holiday
A certified consultant costs $250–400/hr with a 3–5 day turnaround per config change. GeneWorks delivers the same artifact — blueprint, code, ATF tests, packaged Update Set — in minutes. Every session makes it smarter about your instance; every consultant rotation loses institutional knowledge.
vs ServiceNow Now Assist — we build platforms; Now Assist answers questions
Now Assist summarises tickets, drafts responses, and finds knowledge articles. It doesn't build business rules, configure SLAs, write ATF tests, or deploy Update Sets. GeneWorks operates one layer below — the platform engineering layer Now Assist sits on top of.
vs Generic AI Coding Assistants — context is everything; generic AI has none of yours
Generic tools generate code in isolation. They don't know your ACLs, business rules, SLA structure, or what breaks when you change a field. GeneWorks carries a permanent workspace memory of your platform. Paste-and-pray is not a deployment strategy.
vs Moveworks — different job, different buyer, perfect pairing
Moveworks is an employee self-service assistant. It interacts with ServiceNow as a data system — it doesn't build or configure the platform. GeneWorks builds the platform Moveworks runs on. Designed to coexist: one for users, one for builders.
The GeneWorks investor deck.
Eight slides — the problem, solution, product, moat, market, model, traction, and the ask. Use the arrows or your keyboard (← →); press the ⤢ button to present fullscreen.
Self-contained HTML deck — open it anywhere, present from any browser, no software required.
Durable, instance-specific knowledge.
GeneWorks gives its agents durable knowledge — through an extensive training corpus, a database layer with embeddings, a self-healing loop, and a permanent workspace that never forgets.
Trained across the entire ServiceNow knowledge surface — product docs, upgrade & release notes, product fixes & known errors, YouTube transcripts, community notes, partner-portal methodologies, support docs, and GeneWorks delivery IP. Designs and code follow real ServiceNow practice, not generic guesses.
A database layer encodes the training corpus, your uploaded documents, and prior work as vector embeddings. At query time the agents retrieve the most relevant knowledge by semantic similarity — by meaning, not exact keywords. Retrieval runs within your environment.
When a build or test fails on a known pattern, the agents repair and re-run it automatically — the one-click Fix ATF / Fix FT in Verify. Every mistake is written to a lessons-learned file the agents read before acting, so context is never lost between sprints.
Agent topology, pipeline, impact analysis, execution & security.
Section 01 — Agent Topology
Master-worker architecture. Gene is the orchestrator; all domain work is delegated to specialist agents.
- Gene — Master Agent: Receives all user requests. Classifies intent, routes to the right specialist, synthesizes results, manages the shared MASTER_STATE. Active locks prevent concurrent conflicting builds on the same resource.
- Specialist Agents — Domain Workers: ITSM, ITOM, Platform Admin, and Integration agents each carry 5 skills — Architect, Functional, Coder, ATF-Tester, Selenium-Tester. Each skill has its own SKILL.md defining persona, tools, and output format.
Section 02 — SDLC Pipeline
- Design: Parses natural language into a plain-English design document. No code yet.
- Blueprint: Full H1–H8 impact analysis. Maps affected tables, fields, dependent rules. Produces a structured blueprint JSON. Risk level assigned: low / medium / high.
- Stories (✋): Breaks the blueprint into atomic engineering stories. User reviews and approves before build. Medium/high risk also requires explicit sign-off on risk level.
- Build: Each story executed via REST API against your instance. Artifacts created natively — no file generation. Scoped to a named Update Set opened at build start.
- UAT: ATF suite written and executed via the ATF Runner API. Each story gets at least one test. Failures surface to Gene for retry.
- Complete: Update Set closed. Delivery summary produced. Dependencies recorded. Lessons-learned updated. Build archived to gw_events.
Section 03 — Impact Analysis Engine
Eight impact categories. Every change is triaged for blast radius before a single line is written.
Each H-section is scored Green (safe), Yellow (caution), or Red (stop, human review required). The combined score determines the overall risk level. After every build, H-section results are recorded in the workspace.
Section 04 — Native Execution
- REST Native: Every artifact is created by calling the ServiceNow Table API directly. No file generation, no XML imports. It's in your instance immediately.
- Named Update Sets: Every build opens a named Update Set at start, closes at end. You preview and commit to production. GeneWorks never touches production directly.
- ATF Integration: Gene uses the ATF Runner API on your instance to write and execute test suites. Each story gets at least one test. Tests are stored in ServiceNow — you own them.
Section 05 — Security Model
- Credentials stay local: stored only on the client machine, never sent to any external service. Direct, authenticated REST call.
- Security fence on every message: injected server-side into every agent context before the model sees it; not modifiable at runtime.
- Blocked command patterns: mass deletes, production table truncation, credential modification — pattern-blocked at the execution layer.
- Lower instances only: dev, PDI, UAT. Production changes only after you commit the Update Set through standard promotion.
- All changes reversible: scoped to a named Update Set — review, roll back, or delete through standard ServiceNow tooling.
Setup takes under 20 minutes.
Three things. No infrastructure. No install. Just connect your ServiceNow dev instance and tell Gene what to build.
A ServiceNow dev or PDI instance
Not production. A developer or personal developer instance is perfect.
Admin credentials for that instance
Needed to create artifacts and run ATF tests. Never stored externally.
One sentence on what to build first
That's the entire requirement. Gene asks clarifying questions if needed.
What runs on your instance
Four things. All reversible. Nothing permanent without your approval.
A small REST API helper
Enables automated test execution. Can be deleted anytime — a standard ServiceNow Scripted REST API.
Background scripts during builds
Scoped to your active Update Set. Visible and auditable through standard ServiceNow tooling.
Read-only audit syncs
We read your platform history to build the memory graph. No writes during sync. Your data stays on your infrastructure.
ATF tests
Gene writes and runs its own tests, stored natively in ServiceNow. You own them. They stay on your instance indefinitely.
Time to first delivery
| When | Milestone | What happens |
|---|---|---|
| Day 0 | Connect | <20 min. Gene reads your platform. Submit your first request. |
| Day 1 | First Delivery | First Update Set ready for review. Real artifacts in your instance. |
| Wk 1 | Memory Graph | 1,000+ audit records indexed into the embeddings store. |
| Mo 1 | Deep Knowledge | Gene knows your instance better than most of your team. |
What Gene can build on day one
Three rules. Non-negotiable.
Lower instances only
Dev, PDI, UAT — never production. Enforced at the execution layer, not just policy.
Everything in Update Sets
You commit to production. We never do. The Update Set is yours to preview, approve, and promote.
Full control always
Pause, review, or roll back anything, anytime. No persistent state you don't control.
GeneWorks in the field. Real problems. Real deployments.
Three representative scenarios showing how GeneWorks transforms ServiceNow delivery across different organisation types.
Greenfield ITSM Implementation in 6 Days
The Situation
A consulting team had 30 days to stand up a full ITSM environment for a government agency. Prior estimate: 6 weeks with two developers. Using GeneWorks, they ran the ITSM Wizard end-to-end across all 8 phases.
What GeneWorks Did
Created P1–P4 SLA definitions with breach notifications · Built 14 catalog items with approval workflows · Bulk-imported 240 users across 9 assignment groups · Wrote and executed 38 ATF tests — all passed · Produced full TDD documentation for every artifact.
Outcome
6-week scope delivered in 6 days. Every artifact documented, tested, and packaged in named Update Sets. The team reviewed and committed to production — GeneWorks never touched production.
Legacy Platform Modernisation — No Developer Queue
The Situation
A mature platform had 3 years of technical debt. Their sole internal ServiceNow developer left, leaving a 60-item backlog. The team needed to modernise incident routing, rebuild broken SLAs, and reconfigure their Service Catalog — without hiring or engaging an SI.
What GeneWorks Did
Indexed the entire platform — identified 12 conflicting business rules · Rebuilt SLA definitions with correct breach logic · Cleared the 60-item backlog across 3 months — 47 tasks completed · Every change impact-analysed — 0 production incidents.
Outcome
3 years of technical debt cleared in 3 months without a new hire. GeneWorks now runs continuously as the team's permanent platform engineering capacity.
First ServiceNow Deployment — Senior Architect on Demand
The Situation
A company scaling past 600 employees had just purchased ServiceNow but had no certified internal developers and couldn't justify a multi-month SI engagement. They needed a working ITSM environment within their IT team's capacity.
What GeneWorks Did
Connected to PDI in 20 minutes — first build same day · Gene acted as senior architect, explaining tradeoffs · Full ITSM environment live within 2 weeks · IT team learned ServiceNow patterns through the process — no black box.
Outcome
Full working ITSM environment delivered in 2 weeks at a fraction of SI cost. No certified developer needed. The team now runs GeneWorks as their continuous platform engineering layer.