01 · You approve the plan first.
Builds run in phases with checkpoints, so you see what will change before anything is written.
Phyllis builds the real records on your instance — tables, fields, business rules, client scripts, UI actions, flows, ACLs, catalog items. The whole change lands in scoped update sets, every field diff-verified, staged for your approval. Nothing ships unattended.
Build the warranty claim flow with approval over $5k.@ for records · / for commands
Phyllis builds the change on your instance — real records and config, scoped update sets, every field diff-verified and staged for your approval before anything ships.
Phyllis doesn't hand you a code sample to paste. She creates the actual tables, fields, business rules, client scripts, UI actions, flows, ACLs and catalog items on your instance — named, linked, and working against your real schema.
After every write, Phyllis reads the record back and diffs it against what she sent — no silently dropped fields, no fields that ServiceNow lied about saving. The whole change stays staged in scoped update sets until you approve it. Nothing ships unattended.
Every artefact is built to your standards. Phyllis follows your naming conventions, target scope and estimation rules — and stages ATF tests alongside the change — so what lands reads like your best engineer wrote it, not a bot.
Builds run in phases with checkpoints, so you see what will change before anything is written.
Real records, in the right scope and update set, following your team’s conventions.
After each write Phyllis reads the record back and checks it matches what she meant to change.
Configuration and code across the platform — each artefact built in your instance, in your update set.
sys_db_objectsys_scriptsys_script_includesys_hub_flowsys_security_aclsc_cat_itemsp_widgetWorkspacesMobileDashboardsNow Assistsys_atf_testCatalog item previews run the real rules before anything is built — conditional fields appear, mandatory flags toggle, prices recalculate and order guides step through.
Phyllis builds real records and config on your instance — scoped update sets, every field diff-verified against what ServiceNow actually saved, staged for your approval.
Catalog items with variables, UI policies, client scripts, and fulfillment — built end-to-end from a sentence.
Read the use caseFlow Designer flows, business rules, AI agents, notifications — automation built, tested, and approval-gated.
Read the use casePhyllis builds and extends your entire employee-and-agent experience — any portal page, workspace or brand theme — grounded in your live instance and staged for your approval.
Read the use caseYes. Your conventions are part of every build — prefixes, scopes and patterns — and she reuses what already exists instead of duplicating it.
Into an update set in your instance, in the right application scope, staged for your approval. Nothing is promoted without you.
Every write is read back and checked, builds pause at checkpoints, and an Instance Scan runs after every build. You review before anything moves.
Yes. Per instance, owners and admins can make it read-only, block tables or switch off tools — enforced on every request.
One teammate from the first question to a promoted, tested change.
Phyllis grounds herself in the full context of your ServiceNow instance — its tables, ACLs, flows, update sets, configurations, and dependencies. Every answer is evidence-backed and traceable to the records it came from.
Explore AnalyzeSay “I want to implement ITSM” and Phyllis returns sequenced stories with priorities, points, and acceptance criteria — synced both ways with Jira or ServiceNow Agile 2.0.
Explore PlanBatch and release update sets through chat — in the right order, with conflicts surfaced before you promote.
Explore Deploy
