farstic/ai-servicenow-architect / .claude/skills/now-assist-genai
now-assist-genai
VerifiedUse when asking what Now Assist and the generative-AI layer can do — the Now Assist skill catalogue, AI Skill Kit, Now LLM Service, Generative AI Controller, AI Agents, AI Control Tower. Reference knowledge only; the builder is now-assist-specialist.
| File | Kind | Size |
|---|---|---|
| EXAMPLES.md | markdown | 2.5 KB |
| SKILL.md | skill md | 8.1 KB |
EXAMPLES.md
View on GitHub# Now Assist / GenAI (Reference) v1.0 — Worked Examples
This is a *reference* skill, so its examples are grounded Q&A — not buildable designs. The moment a question turns into "design/build it," hand off to the **Now Assist Specialist**.
---
## Example 1 — "Can Now Assist summarise CSM cases, and what powers it?"
**Answer.** Yes. Case/incident **summarization** is an out-of-box Now Assist skill, enabled and tuned in the AI Admin Hub console *(citation: markdown/intelligent-experiences/configure-a-now-assist-skill.md)*. It runs on the model provider selected for the skill — the **Now LLM Service** (a ServiceNow hosted model) or a supported third-party LLM; developers use the **Generative AI Controller** with your own third-party LLM licenses. *(citation: markdown/intelligent-experiences/edit-model-providers.md, markdown/intelligent-experiences/servicenow-large-language-model-now-llm/now-llm-model-updates.md, markdown/intelligent-experiences/exploring-now-assist-platform.md)*
**Release note.** Confirm the specific summarization skill is GA in your engagement's release family before committing to it.
**Hand-off.** If you want this *designed* — when it fires (resolution vs on-open), what the prompt includes, low-confidence routing — that's a **Now Assist Specialist** task.
---
## Example 2 — "How do we govern which AI features are on, and can we use our own LLM?"
**Answer.** **AI Control Tower** is the governance surface — discover, monitor, manage, and audit AI features (ServiceNow and third-party) across the instance. Third-party model routing (**bring-your-own-LLM**) is configured through that governance layer rather than by each feature calling a model directly. *(citation: markdown/intelligent-experiences/ai-control-tower/ai-control-tower-landing.md, markdown/intelligent-experiences/ai-control-tower/configure-third-party-llms-using-ai-control-tower.md)*
**§1.1 note (for the builder).** Enabling OOB skills and configuring Control Tower is configuration. A **custom** skill (AI Skill Kit) over baseline tables is configuration too; **new tables/scopes/Connection Aliases** behind a custom skill or agent are §1.1 — flag for the Now Assist Specialist + Chief Architect.
---
## Reading these examples
- Reference answers are **grounded in a cited doc** and **flag release-sensitivity** — Now Assist moves fast.
- Anything that becomes "design it / build it" is handed to the **Now Assist Specialist**; this skill stops at reference.
---
*End of Now Assist / GenAI reference EXAMPLES.md v1.0.*
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |