Update Invent trigger management documentation (TSP-1322)

[claude]

Summary

• build/invent/invent.mdx: Added two new capability cards — "Enable or disable agent triggers" and "Enable or disable workforce auto-triggers" — to the "What you can do" section. Added an <Info> note about the bug fix where triggers created via Inventor now correctly display as "active".
• build/agents/build-your-agent/triggers.mdx: Added a "Managing triggers with Inventor" subsection under "Managing your triggers", noting this is an Enterprise-only conversational alternative to UI controls.
• build/workforces/build-an-ai-workforce/add-triggers.mdx: Added a "Managing workforce triggers with Inventor" subsection under "Pausing triggers" with a <Warning> callout that the workforce must be published before Inventor can manage its trigger states.

Relates to PR #15602.

Linear: https://linear.app/relevance/issue/TSP-1322/

🤖 Generated with Claude Code

[linear]

TSP-1322

[mintlify]

Preview deployment for your docs. Learn more about Mintlify Previews.

Project	Status	Preview	Updated (UTC)
relevanceai	🟢 Ready	View Preview	Jun 24, 2026, 2:29 AM

💡 Tip: Enable Workflows to automatically generate PRs for you.

[github-actions]

🎯 Vibe check

Reviewed: 3 files (2 with issues, 1 mostly clean)

Scores

	Dimension	Score	What's holding it back
🔴	Consistency	5/10	add-triggers.mdx has 10+ Title Case headings that should be sentence case. invent.mdx uses "Invent" instead of "Inventor" in one warning, and lowercases product terms ("agents, tools, workforces") in feature card descriptions.
🟡	Technical clarity	7/10	add-triggers.mdx uses full https://relevanceai.com/docs/... URLs in the testing FAQ instead of root-relative paths. triggers.mdx describes "visual status indicators" without specifying what they look like.
🟡	Non-technical clarity	7/10	invent.mdx includes a changelog-style <Info> ("now correctly display as 'active' immediately after creation") that will confuse readers who aren't tracking a bug fix.
🟡	Structure	7/10	invent.mdx ends abruptly after the MCP vs Inventor comparison without a closing CTA — this is a concept/overview page and needs one. triggers.mdx uses <Columns cols={2}> where the rest of the repo uses <CardGroup cols={2}>.

Score key: 🟢 9–10, 🟡 6–8, 🔴 1–5.

✨ Overall vibe: The new content itself is solid — the trigger pausing/resuming instructions are clear and well-structured, and the Inventor trigger management cards are a useful addition. The main drag is add-triggers.mdx, which hasn't had its headings converted to sentence case (the CLAUDE.md requirement), and uses absolute URLs for internal links. Fix those and the page is in good shape.

🔧 Issues (12)

build/invent/invent.mdx

• invent.mdx:21 — Card body: "Create new agents, tools, workforces, and triggers" → "Create new Agents, Tools, Workforces, and Triggers" (product terms; same fix needed at line 147)
• invent.mdx:33 — "restructure a workforce" → "restructure a Workforce"
• invent.mdx:44 — Card title: "Enable or disable agent triggers" → "Enable or disable Agent Triggers" (both are product terms; sentence case still requires product-name caps)
• invent.mdx:47–48 — Card title: "Enable or disable workforce auto-triggers" → "Enable or disable Workforce auto-triggers"; body: "The workforce must be published" → "The Workforce must be published"
• invent.mdx:52–54 — <Info> reads like a changelog note ("Triggers created via Inventor now correctly display as 'active' immediately after creation"). Docs describe how the product works, not what changed. Either rephrase as behavior ("Triggers created with Inventor display as active immediately") or remove entirely.
• invent.mdx:139 — "Invent is expensive to run" → "Inventor is expensive to run" (every other reference on the page uses "Inventor")

build/workforces/build-an-ai-workforce/add-triggers.mdx

• add-triggers.mdx:8,13,49,51,59,68,70,83,95,97,108,187,189,196,202,209 — Pervasive Title Case headings. All of these are wrong per CLAUDE.md sentence-case rule. Representative fixes:
  • ## Understanding Triggers → ## Understanding triggers
  • ## Adding Triggers to Your Workforce → ## Adding triggers to your Workforce
  • ### Adding Your First Trigger → ### Adding your first Trigger
  • ### Adding Additional Triggers → ### Adding additional triggers
  • ## Configuring Triggers → ## Configuring triggers
  • ### Manual Trigger Configuration → ### Manual Trigger configuration
  • ### Integration Trigger Configuration → ### Integration Trigger configuration
  • ### Recurring Schedule Trigger Configuration → ### Recurring Schedule Trigger configuration
  • #### Simple Schedule Options → #### Simple schedule options
  • #### Advanced: Cron Expressions → #### Advanced: cron expressions
  • ## Best Practices for Using Triggers → ## Best practices for using Triggers
  • ### Strategic Trigger Placement → ### Strategic Trigger placement
  • ### Trigger Maintenance → ### Trigger maintenance
  • ### Recurring Schedule Best Practices → ### Recurring schedule best practices
  • ### Security Considerations → ### Security considerations
• add-triggers.mdx:247,262,264,266 — Internal links use full https://relevanceai.com/docs/... URLs. Per CLAUDE.md, internal links must be root-relative (e.g., /build/workforces/workforce-features/workforce-task-view, /get-started/core-concepts/tools, /build/agents/build-your-agent/triggers)
• add-triggers.mdx:17,25 — "your agent" / "your agents" lowercase when referring to the Relevance AI product feature → "your Agent" / "your Agents"

build/agents/build-your-agent/triggers.mdx

• triggers.mdx:12–14 — Bullet list switches from "your Agent" (line 8, correct) to "your agent" (lowercase) mid-page. Fix: "Set your Agent to run…", "Configure your Agent to respond…", "Allow users to directly engage with the Agent…"

🧩 Component suggestions (2)

• triggers.mdx:90–95 — Uses <Columns cols={2}> to wrap <Card> components. The pattern used elsewhere in the repo (e.g., invent.mdx:19, invent.mdx:235) is <CardGroup cols={2}>. Verify whether <Columns> renders correctly in Mintlify, or switch to <CardGroup cols={2}> for consistency.
• invent.mdx:52–54 — The <Info> callout ("Triggers created via Inventor now correctly display as 'active' immediately after creation") is better handled as either plain prose in the relevant section or removed. If the fix matters to users, fold it into the card at line 44: "After creating a trigger with Inventor, it displays as active immediately."

🏗️ Page structure (2)

• build/invent/invent.mdx — No closing CTA. This is a concept/overview page; readers learn what Inventor is and what it can do, then hit a dead end after the MCP comparison. Add a ## What's next? or CTA card pointing to /build/agents/build-your-agent/triggers (to see what Inventor can manage) and /build/agents/create-an-agent (to start building with Inventor).
• build/invent/invent.mdx:172–173 — The Model selection tab says "Choose from the configurable list; there's a default if you don't change it." This doesn't give readers enough to act on. Either name the available models and the default, or link to wherever model options are documented.

⚠️ Contradictions (2)

• add-triggers.mdx:231 says timezone for scheduled runs can be adjusted "in your workforce settings"; the context page scheduled-triggers.mdx:156 says "in your agent's schedule settings." These are describing the same setting from different entry points — worth verifying which UI label is accurate and aligning both pages.
• triggers.mdx:54 mentions Inventor can manage individual agent trigger states with no prerequisites. add-triggers.mdx:183–185 has a <Warning> that "the Workforce must be published before Inventor can manage its trigger states." It's unclear whether agent triggers have a similar publish requirement. If they do, add a matching <Warning> to triggers.mdx. If they don't, note the distinction explicitly.

✅ Clean files (1)

build/agents/build-your-agent/triggers.mdx — Minor capitalization inconsistency in the opening bullets (noted above), but otherwise well-structured, no banned words, good use of components, and the new "Managing your triggers" section is clearly written with appropriate visual hierarchy.

🔋 Credit usage

Item	Count
Files reviewed	3
Context pages read	2
Total lines processed	~947

Files read: build/agents/build-your-agent/triggers.mdx (127 lines), build/invent/invent.mdx (251 lines), build/workforces/build-an-ai-workforce/add-triggers.mdx (273 lines), build/agents/build-your-agent/agent-triggers/scheduled-triggers.mdx (159 lines), build/workforces/build-an-ai-workforce/introduction-to-nodes.mdx (137 lines)