*

Author: danstarns

.trunk/trunk.yaml

@@ -17,10 +17,11 @@ runtimes:
     - [email protected]
 
 lint:
+  disabled:
+    - vale
   enabled:
     - [email protected]
     - [email protected]
-    - [email protected]
     - [email protected]
     - [email protected]
     - git-diff-check

threads.mdx

@@ -6,7 +6,7 @@ description:
   deploy to production-ready code"
 ---
 
-**Threads is where ideas become agents.** It's a conversational interface that
+**Threads is where ideas become agents.** it's a conversational interface that
 lets you build, train, and refine AI agents through natural language—no coding
 required. When you're ready, deploy your agent as production-ready code.
 
@@ -28,7 +28,7 @@ Most AI agent development follows a painful pattern:
 **Threads eliminates this translation loss.** Domain experts work directly with
 agents, training them through conversation, seeing immediate results, and
 iterating in real-time. When ready, **eject to code** exports your trained agent
-as a complete Modus application.
+as a complete Modus app.
 
 ```text
 Traditional: Idea → Requirements → Code → Deploy → Test → Repeat
@@ -67,7 +67,7 @@ Everything you build in Threads can be **exported as real software**:
 - Your agent's personality and instructions
 - The tools it has access to
 - Its conversation patterns and responses
-- Complete Modus applications through **eject to code**
+- Complete Modus apps through **eject to code**
 
 ## Connections
 
@@ -89,7 +89,7 @@ tools:
 - **Notion** for documentation and knowledge management
 - **Exa** for enhanced web search capabilities
 
-### Model Context Protocol (MCP) support
+### Model context protocol support
 
 Hypermode fully supports the **Model Context Protocol**, an open standard for
 secure, structured tool integration. Your agents can connect to any
@@ -101,7 +101,7 @@ internal tools.
 Through **Pipedream Connect**, your agents gain instant access to over **2000
 pre-built integrations** across the software ecosystem. This includes:
 
-- CRM platforms like Salesforce and HubSpot
+- Customer relationship management platforms like Salesforce and HubSpot
 - Marketing tools like Mailchimp and Google Analytics
 - Communication platforms such as Discord and Microsoft Teams
 - E-commerce solutions like Shopify and Stripe
@@ -247,14 +247,14 @@ instruction.
 detection to ticket creation, saving hours of manual work while ensuring nothing
 falls through the cracks.
 
-## Eject to Code: From Conversation to Deployable Software
+## Eject to code: from conversation to deployable software
 
 Your Code Review Agent works perfectly in Threads—automatically hosted and
 maintained. But if you want to hand it off to your development team or integrate
 it into larger systems, **eject to code** lets you export everything you built
-through natural language as a complete Modus application.
+through natural language as a complete Modus app.
 
-### From Threads to Modus Code
+### From threads to Modus code
 
 Remember your Code Review Agent that analyzes pull requests and creates Linear
 tickets? Here's what that conversation becomes when exported:
@@ -301,9 +301,9 @@ func ReviewPullRequest(agentId string, prData string) (string, error) {
 }
 ```
 
-### The Power of Eject to Code
+### The power of eject to code
 
-#### **From Conversation to Real Software**
+#### **From conversation to real software**
 
 **What you built in Threads:**
 
@@ -318,9 +318,9 @@ func ReviewPullRequest(agentId string, prData string) (string, error) {
 - Tool integrations (GitHub, Linear) configured and functional
 - GraphQL API ready for deployment
 
-#### **Built on Open Source Modus**
+#### **Built on open source Modus**
 
-Your exported agent runs on **Modus**, Hypermode's open-source agent runtime:
+Your exported agent runs on **Modus**, Hypermode's open source agent runtime:
 
 ```bash
 # Your agent becomes a standard Modus app
@@ -337,7 +337,7 @@ modus deploy   # Production deployment
 - **Standard DevOps**: CI/CD, testing, monitoring work normally
 - **Full transparency**: Complete visibility into agent behavior
 
-#### **Enterprise-Grade Architecture**
+#### **Enterprise-grade architecture**
 
 The exported code isn't a prototype—it's enterprise-grade software:
 
@@ -347,25 +347,25 @@ The exported code isn't a prototype—it's enterprise-grade software:
 - **Observability**: Built-in logging, tracing, and debugging
 - **Security**: Tool access scoped to agent roles
 
-#### **Developer-Friendly Handoff**
+#### **Developer-friendly handoff**
 
 Platform teams get real software they can audit and extend while preserving all
 the natural language training from Threads.
 
-### Ready to Build Sophisticated Agents?
+### Ready to build sophisticated agents?
 
-**This is just the beginning.** The pseudo-code above shows the concept, but
-Modus provides a complete framework for building sophisticated, stateful agents
-that scale.
+**This is just the beginning.** The pseudo-code shown here demonstrates the
+concept, but Modus provides a complete framework for building sophisticated,
+stateful agents that scale.
 
 **Your agent works perfectly in Threads.** For many use cases, keeping your
 agent hosted automatically in Threads is ideal—it handles deployment, scaling,
 and maintenance for you.
 
 **Ready for more control?** If you're looking to hand off to other engineers,
 integrate with existing systems, or build coordinated multi-agent workflows, you
-can eject to code and get a complete Modus application that your development
-team can own, extend, and deploy anywhere.
+can eject to code and get a complete Modus app that your development team can
+own, extend, and deploy anywhere.
 
 **Learn more about building agents with Modus:** For complete documentation on
 agent development, tool integration, and deployment, visit our
@@ -431,7 +431,7 @@ Agent: *Agent is now deployed and ready for your sales team to use*
 - **Deal prioritization** based on your criteria for pipeline review
 - **Follow-up suggestions** with draft messages for outreach
 
-**Business impact**: A marketing agency reduced pipeline review time from 2
+**Business impact**: a marketing agency reduced pipeline review time from 2
 hours to 15 minutes and improved follow-up consistency with their agent's
 pipeline analysis.
 
@@ -481,14 +481,14 @@ Agent: *Agent is now deployed and ready for your support team to use*
 
 **Current capabilities**:
 
-- **Email analysis** for inbox review and categorization
+- **email analysis** for inbox review and categorization
 - **Ticket prioritization** based on your criteria for support queue analysis
 - **Response drafting** for common issues and customer communication
 - **Escalation identification** for issues that need team attention
 - **Customer sentiment analysis** to check satisfaction levels
 - **Knowledge base suggestions** for relevant help articles
 
-**Business impact**: A SaaS company reduced support triage time from 2 hours to
+**Business impact**: a SaaS company reduced support triage time from 2 hours to
 20 minutes with their agent's daily support request analysis and categorization.
 
 ### Marketing insights agent
@@ -545,11 +545,11 @@ Agent: *Agent is now deployed and ready for your team to use for marketing analy
 - **Optimization recommendations** based on data analysis for campaign
   improvements
 - **Audience segmentation analysis** to understand engagement patterns
-- **ROI calculations** to measure campaign effectiveness
+- **Return on investment calculations** to measure campaign effectiveness
 
-**Business impact**: An e-commerce brand improved campaign ROI by 60% and
-reduced campaign analysis time from 4 hours to 30 minutes with their agent's
-weekly performance reviews.
+**Business impact**: an e-commerce brand improved campaign return on investment
+by 60% and reduced campaign analysis time from 4 hours to 30 minutes with their
+agent's weekly performance reviews.
 
 ## Advanced patterns
 
@@ -598,7 +598,8 @@ Agent: "I'll update my review criteria to include performance analysis
 
 Threads works with **multiple models** through Hypermode's Model Router:
 
-- **GPT-4.1**: Latest OpenAI model for complex reasoning and code analysis
+- **Generative Pre-trained Transformer 4.1**: Latest OpenAI model for complex
+  reasoning and code analysis
 - **Claude 4**: Anthropic's advanced model for writing and analysis tasks
 - **Gemini**: Google's model for multi-modal tasks and data processing
 - **O1/O3**: OpenAI's reasoning models for complex problem-solving