Agentic interfaces: Rob says MCP was synonymous with this a few months ago, but these days substantial doubt that will be future of the field. Some teams are CLI first, some are MCP first, some are both.
AGENTS
-
LLMs Can Grade Every Sales Call for Instant Feedback
By
–
Analysis: Many SaaS capture routine events in people’s workflows. You can potentially have LLMs give ~instant feedback on execution quality of those with less friction and more consistency than traditional human management would ever be able to do. e.g. Grade every sales call.
-
AI Converts Handwritten Notes Into Assisted Living Placement Forms
By
–
For brokers placing seniors in assisted living, rather than a web form framework, made the capability to let user take notes on paper and then AI crunches that into results of a web form.
-
Suggest Prompts to Users Instead of Blank LLM Input Box
By
–
Given you know domain better than customers rather than giving blank text box for interaction with LLM over deterministic domain model, give suggestions of what they could ask for.
-
Top Six In-Product AI Usage Patterns From Chat to Agentic
By
–
In-product usage #1: "Chat" / conversational interface
#2: Generation
#3: Categorization
#4: Ingestion
#5: Analysis
#6: Agentic interfaces (MCP / CLI) -
Chat Interface Overused as AI Integration Model Says Expert
By
–
Chat interface has overinfluenced builders. Just because it is traditional and relatively easy to spec out doesn't mean it is the ideal way to integrate into existing/wider software suite.
-
LangSmith Deployments: Moving AI Agents to Production
By
–
Building agents locally does not mean they’re ready to deploy in production LangSmith deployments helps with that
-
Async Subagents: Non-blocking Event Loop Architecture
By
–
Big release here! Async subagents will become more and more of a thing, as subagents get longer running and you don’t want to block the event loop
-
Agent Term Overload: Automation vs. ML Investment Requirements
By
–
The word "agent" is the most overloaded term in AI right now. Your backlog probably has 5-10 agent ideas. But one agent idea is a 6-week automation you can build with n8n. Another is a 6-month bet requiring a dedicated ML team. Putting them on the same spreadsheet and hoping
-
Custom Auth for Per-User Data Isolation in AI Deployment
By
–
One deployment, isolated data per user. Add custom auth so every user gets their own scoped threads, runs, and conversation history — with per-user data isolation and role-based access using any auth provider. Full walkthrough: https://
youtu.be/DkNqgCz8cjE Docs: