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.
@patio11
-
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.
-
SaaS Data Ingestion Challenges Solved by Modern AI Tools
By
–
Ingestion: Particularly at onboarding time, SaaS founders have an issue with "You possibly have data, perhaps dirty, fragmentary, or in almost purposely perverse formats. I would like to crush it into a defined database format." Ingestion has gotten much better because modern…
-
AI Categorization Models Replace Manual Tagging and Taxonomy Work
By
–
Categorization: We've had tag clouds and taxonomy for forever. Historically, lots of manual work pushed to user, to outsourced teams, or (for very large companies) custom-built models. Now categorization models are trivial, scale to the moon, and liberate people from this work.
-
AI-Assisted Generation Still Searching for High-Value Use Cases
By
–
Rob: AI-assisted generation is still in early stages. Saving someone 2 minutes isn't interesting. Saving someone a day is. We don't seem to have good patterns for where it is *actually* unlocking excess value yet, but many companies doing e.g. auto-generated notes on calls, etc.
-
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.
-
LLMs Simplify Search Interfaces Beyond Boolean Logic for All Users
By
–
Rob: Lay users (non-engineers) don't understand boolean logic like AND/OR. We once relied on complex composed interfaces to do filtering/search, and/or pseudo-syntax. LLMs can reinvent some interfaces to make them radically simpler and more effective for users. Everyone can text
-
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) -
eBay AI Falls Short on Structured Data Automation
By
–
Rob's example: eBay's AI integration will spin a paragraph of text for an item you're listing, like a boardgame, but won't do "Take a photo of the object; we'll fill in the 30 structured data form fields you need to successfully sell something on eBay."