Why Salesforce Agents Fail — A Systems Breakdown
A systems breakdown of Salesforce agents: system-prompt load, context saturation, role confusion and the architecture needed for more deliberate workflows.
Lynn Cole / Writing
Writing
Essays, thoughts, and technical notes.
MCP: usability, abstraction, and scaling costs
My critique of MCP’s abstraction, security and scaling costs, and why some of its use cases remind me of FastAPI.
Boarding the AI hype train: a satire
A satirical ride on the AI hype train, featuring pivot tables, six hundred hello-world nodes and an automatic water-bottle MCP.
An early Codex workflow evaluation
An early Codex workflow evaluation finds useful planning and implementation alongside task-list friction, isolated workers and Git conflicts.
What a task-completion paper actually tested
A task-completion paper pushes models until they fail. The more revealing part is how confidently people read their own agendas into the result.
Documentation debt is still infrastructure debt
Documentation debt is still infrastructure debt. AI makes the habit easier, and information silos remain an expensive way to look busy.
Radio echoes of a civilization
What if distant listeners were more interested in our phone traffic, angry emails and love letters than our broadcasts? Radio carries an intimate echo of civilization.
Do not make your product less useful
Don't ever do anything to intentionally make your product less useful, especially when there are open source implementations of the same concept or competing products in the same space.
Prompt augmentation versus deliberate context design
Deliberate context design means separating user intent, memory, tools and instructions rather than packing them into a noisy prompt.
When the value moves upstream from the code
When code becomes cheap to replace, more of the value and responsibility moves into requirements, planning and validation.
Please, thank you, and the shape of an interaction
Please and thank you shape an interaction. I see politeness as a way to reinforce a productive trajectory rather than flatter a machine.
Cleaner signals before larger models
Clean data, explicit structure and useful scaffolding matter before larger models. Better weights are not a substitute for a legible task.