Permission-aware assistance
Career recordAgent-assisted experiences that combine relevant context, bounded tools, deterministic controls, and human handoff.
Solution 03
Agentic User Experiences
Agents that understand users, use trusted tools, and take useful action.
- AI Agents
- MCP
- Identity
- Context
- Tool Calling
- Human Handoff
A capable model is not a product
A model that answers well is not yet something people can rely on. To act, an agent has to know who it is talking to, what that person is allowed to do, and when to stop. The hard part sits at those boundaries, not in the prompt.
Boundaries that make action safe
-
01
A known user, not an anonymous prompt
The experience establishes the user and applicable permissions before the agent can act.
-
02
Context is assembled, not hoped for
The model reasons over facts gathered deliberately rather than guessing at what it was never given.
-
03
Tools hold the sensitive parts
Typed tools perform bounded actions on the user's behalf while sensitive credentials and system access remain outside the model.
-
04
Determinism where models are unreliable
Validation and explicit failure handling cover the steps that must not vary, so uncertainty ends in a defined outcome.
-
05
A way out to a person
When permissions or confidence run out, the agent stops and hands the interaction to a person with the relevant context.
What has been built
Repository-aware automation
Personal projectA GitHub App that catalogs repositories and runs queued background work on a cloud-neutral compute boundary. In active development.
Context and control patterns
Career recordApproaches for assembling relevant context and using deterministic handling where model output requires validation.
Agentic workflows
Personal projectPackaged specification, review, and implementation workflows for agent runtimes — the practice used to build this site.