Softlander blog perspectives published in July 2026.
Protocols make tools and agents interoperable, but they also standardise discovery, delegation and context exchange. Those interfaces need explicit trust and policy controls.
A convincing message can conceal a failed or unauthorised operation. Agent evaluation must inspect tool calls, external state and control decisions.
A credible AI success story separates what was delivered from what changed, defines the baseline, shows the contribution chain and preserves uncertainty and permission.
Keep sensitive data under client control by moving approved methods and people to the environment, exporting only the minimum reviewed evidence needed for collaboration.
The question that sequences a post-quantum programme is not which algorithm to adopt. It is which of your data, recorded by an adversary today, would still matter when it can be decrypted.
An orchestrator should be judged by the workflow it controls: decomposition, routing, state, authority, recovery, verification and stopping—not by a polished final response.
Effective oversight gives a prepared person the signal, authority, time and interface needed to prevent or limit a defined AI failure.
Run evaluations often, but interrupt people only when a signal maps to user consequence, a decision owner and a tested response.
Review an MCP server as a privileged protocol adapter: verify tool semantics, OAuth boundaries, token audience, downstream delegation, input handling, isolation, logging and consent.
Most threat models are produced once, filed, and never consulted again. A model earns its place when every ranked attack path is attached to an architectural decision someone has to make.
KEEP EXPLORING
Read the method, assumptions and questions to ask.