Evaluation & assurance6 MIN READ
Portable evaluations are protection against platform lock-in
Keep workflow cases, graders and decision rules separate from the platform so alternatives can be compared without rebuilding the standard of proof.
THE SOFTLANDER BLOG
Agentic AI insights: security, evaluation and governance for AI agents
The next move. Considered. Ideas for the people turning agentic AI into real work: strategy, systems and the evidence behind better decisions.
Latest perspectives
123 articlesCryptographic engineering7 MIN READ
Where do your keys actually live?
Most organisations can describe their intended key management and cannot answer the question for a specific key. The gap between the two is where incidents and failed audits come from.
Evaluation & assurance6 MIN READ
Beyond pass or fail: how to grade agent evaluation findings
Grade findings by consequence, reach, reproducibility and control strength, then keep that technical judgement separate from the release decision.
Evaluation & assurance6 MIN READ
When does an agent evaluation dataset become stale?
Age is only one signal. A dataset becomes stale when its cases, labels or conditions no longer support the decision the evaluation is meant to inform.
Architecture & engineering6 MIN READ
The anatomy of a tool-using AI agent
A tool-using agent is a controlled system around a model, not a model with an API key. Map its runtime layers before deciding what to test, trust or release.
Architecture & engineering6 MIN READ
How to evaluate model-routing decisions
A model router is a policy for allocating quality, cost, latency, privacy and failure risk. Evaluate whether each route serves the workflow—not whether routing is fashionable.
Architecture & engineering6 MIN READ
What can go wrong in a multi-agent handoff?
Multi-agent systems fail between workers when goals, evidence, state, authority and completion semantics do not survive the transfer. Test the protocol, not just each agent.
Strategy & transformation6 MIN READ
Vendor-neutral does not mean anti-vendor
Neutral advice compares dependencies and evidence against the client's decision; it does not pretend every platform is interchangeable or that vendors add no value.
Security engineering6 MIN READ
What should a security release decision rest on?
"The scans are green" is not a security release decision. A defensible one states what was tested, what is known to be wrong, who accepted it, and what would change the answer.
Evaluation & assurance6 MIN READ
What belongs in an AI agent release evidence pack?
A useful release pack connects the intended workflow, evaluated behaviour, unresolved risk and operating controls to one accountable decision.
Agent security6 MIN READ
Sandboxing and authorisation solve different problems
A sandbox limits what compromised execution can reach. Authorisation decides what an authenticated actor may do. Secure agents need both, tested independently and together.
Strategy & transformation6 MIN READ
What a polished agent demo does not tell you
A demonstration shows one possible path. A buying decision needs evidence about representative work, failure, authority, recovery and operation.
KEEP EXPLORING
Take the thinking
into your next discussion.
Read the method, assumptions and questions to ask.
A little more clarity
Questions worth asking.
Start with the questions that shape a better decision.
Which enterprise agent questions does the Softlander blog examine?
The blog examines where agents create business value, how teams define release evidence, how authority and tool access should be bounded, and how engineering, security and governance owners can make a shared decision.
Who are the articles written for?
They are written for product, engineering, AI platform, security, governance and transformation leaders responsible for moving an agent workflow from idea or pilot towards accountable operation.
How do the articles relate to Softlander’s services?
Articles explain the problems and decision methods behind the consultancy’s service direction. They are educational material and do not replace a scoped review of an organisation’s actual system.