Can an AI agent use your website? A practical audit
Agentic readiness audit for the website: rendered content, semantic structure, forms, errors, and action confirmation.
Blog
Beyond “state of the art”: how do we test a programming agent
How we evaluate a coding agent beyond benchmarks: real tasks, regressions, review, and accepted results.
Agent-ready APIs: clear actions and reliable retries
APIs for AI agents: validation, authorization, idempotency, and handling retries without uncontrolled duplication of actions.
What's happening in production? Observability for applications and AI agents
Observability for applications and AI agents: logs, metrics, traces, useful alerts, and error diagnostics without data exposure.
One agent or a team of agents? How do we coordinate development without conflicts
One agent or more? Delegation, separate workspaces, handover of results, and code integration without overwrites.
The shared memory of AI agents: what we retain, who can read it, and when we forget
Agents Shared Memory explained in practice: context, provenance, access, concurrent updates, and information expiration.
IDE, terminal or cloud? How to choose development tools for AI agents
How to choose between an AI agent in the IDE, terminal, or cloud, evaluating execution, isolation, permissions, review, and integration into the team workflow.
How we prepare code for AI agents: context, rules, and test environments
Get the repository ready for AI agents: clear instructions, AGENTS.md, architectural context, test data, and reproducible checks.
Project management with AI agents: from goals to verifiable tasks
Project management with AI agents: objectives, tasks, dependencies, responsibilities, and evidence for deliverable acceptance.
Who holds the project keys? Identities and secrets for applications and agents
Identities for applications and agents, protected secrets, and temporary access: practical steps for a digital project’s infrastructure.
The 90-day adoption plan: from first pilot to a measurable agentic system
A practical six-step framework to assess, pilot, and operate an AI agent in a controlled manner, with KPIs, decision gates, governance, and stopping criteria.
How much is an AI agent worth: total cost, KPIs, and return on investment
Guide for SMEs: the total cost of an AI agent, six KPIs, real savings, and a sample ROI with three scenarios and investment payback.