Engineering notes
Every article starts with a practical question, explains the necessary terminology, and links to primary sources. We separate external evidence, project experience, and conclusions — and state what cannot be inferred from them.
Action-taking agents need governed identities. This article defines agent identity, examines Microsoft Entra Agent ID and the MCP authorization model, and lays out least privilege at the tool boundary, delegation-aware audit trails, and shadow-agent discovery — including what each control does not solve and which control planes we expect next.
A technician asked what happens if two cleaning agents are mixed and the safety filter refused, which is the one question the safety data sheet exists to answer. Kumar et al. show guardrails trade false positives against false negatives with no free option. What we measure on both sides, why a refusal is a defect with a ticket, and where we accept over-blocking deliberately.
A planner, a researcher, a writer, a critic and a supervisor produced plausible plans and wrong results that nobody could attribute to a component. Cemri et al. build a taxonomy of why multi-agent systems fail, and most of the categories are coordination rather than capability. What we replaced with ordinary code, the two places a second agent still earns its place, and why the diagram is so persuasive.
GPT-5 turns the model picker into a real-time router that chooses between a fast path and a reasoning path per request. We examine how the router decides, why the API keeps explicit controls, what launch week revealed about predictability, and how evaluation practice must change when the product is a portfolio behind one name.
A JSON manifest lets declarative agents specialize Microsoft 365 Copilot through instructions, knowledge, and OpenAPI actions — running entirely on Microsoft's orchestrator with no hosting of your own. We examine the schema as of August 2025, governance in the admin center, the metering economics, and the concrete cases where pro-code custom engine agents remain the better choice.
Models are better at knowing what they do not know when the subject is widely documented. Ni et al. connect that self-assessment to how popular the knowledge is, which has an uncomfortable consequence for specialists: the assistant is least able to flag its own uncertainty precisely where a customer's expertise lives. What follows for architecture, and the demonstration trap it explains.
The 2025 retrieval default combines BM25 and dense vectors with reciprocal rank fusion, then reorders them with a cross-encoder reranker. We cover the measured lifts from Anthropic and Cohere, a realistic latency budget, three production rerankers, and the query classes this baseline still cannot answer.
A customer wanted an assistant to modernise a fifteen-year-old codebase, and we spent the first six weeks writing tests. Translating code is the part models are good at; knowing whether the translation preserved behaviour is the part that decides whether the project ships. What we test first, why we migrate leaves before trunks, and the change we refused to let an assistant make.
Ask in German, get a number from the ERP: the demonstration is irresistible and the production version looks nothing like it. We expose curated views rather than tables, because a correct query over the wrong table is the failure that has no error message. What we forbid outright, why every answer shows the query, and the number that was right and still wrong.
Google donated the Agent2Agent (A2A) protocol to the Linux Foundation. AWS, Cisco, Google, Microsoft, Salesforce, SAP, and ServiceNow are founding participants. We examine what the protocol specifies, what it deliberately leaves out, and why neutral governance is the precondition for agent interoperability across organizational boundaries.
Agent journeys ultimately reach systems you cannot test at volume: payment providers, ERP backends, partner APIs. We apply service virtualization to agents — simulated counterparts implementing the real contract, holding state, injecting faults — and argue that every simulated result must carry an explicit label. With verified data from τ-bench, τ²-bench, and Microcks 1.12.0.
On 12 and 13 June 2025, Cognition and Anthropic published apparently opposite advice on multi-agent LLM systems. We compare 'Don't Build Multi-Agents' with Anthropic's research-system post — a 90.2 percent lift at roughly 15x token cost — and derive a decision rule: parallelize decomposable breadth, keep shared-context work single-threaded.