Tag
26 articles connected to this technical signal.
A production runbook for comparing a candidate agent with the active runtime on the same requests without duplicating actions, then deciding promotion, canary or rollback.
Read articleA production runbook for attributing token and tool-call growth, isolating amplification, enforcing an execution budget, and validating or rolling back an AI agent release.
Read articleA production runbook for defining latency budgets, idempotency, retries, circuit breakers, traces and rollback for an MCP tool called by an AI agent.
Read articleA production runbook for qualifying structured AI agent tool output with schema, sources, diff, idempotence, policy, traces, human validation and rollback before writing to production.
Read articleA production runbook for qualifying AI agent permission drift with the real identity, RBAC, tool scopes, traces, expected denials, human validation and rollback before widening access.
Read articleA production runbook for qualifying the handoff from a Microsoft Foundry agent to Azure Automation, AWX, Azure DevOps or an MCP tool with contract, identity, traces, dry run, human validation and rollback.
Read articleA production runbook for qualifying MCP server drift with tool manifests, schemas, identity, secrets, network path, traces, evaluations, validation and rollback before reauthorizing an AI agent.
Read articleA production runbook for qualifying an internal MCP server with tool inventory, scopes, identities, secrets, audit, dry runs, evaluations, human validation and rollback before agent access.
Read articleA production runbook for qualifying a failed AI agent tool call with trace evidence, idempotence, identity, backend state, approvals, validation and rollback before retrying.
Read articleA production runbook for qualifying AI agent memory with sources, traces, aging, permissions, evaluations, guardrails, human validation and rollback before it influences real actions.
Read articleA production runbook for qualifying an AI agent evaluation set with business cases, retrieval, tool calls, traces, thresholds, human validation and rollback before promotion.
Read articleA production runbook for qualifying Microsoft Foundry agent guardrails with sources, refusals, tools, identity, traces, canary, human validation and rollback before user exposure.
Read articleA production runbook for qualifying suspected prompt injection in an AI agent retrieval corpus with sources, traces, evaluation, tools, guardrails, validation and rollback.
Read articleA production runbook for qualifying an agent approval policy change with action scope, identity, traces, evaluation cases, guardrails, human validation and rollback.
Read articleA production runbook for qualifying Azure OpenAI or Microsoft Foundry throttling with quota, deployment capacity, agent traces, retries, fallback, validation and rollback before changing models.
Read articleA production runbook for rotating or revoking an AI agent runtime identity with scoped permissions, dry-run tool calls, traces, approvals, validation and rollback before breaking production actions.
Read articleA production runbook for qualifying a new AI agent tool with contract review, scoped identity, dry run, traces, approvals, evaluation cases and rollback before enabling real actions.
Read articleA production runbook for qualifying a retrieval index update with source diff, metadata, chunking, evaluations, traces, human validation and rollback before changing an AI agent's answers.
Read articleA production runbook for qualifying incomplete AI agent traces with conversation events, sources, tool calls, identities, approvals, evaluations and rollback before restoring an action.
Read articleA production runbook for exposing Azure DevOps to an AI agent through MCP with project scope, permissions, allowed actions, evidence, logs, human validation and rollback.
Read articleA production runbook for qualifying AI agent contract drift with prompts, tool manifests, sources, evaluations, traces, human validation and rollback.
Read articleA short query to isolate write-capable tool calls, their execution identity and correlation before disabling an AI agent.
Read articleA production runbook for qualifying an AI agent action with traces, sources, tools, identity, KQL, human validation and rollback without disabling the whole assistant.
Read articleA runbook for validating an AI agent before real action by separating sources, tools, identity, evaluation cases, human approvals, logs and rollback.
Read articleA production runbook for exposing MCP tools to an AI agent while keeping action scope, approvals, identities, logs, evaluation and rollback under control.
Read articleA production runbook for qualifying an AI agent that selects the wrong tool, acts without evidence or hides an action behind a plausible answer.
Read article