2026/Free online book · Field Manuals
Agents That Actually Work
The narrow band where autonomy earns its keep
Access
Free
Chapters
12
Read time
140 min
Alpesh Nakrani
VP of Growth at ViitorCloud · former CTO & COO
Agent demos are intoxicating and agent production is sobering. The truth is there is a real, narrow band of tasks where an agent beats a script and a human both. This manual is about locating that band for your domain, instrumenting it, and resisting the pressure to widen it before the evidence does.
Between the demo and the disappointment is a thin set of tasks where agents are genuinely better. How to find it and stay inside it.
This edition is free to read onsite. Each chapter has its own URL, so readers can bookmark, share, and return to the exact section they need.
Table of contents
INTIntroduction: The Demo That LiedAn agent that aced the demo broke production because one tool had side effects, one response was ambiguous, and nobody could find where the plan changed.8 min01What an Agent Is and Is NotMost systems people call agents are scripts, workflows, or copilots in costume, and the mislabel is where the cost comes from.10 min02The Autonomy LadderSix rungs from script to autonomous agent, with promotion criteria so you climb on evidence instead of enthusiasm.10 min03The BOUND TestFive gates that decide whether a task deserves an agent at all, applied before a single line of orchestration code.10 min04Bounded Goals and Task ContractsTurning a fuzzy objective into a machine-checkable contract with success conditions, scope boundaries, and a stopping rule.10 min05Tools, Permissions, and Side EffectsThe Tool Trust Contract: the seven properties every tool must declare before an agent is allowed to call it.10 min06State, Memory, and Context ControlAn agent's reliability is bounded by what it can see, what it remembers, and what it carries between steps, all of which you must control deliberately.10 min07Planning Without WanderingThe agent loop is where autonomy lives and where it runs away, so it needs budgets, convergence checks, and a forced landing.10 min08Evaluating Agent RunsTask success is the metric everyone reports and the one that hides the most, so an agent eval measures the path, not just the destination.10 min09Human Handoffs and ApprovalsApproval gates earn their keep only when they intercept the right actions, give the human enough to decide, and do not become a rubber stamp.10 min10Observability and ReplayIf you cannot reconstruct exactly what the agent saw, decided, and did at every step, you do not have an agent in production, you have a liability you cannot debug.10 min11Security Boundaries for Tool-Using SystemsAn agent processes instructions and untrusted data in the same channel, so its tools become an attacker's tools unless you draw the boundaries deliberately.12 min12Incidents, Kill Switches, and RollbackEvery agent fails eventually, so the question that decides your worst day is whether you can stop it, unwind it, and learn from it.11 minENDConclusion: The Most Accountable Agent WinsThe best agents are not the most autonomous; they are the most accountable, and the BOUND Checklist is how you ship one.9 min