Reliable AI Agents: Guardrails, Evals, and the Deterministic Core — Engineering Trust. Red-teaming, invariants, injection defense, observability, assurance case, built around a real credit age

Prijzen vanaf
11,99

Gesponsorde links

VERGELIJK ALLE AANBIEDERS (2)

Beschrijving

Bol Your agent works in the demo. Now make it safe enough to put money - and a regulator - behind.When a wrong answer is an awkward email, "usually works" is fine. When it is money that does not come back, a limit breached, a regulator's question, "usually works" is a liability with good demos. This book engineers the difference. Its running system is Harbor Credit - an agent that extends trade credit to a small business's wholesale buyers - and across ten chapters it wraps that agent in the full assurance pipeline that turns an impressive prototype into a system you can certify.Through ten chapters, each moving from a reproduced failure to tested code, you will build: - A red-team harness and a six-type failure taxonomy - because agent failures are systematic, not bad luck - Evals that report quality and safety as separate numbers, with a calibrated LLM-judge and a golden set as executable spec - Input and output guardrails - deterministic, fail-safe rails at the boundary, the model free in the middle - The deterministic core: business invariants in plain Python that have the last word over whatever the model proposes - Business invariants elicited from catastrophe, sorted from preferences, and pinned to acceptance cases - A threat model and the strongest security an agent can have - safe by construction, where even an obeyed injection cannot breach a limit - Observability with byte-for-byte trajectory replay - you debug trajectories, not lines - Graceful degradation - timeouts, circuit breakers, and a safe mode that never auto-approves - Property-based and adversarial testing that certifies distributions, not single cases - The assurance case - the auditable, evidenced argument, with disclosed residual risk, that the agent is safe to deploy The governing idea, held for ten chapters: put the LLM at the boundary and the invariants in the core, so safety holds regardless of model quality - perfect, degraded, or jailbroken. Each chapter adds a research lineage (FMEA and fault trees to reference monitors, QuickCheck to the safety case), a failure catalog, and exercises. The companion repo has one dependency, thirty-three tests, and runs entirely offline.Who it's for: senior engineers, and anyone deploying agents in high-stakes or regulated domains, who have built and dissected an agent (Books 2-3 or equivalent). The AI Agent Series takes readers from first contact to professional mastery across seven volumes. This is Book 5: trust, engineered.

Vergelijk aanbieders (2)

Gesponsorde links · Sommige shops betalen ons een vergoeding

Sorteren op:

€ 11,99 Gratis verzending

€ 13,50 € 2,99 verzendkosten Totaal € 16,49

Beschrijving (1)

Your agent works in the demo. Now make it safe enough to put money - and a regulator - behind.When a wrong answer is an awkward email, "usually works" is fine. When it is money that does not come back, a limit breached, a regulator's question, "usually works" is a liability with good demos. This book engineers the difference. Its running system is Harbor Credit - an agent that extends trade credit to a small business's wholesale buyers - and across ten chapters it wraps that agent in the full assurance pipeline that turns an impressive prototype into a system you can certify.Through ten chapters, each moving from a reproduced failure to tested code, you will build: - A red-team harness and a six-type failure taxonomy - because agent failures are systematic, not bad luck - Evals that report quality and safety as separate numbers, with a calibrated LLM-judge and a golden set as executable spec - Input and output guardrails - deterministic, fail-safe rails at the boundary, the model free in the middle - The deterministic core: business invariants in plain Python that have the last word over whatever the model proposes - Business invariants elicited from catastrophe, sorted from preferences, and pinned to acceptance cases - A threat model and the strongest security an agent can have - safe by construction, where even an obeyed injection cannot breach a limit - Observability with byte-for-byte trajectory replay - you debug trajectories, not lines - Graceful degradation - timeouts, circuit breakers, and a safe mode that never auto-approves - Property-based and adversarial testing that certifies distributions, not single cases - The assurance case - the auditable, evidenced argument, with disclosed residual risk, that the agent is safe to deploy The governing idea, held for ten chapters: put the LLM at the boundary and the invariants in the core, so safety holds regardless of model quality - perfect, degraded, or jailbroken. Each chapter adds a research lineage (FMEA and fault trees to reference monitors, QuickCheck to the safety case), a failure catalog, and exercises. The companion repo has one dependency, thirty-three tests, and runs entirely offline.Who it's for: senior engineers, and anyone deploying agents in high-stakes or regulated domains, who have built and dissected an agent (Books 2-3 or equivalent). The AI Agent Series takes readers from first contact to professional mastery across seven volumes. This is Book 5: trust, engineered.


Productspecificaties

Merk Independently Published
EAN
  • 9798171349462
Maat


Prijshistorie

* Prijshistorie bevat geen data van Amazon.

Prijzen voor het laatst bijgewerkt op:

Uitgelichte Keuze
11,99
Naar shop