Agentic vs. Deterministic System Design
The architectural choice, for AI-driven analysis/diagnostic tasks, between an agent that autonomously investigates and fetches its own data via tools (flexible, covers novel cases, harder to debug/operate) and a deterministic pipeline that pre-correlates signals into one fixed context before a single model call (repeatable, cheaper, cleanly evaluable, blind to unanticipated signals).
Also known as: deterministic (RCA) design, agent-based (RCA) design, deterministic pipeline
Part of: Agent Harness
How authors use it
Oldest first (extraction date when no publication date is known).
| Author | Their term | Their meaning |
|---|---|---|
| AI Root Cause Analysis Shifts from Model Reasoning to Context Engineering Mark Silvester · 2026-07-25 | deterministic (RCA) design | An architecture that correlates signals into findings up front and hands the model one fixed, prepared context with no agent loop -- as instantiated by Coroot and (per the article) Dynatrace's Davis AI. |
| AI Root Cause Analysis Shifts from Model Reasoning to Context Engineering Mark Silvester · 2026-07-25 | agent-based (RCA) design | An architecture that hands the model tools and lets it decide what telemetry to fetch as it reasons, i.e. an open-ended investigation loop. |
Documents (4)
- 12-Factor Agents: Patterns of reliable LLM applications — Dex Horthy, HumanLayer AI Engineer · 2026-10-08 Reader 🖥️
Reliable production LLM agents are built not by adopting an agentic framework that hides the hard parts, but by applying ordinary software-engineering discipline — owning your prompts, your control flow (the loop/switch-statement/context-window triad), and your execution/business state — to what is fundamentally a stateless-function (LLM) called inside a small, deterministic, developer-controlled loop. - Presentation: From Thousands to One: Building LLM-Powered Selection Systems Jendrik Jördening · 2026-08-17 source ↗ Reader 🖥️
When you need an LLM to select one item from among many database-backed options (an ID, a station, a record), you must strip the model down to only the irreducibly textual/semantic step it is actually good at — schema-restricted, range-bounded, and independently validated by a second model call — while pushing every deterministic operation (filtering, comparison, control flow) into ordinary code, recovering a classic model-view-controller separation that a single freeform LLM call destroys. - AI Root Cause Analysis Shifts from Model Reasoning to Context Engineering Mark Silvester · 2026-07-25 Reader 🖥️
The hard part of AI-assisted root cause analysis has shifted from model reasoning -- which recent evidence suggests is largely solved by frontier and even many open-weight models given the same prepared context -- to context engineering: the harness work of correlating signals and assembling a compact, unmisleading context before the model is ever called. - This coding agent doesn’t want your feedback — it ships without it Darryl K. Taft · 2026-06-01 source ↗ Reader 🖥️
AI coding tools have been optimizing the wrong variable — speed within a chat-based, human-reviewed iteration loop — when the real failure mode of AI-generated code is architectural (state management and concurrency); the fix is a closed-loop agent that internalizes review inside a deterministic, type-checking runtime and makes the developer's involvement in the loop optional rather than merely faster.
Open gaps (2)
- incompleteThe article never explains what happens when Skipper's internal fix loop exhausts its eight attempts without passing type checks — does it return the last broken candidate, surface an error to the developer, or fail silently? Without an answer, 'ships without your feedback' is a claim about the happy path only; the framing hides an unspecified failure mode at precisely the point where developer judgment would otherwise matter most.This coding agent doesn’t want your feedback — it ships without it — read next: A technical writeup, postmortem, or incident report on Skipper's real production failure behavior; more generally, material on retry-budget exhaustion and failure disclosure in agentic code-fix loops.
- incompleteRule 6 ('narrow down deterministically') assumes a pre-existing, well-structured backing dataset to narrow into (a station table with EVA numbers). The talk doesn't address what to do when the candidate set itself is fuzzy, unbounded, or must be discovered dynamically — which is exactly the harder procurement-cost-center use case the author mentions in the opening and then explicitly declines to return to.Presentation: From Thousands to One: Building LLM-Powered Selection Systems — read next: Look for techniques for LLM-driven selection when the candidate universe cannot be cheaply pre-filtered by deterministic code (e.g., open-world entity resolution, dynamic vendor/cost-center taxonomies).