Topic starter
20/08/2026 6:05 pm
TL;DR: Building a shopping assistant shows that forcing every interaction through agentic reasoning adds latency, cost, and control risk when clear intents can be handled deterministically, while open-ended, multi-step tasks still need a ReAct-style loop, TruFoundry’s analysis finds. TrueFoundry’s analysis also shows that state must be organised around workflows and explicit context, not just conversation history, to keep multi-product assistants reliable.
Editorial analysis by NHI Mgmt Group, based on content published by TruFoundry: “Deterministic vs Agentic Workflows: Lessons from Building a Shopping Assistant”.
Key questions
Q: When should teams use deterministic workflows instead of agentic reasoning in AI assistants?
A: Use deterministic workflows when the intent is clear, the tool is known, and the expected output is predictable.
Q: Why does building SSO in-house often create more risk and cost than using a dedicated provider?
A: In-house SSO usually looks cheaper at first, but the hidden cost is ongoing engineering effort.
Q: What breaks when AI assistants rely on flat conversation history?
A: A flat history accumulates irrelevant context, increases token load, and makes it hard to know which object the user means.
Practitioner guidance
- Route known intents deterministically Classify requests such as specs, coupons, and review summaries into direct tool execution paths, and reserve reasoning loops for requests that genuinely need multi-step decisioning.
- Limit ReAct to uncertain workflows Use agentic loops only for cases like inventory checks, store discovery, or fulfillment selection where intermediate results change the next action.
- Split state by workflow and entity Keep user-level state separate from product-level state, and make current_product_id an explicit variable so context shifts do not corrupt downstream actions.
Bottom line: Deterministic workflows are the better control pattern for known intents because they reduce latency, cost, and decision noise.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
20/08/2026 6:40 pm
Deterministic routing is the governance control hidden inside performance engineering. When a request has a known intent, the safest design is often the least autonomous one because it constrains tool choice, output shape, and state drift. That makes the system easier to test, easier to audit, and less likely to improvise where no judgment is needed. For practitioner teams, the control question is not whether the model can reason, but where reasoning should be disallowed.
A few things that frame the scale:
- AI-related credential leaks surged 81.5% year-over-year in 2025, with the surrounding AI infrastructure leaking 5x faster than core LLM providers, according to the State of Secrets Sprawl 2026.
A question worth separating out:
Q: How should teams structure workflow state for multi-step AI assistants?
A: Separate state by workflow and entity, such as user preferences, active product context, and agent-thread memory. Make key context variables explicit, so the system can refresh downstream data when the user changes focus. That approach keeps orchestration predictable and reduces accidental context bleed across tasks.
👉 Read our full editorial: Deterministic workflows still beat agentic reasoning for AI assistants