Model-Driven Agent Design
The design philosophy of giving a capable model a system prompt, tools, and minimal scaffolding and trusting it to plan/sequence its own actions, instead of constraining it with developer-authored workflow logic (if/for/while, DAGs).
Also known as: model-driven approach, model-driven, trust the model, workflow-driven agents, DAG-based orchestration
How authors use it
Oldest first (extraction date when no publication date is known).
| Author | Their term | Their meaning |
|---|---|---|
| Podcast: Strands Agents with Clare Liguori InfoQ Podcast; host: Thomas Betts; guest: Clare Liguori (AWS, technical lead, Strands Agents SDK) · 2026-07-20 | model-driven approach | Building an agent from just three choices -- a system prompt, a set of tools, and a model -- and trusting the model's own reasoning and tool-call planning to handle inputs, instead of pre-scripting control flow. |
Documents (1)
- Podcast: Strands Agents with Clare Liguori InfoQ Podcast; host: Thomas Betts; guest: Clare Liguori (AWS, technical lead, Strands Agents SDK) · 2026-07-20 source ↗ Reader 🖥️
Building reliable production AI agents means resisting the instinct to constrain them with deterministic workflow logic -- which Strands's own case-study testing shows is measurably less accurate and more brittle than trusting the model -- and instead investing in a minimal model-driven design (system prompt, tools, model) supplemented by targeted runtime controls (evals, stateful 'steering hooks' backed by a full tool-call ledger, continuous evaluation against live traffic) that inject determinism only where and when the model actually needs it, with the harness's job now expanding from running a short reasoning loop toward sustaining long-running, resumable, self-tracking agentic work as the underlying models keep improving.
Propositions touching this concept (4)
By publication month, oldest first (extraction month when no publication date is known).
2026-07
- explicitWorkflow-heavy agent architectures are too brittle to handle real-world unpredictable inputs (e.g. compound questions); the model-driven approach -- system prompt, tools, and a model -- is both easier for developers to adopt and more reliable than heavy scaffolding.
- explicitTraditional software engineering discipline -- unit-testing individual tools to high coverage, chaos/red-team testing with unexpected inputs -- remains essential in a model-driven architecture; trusting the model to reason doesn't replace testing the deterministic pieces it calls.
- explicitThe real payoff of the model-driven approach is that adopting a more capable new model should require changing as little as one line of code (the model identifier) -- which only holds if the team hasn't built heavy custom scaffolding tightly coupled to the current model's specific limitations.
- implicitThere is an unresolved tension between the 'responsible AI' instinct to constrain agents with explicit, auditable workflow/allowlist logic (Thomas's framing of his own team's platform) and the model-driven finding that such constraints reduce both accuracy and flexibility; evals and steering hooks are offered as a way to gain some determinism without giving up flexibility, but whether they satisfy the same audit/compliance bar that motivates workflow-engine designs is never directly addressed.
Open gaps (1)
- incompleteThe 'rethinking' is asserted rather than performed. The article never enumerates the prior harness assumptions being overturned (e.g., DAG-based orchestration, deterministic tool dispatch, code-defined skills, developer-mediated change) nor articulates the new principles replacing them beyond 'skills written in English.' For a piece titled 'Rethinking the Agent Harness,' the actual rethink is one anecdote and one neologism.This Week in AI: Rethinking the Agent Harness — read next: Berryman & Ziegler, 'Prompt Engineering for LLMs' (the cited O'Reilly book); Anthropic's own Claude Code design docs; the Stanford paper at arXiv:2603.28052; Birgitta Böckeler's 'harness engineering' piece for an attempt to actually decompose the harness layer.