Despite access to the powerful Fable model, Mike Krieger finds it's "overkill" for simple queries like sports scores. He deliberately uses the faster, less "thoughtful" Sonnet model on his phone, highlighting the need for a "model fleet" approach for different tasks.

Use a highly intelligent model like Opus for high-level planning and a more diligent, execution-focused model like a GPT-Codex variant for implementation. This 'best of both worlds' approach within a model-agnostic harness leads to superior results compared to relying on a single model for all tasks.

Sophisticated users are moving beyond single-model setups. An optimal strategy involves using Anthropic's Opus 4.7 for its superior high-level planning capabilities and then handing off execution to OpenAI's GPT-5.5. This multi-model approach leverages the distinct strengths of each platform, widening the performance gap against any 'mono-model' workflow.

An effective cost-saving strategy for agentic workflows is to use a powerful model like Claude Opus to perform a complex task once and generate a detailed 'skill.' This skill can then be reliably executed by a much cheaper and faster model like Sonnet for subsequent use.

Weaker 'executor' models like Anthropic's Haiku tend to under-call the advisor tool by default. System prompts must explicitly encourage consultation at key moments to boost performance, whereas more capable models like Opus already know when to escalate and can even be hindered by such nudges.

The strategy pairs a cheap 'executor' model for most tasks with an expensive 'advisor' model for critical guidance. The advisor's high-quality, early-stage planning prevents the cheaper model from making costly mistakes and wasting tokens, leading to overall lower costs despite using a premium model.

Legal AI firm Harvey proved a hybrid system—using a smaller model as a primary worker and routing selectively to a frontier model as an "advisor"—can beat a frontier-only approach on both quality and cost. This demonstrates that intelligent orchestration is a more effective strategy than simply using the most powerful model for every task.

OpenAI's router makes an upfront, system-level decision on which model handles a query before it starts. In contrast, Anthropic's advisor pattern empowers the cheaper model to run the task and escalate to a more intelligent model mid-process based on its own judgment, representing a shift from pre-emptive dispatch to in-context escalation.

The LLM provides intelligence (the "brain"), but the agentic harness provides the ability to interact with and affect the real world (the "body"). A less intelligent model with a capable harness can outperform a smarter model with a limited one, shifting value to the application layer.