Search as Code: Perplexity rewrites AI search

From fixed API to programming agent: the paradigm shift

For years, AI-powered search systems have operated on a rigid pattern. A language model would receive a query, call a predefined search API, and return results. The process was linear, but also limited. Fixed APIs cannot dynamically adapt to the complexity of the request. Therefore, the model was forced to work with standardized outputs, often redundant or irrelevant.

Perplexity has overturned this logic with Search as Code . In this new paradigm, the AI agent doesn't call an external API. Instead, it directly writes the Python code needed to build its own search pipeline. Therefore, the model autonomously decides how to filter data, remove duplicates, and aggregate sources. Everything happens within an isolated and controlled sandbox environment.

This approach closely resembles the logic of tool-use agents , but it goes further. Instead of using predefined tools, the agent itself becomes the author of the tools. In summary, this is a qualitative leap in the reasoning and autonomy capabilities of language models applied to research.

Internal architecture: how the Python sandbox works

The heart of Search as Code is a secure execution environment. The AI agent generates Python code that runs in a sandbox with controlled access to external resources. This allows the system to query heterogeneous sources, apply custom filtering logic, and deduplicate results before returning them to the main model.

According to reports by The Decoder , the system reduces token consumption by up to 85% compared to equivalent architectures from OpenAI and Anthropic. This figure is significant. In fact, token costs represent one of the most relevant expenses for those operating large-scale AI pipelines.

Furthermore, the system surpasses industry benchmarks. This suggests that the flexibility of the dynamically generated pipeline produces qualitatively superior results compared to static approaches. In particular, the internal deduplication capability reduces information noise, improving the accuracy of the final answers.

To delve deeper into the architectural implications of autonomous AI agents, it is useful to consult the analyses of Gartner on the evolution of AI agents and the research work of MIT Technology Review on emerging architectures.

Real-world use cases for Italian SMEs

The most relevant question for an Italian SME is not technical. It's operational: does this technology change anything in my processes today? The answer depends on the sector and the company's level of digital maturity.

In B2B Retail , for example, a Search as Code agent could build price and supplier availability monitoring pipelines in a completely automated way. Instead of relying on rigid scrapers or expensive commercial APIs, the agent writes its own data collection code. As a result, the system dynamically adapts to changes in sources without manual intervention.

In digital marketing , the applications are just as interesting. An agent could build search pipelines for competitive analysis, aggregating data from different sources with custom filtering logic. We at SHM Studio we see in this approach a natural evolution of tools for artificial intelligence applied to marketing .

Furthermore, in the sector of professional services , custom research pipelines can support due diligence, regulatory monitoring, and market analysis tasks. Therefore, the value is not only in cost savings but in the quality and relevance of the information collected.

For companies evaluating how to integrate these capabilities, the starting point is often a review of their own digital marketing strategy and existing information flows.

Comparison with OpenAI and Anthropic: where's the difference

OpenAI and Anthropic offer agentic search solutions through tools like function calling and tool use . However, these approaches remain anchored to predefined schemes. The model chooses which tool to use, but cannot modify its internal behavior.

Perplexity's Search as Code introduces a higher level of flexibility. The agent doesn't choose between existing tools. Instead, it builds the most suitable tool for the specific need. This difference is substantial from an engineering perspective.

In terms of costs, the advantage is already quantified: up to an 85% reduction in token consumption. For a company managing significant volumes of AI queries, this translates into concrete operational savings. Similarly, reducing informational noise improves output quality, lowering costs associated with manual result verification.

However, it's important not to overestimate the comparison. OpenAI and Anthropic have more mature ecosystems, with established enterprise integrations. Therefore, the choice between different platforms depends on the specific context of each organization. For an in-depth look at competitive dynamics in the AI sector, it's useful to consult analyses from Harvard Business Review on enterprise AI .

Trade-offs and risks to consider

Every innovative architecture brings trade-offs with it. Search as Code is no exception. The first critical aspect concerns the sandbox security . Allowing an AI agent to write and execute Python code introduces security risks that must be carefully managed. Perplexity claims to have implemented robust controls, but the attack surface remains larger than with fixed APIs.

The second trade-off concerns the reproducibility A dynamically generated pipeline can produce different results with each run. This can be an advantage in terms of adaptability, but it becomes a problem in contexts that require deterministic and auditable outputs.

Furthermore, operational complexity increases. Managing a system where code is dynamically generated and executed requires specific technical skills. For SMEs without a structured IT team, this can be a barrier to adoption. Therefore, it is crucial to assess your level of technological maturity before proceeding with integration.

Finally, dependence on a single provider remains a strategic risk. Relying on Perplexity for a critical component of the information pipeline exposes the company to variations in pricing, policies, or service availability. A balanced AI strategy always includes a contingency plan.

The construction site still open: what's missing for enterprise adoption

Search as Code is a promising technology, but not yet mature for widespread enterprise adoption. Several aspects remain to be defined. Firstly, agent governance: who is responsible for AI-generated code? How is the audit trail managed in regulated contexts?

Second, interoperability standards are lacking. Today, a pipeline built with Perplexity's Search as Code is not easily portable to other systems. Therefore, companies adopting this technology implicitly accept a degree of lock-in.

Despite this, the direction is clear. The AI industry is moving towards increasingly autonomous agents, capable of building their own tools instead of using pre-defined ones. This evolution will have profound implications for automated advertising campaigns , for the SEO and for the content production .

Recommended decision: how to navigate today

For an Italian SME looking to evaluate Search as Code, a gradual approach is recommended. First, it's helpful to map your information flows and identify where rigid search pipelines create bottlenecks. Then, you can evaluate a pilot project on a specific, low-risk use case.

In particular, companies that are already using AI agents in their processes are the best positioned to experiment with this technology. For those still in the early stages, it is wiser to build a solid foundation first: web presence , a strategy structured SEO and campaigns Linkedin and Google Ads optimized.

We at SHM Studio we follow the evolution of these technologies with analytical attention. Our approach is always the same: evaluate the real impact before recommending adoption. To learn more about how these innovations can be integrated into your company's digital strategy, the team is available via the contact page . Furthermore, on our Blog we continue to monitor major developments in the AI and digital marketing landscape.