Past Immediate-and-Pray – O’Reilly

TL;DR:

• Enterprise AI groups are discovering that purely agentic approaches (dynamically chaining LLM calls) don’t ship the reliability wanted for manufacturing programs.
• The prompt-and-pray mannequin—the place enterprise logic lives completely in prompts—creates programs which are unreliable, inefficient, and unimaginable to keep up at scale.
• A shift towards structured automation, which separates conversational means from enterprise logic execution, is required for enterprise-grade reliability.
• This method delivers substantial advantages: constant execution, decrease prices, higher safety, and programs that may be maintained like conventional software program.

Image this: The present state of conversational AI is sort of a scene from Hieronymus Bosch’s Backyard of Earthly Delights. At first look, it’s mesmerizing—a paradise of potential. AI programs promise seamless conversations, clever brokers, and easy integration. However look intently and chaos emerges: a false paradise all alongside.

Your organization’s AI assistant confidently tells a buyer it’s processed their pressing withdrawal request—besides it hasn’t, as a result of it misinterpreted the API documentation. Or maybe it cheerfully informs your CEO it’s archived these delicate board paperwork—into completely the mistaken folder. These aren’t hypothetical eventualities; they’re the each day actuality for organizations betting their operations on the prompt-and-pray method to AI implementation.

Study quicker. Dig deeper. See farther.

The Evolution of Expectations

For years, the AI world was pushed by scaling legal guidelines: the empirical statement that bigger fashions and larger datasets led to proportionally higher efficiency. This fueled a perception that merely making fashions greater would resolve deeper points like accuracy, understanding, and reasoning. Nevertheless, there’s rising consensus that the period of scaling legal guidelines is coming to an finish. Incremental features are more durable to realize, and organizations betting on ever-more-powerful LLMs are starting to see diminishing returns.

In opposition to this backdrop, expectations for conversational AI have skyrocketed. Bear in mind the easy chatbots of yesterday? They dealt with primary FAQs with preprogrammed responses. At this time’s enterprises need AI programs that may:

• Navigate advanced workflows throughout a number of departments
• Interface with a whole lot of inner APIs and providers
• Deal with delicate operations with safety and compliance in thoughts
• Scale reliably throughout 1000’s of customers and tens of millions of interactions

Nevertheless, it’s essential to carve out what these programs are—and are usually not. After we discuss conversational AI, we’re referring to programs designed to have a dialog, orchestrate workflows, and make choices in actual time. These are programs that have interaction in conversations and combine with APIs however don’t create stand-alone content material like emails, displays, or paperwork. Use instances like “write this electronic mail for me” and “create a deck for me” fall into content material era, which lies outdoors this scope. This distinction is vital as a result of the challenges and options for conversational AI are distinctive to programs that function in an interactive, real-time setting.

We’ve been informed 2025 would be the Yr of Brokers, however on the similar time there’s a rising consensus from the likes of Anthropic, Hugging Face, and different main voices that advanced workflows require extra management than merely trusting an LLM to determine all the things out.

The Immediate-and-Pray Downside

The usual playbook for a lot of conversational AI implementations immediately seems one thing like this:

1. Acquire related context and documentation
2. Craft a immediate explaining the duty
3. Ask the LLM to generate a plan or response
4. Belief that it really works as supposed

This method—which we name immediate and pray—appears enticing at first. It’s fast to implement and demos properly. However it harbors severe points that change into obvious at scale:

Unreliability

Each interplay turns into a brand new alternative for error. The identical question can yield completely different outcomes relying on how the mannequin interprets the context that day. When coping with enterprise workflows, this variability is unacceptable.

To get a way of the unreliable nature of the prompt-and-pray method, take into account that Hugging Face reviews the state-of-the-art on perform calling is properly below 90% correct. 90% accuracy for software program will typically be a deal-breaker, however the promise of brokers rests on the flexibility to chain them collectively: Even 5 in a row will fail over 40% of the time!

Inefficiency

Dynamic era of responses and plans is computationally costly. Every interplay requires a number of API calls, token processing, and runtime decision-making. This interprets to larger prices and slower response occasions.

Complexity

Debugging these programs is a nightmare. When an LLM doesn’t do what you need, your fundamental recourse is to alter the enter. However the one method to know the influence that your change could have is trial and error. When your utility includes many steps, every of which makes use of the output from one LLM name as enter for one more, you might be left sifting by means of chains of LLM reasoning, making an attempt to know why the mannequin made sure choices. Growth velocity grinds to a halt.

Safety

Letting LLMs make runtime choices about enterprise logic creates pointless danger. The OWASP AI Safety & Privateness Information particularly warns in opposition to “Extreme Company”—giving AI programs an excessive amount of autonomous decision-making energy. But many present implementations do precisely that, exposing organizations to potential breaches and unintended outcomes.

A Higher Means Ahead: Structured Automation

The choice isn’t to desert AI’s capabilities however to harness them extra intelligently by means of structured automation. Structured automation is a growth method that separates conversational AI’s pure language understanding from deterministic workflow execution. This implies utilizing LLMs to interpret person enter and make clear what they need, whereas counting on predefined, testable workflows for vital operations. By separating these considerations, structured automation ensures that AI-powered programs are dependable, environment friendly, and maintainable.

This method separates considerations which are typically muddled in prompt-and-pray programs:

• Understanding what the person desires: Use LLMs for his or her power in understanding, manipulating, and producing pure language
• Enterprise logic execution: Depend on predefined, examined workflows for vital operations
• State administration: Keep clear management over system state and transitions

The important thing precept is straightforward: Generate as soon as, run reliably endlessly. As an alternative of getting LLMs make runtime choices about enterprise logic, use them to assist create strong, reusable workflows that may be examined, versioned, and maintained like conventional software program.

By retaining the enterprise logic separate from conversational capabilities, structured automation ensures that programs stay dependable, environment friendly, and safe. This method additionally reinforces the boundary between generative conversational duties (the place the LLM thrives) and operational decision-making (which is greatest dealt with by deterministic, software-like processes).

By “predefined, examined workflows,” we imply creating workflows through the design part, utilizing AI to help with concepts and patterns. These workflows are then carried out as conventional software program, which might be examined, versioned, and maintained. This method is properly understood in software program engineering and contrasts sharply with constructing brokers that depend on runtime choices—an inherently much less dependable and harder-to-maintain mannequin.

Alex Strick van Linschoten and the workforce at ZenML have just lately compiled a database of 400+ (and rising!) LLM deployments within the enterprise. Not surprisingly, they found that structured automation delivers considerably extra worth throughout the board than the prompt-and-pray method:

There’s a placing disconnect between the promise of absolutely autonomous brokers and their presence in customer-facing deployments. This hole isn’t stunning after we look at the complexities concerned. The fact is that profitable deployments are likely to favor a extra constrained method, and the explanations are illuminating.…
Take Lindy.ai’s journey: they started with open-ended prompts, dreaming of absolutely autonomous brokers. Nevertheless, they found that reliability improved dramatically once they shifted to structured workflows. Equally, Rexera discovered success by implementing determination bushes for high quality management, successfully constraining their brokers’ determination house to enhance predictability and reliability.

The prompt-and-pray method is tempting as a result of it demos properly and feels quick. However beneath the floor, it’s a patchwork of brittle improvisation and runaway prices. The antidote isn’t abandoning the promise of AI—it’s designing programs with a transparent separation of considerations: conversational fluency dealt with by LLMs, enterprise logic powered by structured workflows.

What Does Structured Automation Look Like in Follow?

Think about a typical buyer assist state of affairs: A buyer messages your AI assistant saying, “Hey, you tousled my order!”

• The LLM interprets the person’s message, asking clarifying questions like “What’s lacking out of your order?”
• Having acquired the related particulars, the structured workflow queries backend knowledge to find out the difficulty: Had been gadgets shipped individually? Are they nonetheless in transit? Had been they out of inventory?
• Primarily based on this info, the structured workflow determines the suitable choices: a refund, reshipment, or one other decision. If wanted, it requests extra info from the client, leveraging the LLM to deal with the dialog.

Right here, the LLM excels at navigating the complexities of human language and dialogue. However the vital enterprise logic—like querying databases, checking inventory, and figuring out resolutions—lives in predefined workflows.

This method ensures:

• Reliability: The identical logic applies constantly throughout all customers.
• Safety: Delicate operations are tightly managed.
• Effectivity: Builders can take a look at, model, and enhance workflows like conventional software program.

Structured automation bridges the most effective of each worlds: conversational fluency powered by LLMs and reliable execution dealt with by workflows.

What In regards to the Lengthy Tail?

A typical objection to structured automation is that it doesn’t scale to deal with the “lengthy tail” of duties—these uncommon, unpredictable eventualities that appear unimaginable to predefine. However the reality is that structured automation simplifies edge-case administration by making LLM improvisation protected and measurable.

Right here’s the way it works: Low-risk or uncommon duties might be dealt with flexibly by LLMs within the quick time period. Every interplay is logged, patterns are analyzed, and workflows are created for duties that change into frequent or vital. At this time’s LLMs are very able to producing the code for a structured workflow given examples of profitable conversations. This iterative method turns the lengthy tail right into a manageable pipeline of latest performance, with the information that by selling these duties into structured workflows we acquire reliability, explainability, and effectivity.

From Runtime to Design Time

Let’s revisit the sooner instance: A buyer messages your AI assistant saying, “Hey, you tousled my order!”

The Immediate-and-Pray Method

1. Dynamically interprets messages and generates responses
2. Makes real-time API calls to execute operations
3. Depends on improvisation to resolve points

This method results in unpredictable outcomes, safety dangers, and excessive debugging prices.

A Structured Automation Method

1. Makes use of LLMs to interpret person enter and collect particulars
2. Executes vital duties by means of examined, versioned workflows
3. Depends on structured programs for constant outcomes

The Advantages Are Substantial:

• Predictable execution: Workflows behave constantly each time.
• Decrease prices: Diminished token utilization and processing overhead.
• Higher safety: Clear boundaries round delicate operations.
• Simpler upkeep: Commonplace software program growth practices apply.

The Position of People

For edge instances, the system escalates to a human with full context, making certain delicate eventualities are dealt with with care. This human-in-the-loop mannequin combines AI effectivity with human oversight for a dependable and collaborative expertise.

This technique might be prolonged past expense reviews to different domains like buyer assist, IT ticketing, and inner HR workflows—anyplace conversational AI must reliably combine with backend programs.

Constructing for Scale

The way forward for enterprise conversational AI isn’t in giving fashions extra runtime autonomy—it’s in utilizing their capabilities extra intelligently to create dependable, maintainable programs. This implies:

• Treating AI-powered programs with the identical engineering rigor as conventional software program
• Utilizing LLMs as instruments for era and understanding, not as runtime determination engines
• Constructing programs that may be understood, maintained, and improved by regular engineering groups

The query isn’t the way to automate all the things directly however how to take action in a approach that scales, works reliably, and delivers constant worth.

Taking Motion

For technical leaders and determination makers, the trail ahead is obvious:

The period of immediate and pray may be starting, however you are able to do higher. As enterprises mature of their AI implementations, the main target should shift from spectacular demos to dependable, scalable programs. Structured automation gives the framework for this transition, combining the facility of AI with the reliability of conventional software program engineering.

The way forward for enterprise AI isn’t nearly having the most recent fashions—it’s about utilizing them properly to construct programs that work constantly, scale successfully, and ship actual worth. The time to make this transition is now.