AI
Building AI systems to automate complex business processes involves breaking problems into a series of small, well-defined patterns. At Sentrix Labs, we are actively working to progress the state-of-the-art in using AI to solve real-world business problems. Patterns are how we build reliable, scalable AI systems.
Neither corporate processes nor AI are monolithic.
The chat interface is by far the most common UI pattern for interacting with AI since the release of ChatGPT.
Yes, chat interfaces are familiar. Users type, AI responds. But consider what happens when you deploy this pattern for expense report processing. Users expect transparency ("Why was this rejected?"), reversibility ("Undo that categorization"), and consistency ("I approved this last week!"). Chat interfaces promise all three but deliver none reliably at scale.
When it works: Customer support, knowledge retrieval, brainstorming When it fails: High-volume transactions, structured data entry, compliance-critical processes
The most common non-conversational UI pattern is to embed AI into existing applications and workflows. Instead of a chat window, AI operates through:
Beyond UI, you must decide how control is shared and handed off between humans and their AI counterparts:
Human Orchestrator Pattern: Humans manually sequence AI tasks. Great for high-stakes decisions, where quality must be verified at every step of the process.
Human-in-the-Loop (HITL) Pattern: AI drives workflow but pauses for human input when confidence drops below threshold.
AI Dynamic Orchestration Pattern: AI plans and executes its own workflows. This patterns has proven extremely useful in software development.
How AI gets activated is as important as what it does. The right trigger pattern can mean the difference between a helpful assistant and an annoying interruption.
The obvious pattern and the most common as it's the interaction pattern for most conversational UIs: user asks, AI responds. But this creates a fundamental scalability problem. If every AI action requires human initiation, you're limited by human bandwidth.
Optimal use cases:
This is where enterprise AI gets interesting. AI activates based on system events:
An emergent pattern is Agent to Agent communication via a protocol, such as Google's A2A or IBM's ACP. Essentially one AI agent triggers another AI agent. Think microservices, but for AI.
Example workflow:
Each agent has one job. Each can be updated independently. Each can scale horizontally.
Don't underestimate the power of "boring" cron-based AI:
When combined with communication tools, the overhead required to generate these reports can be reduced dramatically.
Workflow composition is how you automate larger, more complex business processes.
The simplest pattern: Step 1 -> Step 2 -> Step 3. Perfect for linear processes with clear dependencies.
When tasks don't depend on each other, run them simultaneously to reduce processing times.
AI's superpower is iteration without fatigue. Use it:
A marketing agency uses this for blog post generation. First draft is 60% ready. After 3 AI review loops, it's 90% ready. Human effort drops from hours to minutes.
Real workflows are messy. They need sequential steps, parallel processing, and review loops. The key is mapping your processes to each pattern.
The holy grail is AI that plans its own workflows. Instead of pre-defining steps, you define goals and constraints. AI figures out the path.
This requires sophisticated evals and observability.
Not all AI tasks are created equal. Understanding the difference between deterministic and non-deterministic tasks is crucial for building reliable systems.
These have predictable outputs: API calls, data lookups, calculations, format conversions. These tasks are easy to classify as having completed correctly vs. incorrectly.
These should be implemented as tools/functions, not prompts. They're testable, debuggable, and won't hallucinate.
These require judgment, creativity, or interpretation such as summarization or content generation.
The key is accepting variability while maintaining quality bounds. Use techniques like:
Most real-world processes combine both patterns within a single workflow where some steps use deterministic tasks while others use non-deterministic tasks.
The gap between AI demos and production systems isn't only about technology. Start by mapping your current business processes to these four categories of patterns. Start with the simplest, least error prone pattern for your business needs. First make it work. Then scale.
Lastly, leverage past learnings. No doubt your organization has a playbook from adopting BPO/KPO over the past couple of decades. A lot of those learnings apply to AI.