SENTIENTA
May 7th, 2025
In past posts, we’ve seen how natural language workflows simplify complex portfolio monitoring, and how scheduled tasks let agents run without user input. Today, we’re combining these powers in a single instruction: a user defines a high-level goal—monitor AMZN and NVDA for 3% price drops—and Sentienta handles the rest. It parses the language, builds the workflow, schedules it to run every 30 minutes, and manages each run intelligently. Multiple scheduled workflows can run in parallel, each executing complex logic—no code, no setup screens, just natural language.
The user’s request is simple on the surface—“Monitor AMZN and NVDA for a 3% drop and alert me”—but that instruction triggers a multi-layered automation. Sentienta interprets the goal, identifies that real-time pricing data is needed, calculates change percentages, evaluates conditions, and routes alert tasks if thresholds are met. Each step is delegated to the appropriate agent using the right tools. All of it is wrapped into a workflow that is created instantly through natural language—no coding, no flowchart building, no manual agent assignment.
The following graph shows this simple workflow:
Once the workflow is created, the user simply asks it to run every 30 minutes—and Sentienta schedules recurring executions automatically. Each run pulls updated stock prices, assesses whether either AMZN or NVDA has dropped by 3%, and triggers alerts if so. Users can check task status, inspect the workflow graph, or fetch results at any time—all via natural language. As the transcript shows, there’s no manual reconfiguration between runs. The system just works—consistently, transparently, and in parallel with any other workflows the user initiates.
User:Schedule the following task to occur every 30 minutes: "Here is our portfolio [AMZN, NVDA]. For each stock, if the price decreased by more than 3%, send an alert." This should be done for a max of 16 times.
Wed, 07 May 2025 17:23:54 David:
Task clscofield997atgmail-dropchk1pd6e09bc6 is scheduled to run every 30 minutes and will stop after 16 runs.
...
User:Show results for task clscofield997atgmail-dropchk1pd6e09bc6
Wed, 07 May 2025 22:27:30 David:
Here are the current results for clscofield997atgmail-dropchk1pd6e09bc6:
### Research Results Summary – Stock Price Analysis as of May 7, 2025
#### Table: Stock Price Details
| Attribute | Amazon (AMZN) | NVIDIA (NVDA) |
|-----------------------|---------------------|----------------------|
| Current Price | $189.04 | $113.99 |
| Price Change | +$4.03 | +$0.45 |
| Percent Change | +2.18% | +0.39% |
| Opening Price | $186.71 | $114.29 |
| Previous Close | $185.01 | $113.54 |
| Day’s High | $190.99 | $114.29 |
| Day’s Low | $185.01 | $112.62 |
#### Drop Evaluation Results
| Evaluation Check | AMZN | NVDA |
|------------------------|--------------------------|--------------------------|
| Price Drop Detected | No | No |
| Percentage Change | +2.18% | +0.39% |
| Classification Result | Not a drop (>1%) | Not a drop (>1%) |
| Alert Triggered | False | False |
---
Summary
On May 7, 2025, both Amazon (AMZN) and NVIDIA (NVDA) experienced positive price movements in the stock market:
- Amazon (AMZN) saw a strong gain of +2.18%, rising from a previous close of $185.01 to $189.04. The intraday high reached $190.99.
- NVIDIA (NVDA) posted a modest increase of +0.39%, rising from $113.54 to $113.99, with a high of $114.29 during the session.
According to the automated evaluation workflow:
- No price drop exceeding 3% was observed for either stock.
- As such, both were classified as "no drop", and no alerts were triggered.
The workflow executed a four-step structure per stock — fetching quotes, checking price drops, classifying the result, and sending alerts if necessary — which did not yield any drop alerts for AMZN or NVDA on this date.
This indicates a stable or upward movement in the technology sector for the referenced stocks on May 7, 2025.
This workflow is just one of many that can be created and scheduled in parallel. A portfolio manager might monitor multiple assets, each with its own threshold, timing, or downstream trigger—Sentienta handles them all concurrently. Whether it’s tracking different sectors, adding earnings-based filters, or launching trading actions based on composite signals, every workflow runs independently and automatically. There’s no limit on scale or complexity—just natural language input and intelligent execution.
Sentienta scheduled workflows enable fast triage, coordinated triggers, and domain-specific actions—without custom code.
To learn more start with our Managing Portfolio Workflows with Natural Language: A Multi-Agent Use Case and follow up with Powering Productivity: Task Scheduling for Intelligent Agents.