Tag: business

  • A Messaging Agent for Powering Workflow Notifications and Alerts

    In previous posts, we showcased end-to-end business workflows where the final step—delivering results or critical notifications—was handled by an “Alec” Messaging Agent. Each workflow diagram highlighted Alec as the automated agent responsible for sending these updates to key stakeholders, acting as the bridge between the team’s AI-driven analysis and real-world action. For reference, you can revisit these detailed walk-throughs here: Managing Portfolio Workflows with Natural Language: A Multi-Agent Use Case, Automating Market Vigilance: Scheduled Workflows for Smarter Portfolio Management, Handling the Heat: Workflow Agents in a Critical Incident.

    Messaging Agent Core Features and Availability

    The Alec agent can be accessed directly from the Agent Marketplace under the Messaging section. Simply navigate to Messaging, select Alec, and either deploy the agent as-is or customize its persona and instructions to fit your workflow—all without coding.

    1. Analyzes natural-language transcripts—agent dialog, user input, and workflow results—to determine the subject and email type (alert, notification, summary).
    2. Auto-selects the correct recipients or distribution list from workflow context and dispatches the message.
    3. Writes delivery status back into the workflow for end-to-end auditability.
    4. Available as a pre-built messaging agent in the Agent Marketplace’s new Messaging section; no-code, drag-and-drop setup.
    5. Fully customizable: adjust persona name, tone, and email-formatting instructions to fit any workflow.

    Example Use Cases

    The first, simple use-case shows how the user can ask Alec to summarize a team discussion and email to a couple of recipients:

    User:Alec - please summarize this dialog and send as an email to nekeh10717@dlbazi.com and chris@sentienta.ai
    
    Wed, 21 May 2025 18:20:42 Alec:
    Email sent to ['nekeh10717@dlbazi.com', 'chris@sentienta.ai']

    Below is an example of the kind of message that Alec will deliver:

    In contrast to the previous example, which highlights Alec’s ability to respond to direct user prompts, the prior use cases focus on Alec’s role in delivering messages as part of automated, executed workflows. In each of these, Alec serves as the final messaging agent in automated workflows, delivering workflow outcomes or critical analysis results to designated stakeholders with context-aware notifications or alerts.

    For example, in this post, Alec provided an alert if the price of a stock in the portfolio dropped below a threshold. In this case, the workflow agent created a task that automatically informed Alec of the message type, content, and the condition for sending it. The following shows the task defined for Alec by the workflow agent:

    {
    "taskID": "send_alert_AMZN",
    "agent": "Alec",
    "dependsOn": "classify_price_drop_AMZN",
    "params": {
    "message": "The price for AMZN has dropped by more than 1%.",
    "subject": "AMZN Price Alert",
    "type": "email"
    }
    }

    Conclusion and Next Steps

    Alec combines no-code simplicity with powerful automation, making it easy to streamline communications across any workflow. Whether sending one-off summaries or powering complex alerting and notification patterns, Alec’s flexibility and seamless setup help teams communicate more efficiently. Explore Alec in the Agent Marketplace to enhance communication across your workflows.

  • Managing Portfolio Workflows with NL: A Multi-Agent Use Case

    In our previous post, we demonstrated how a simple workflow could be defined and executed using plain language. This time, we examine a more advanced scenario that includes conditional branching, parallel tasks, and multiple agents interacting across different stages of the workflow. The example: a portfolio review where the Angie agent gathers real-time stock quotes, Rob analyzes price changes, and internal language models classify results. If a stock rises more than 1%, Alec sends an alert while Angie retrieves relevant news and sentiment. All of this is orchestrated by David, who builds and executes the workflow from the user’s natural language instruction. This illustrates how complex, multi-stage business logic can be expressed and enacted entirely through natural language.

    Scenario Description

    The user begins with a portfolio containing four stocks: AMZN, NVDA, AAPL, and GOOG. They ask the system to monitor each stock and take specific actions based on market performance. Specifically, if any stock in the portfolio increases in price by more than 1%, the system should both notify the user and retrieve recent news and sentiment related to that stock. Here is the user’s query:

    Here is our portfolio [AMZN, NVDA, AAPL, GOOG]. For each stock, if the price increased by more than 1%, send an alert and get the latest news and sentiment about the stock

    This scenario involves multiple agents working together: Angie collects the initial quotes, Rob performs the price analysis, and language models classify the results. If a stock meets the threshold, Alec sends an alert and Angie independently gathers news and sentiment. The system intelligently branches execution based on conditional logic and handles parallel tasks across agents—all initiated by a single natural language instruction.

    Workflow Construction Using Natural Language

    Unlike traditional no-code platforms that require dragging blocks or manually assigning agents to predefined tasks, David streamlines the entire process through natural language alone. When the user submits a request, David interprets the intent, identifies the required skills, and matches them to available agents – either defined locally or selected from the Agent Marketplace. For instance, in this scenario, David determines that Angie retrieves quotes and news, Rob analyzes the data, and Alec sends alerts. Task definitions, conditional logic, and parallel execution paths are all inferred—no manual structure or assignment required.

    As the workflow runs, the system transparently relays progress via live status updates for each completed step. At any time, the user can request a graphical representation of the active workflow. First the user gets a list of the workflows, then selects the one they want to see.

    In the detail window, the user can see the workflow, displaying all of the tasks and agents assignments:

    Once the workflow completes, users can retrieve structured results or clean up completed tasks—again with plain language:

    This abbreviated transcript shows the results of each of the tasks that the workflow agent defined and assigned. In addition to getting workflow graphs and results, the user can do the usual workflow and task management functions with natural language queries.

    Conclusion

    This scenario illustrates how complex multi-agent workflows can be created, monitored, and managed using nothing more than natural language. From interpreting conditional logic to orchestrating parallel tasks and assigning agents automatically, David abstracts away all manual configuration. Real-time execution updates, workflow visualization, and result retrieval further demonstrate the depth of control available through natural interaction. By enabling users to express business logic directly in language, Sentienta’s no-code model significantly lowers the barrier to sophisticated workflow automation.

  • How Sentienta Teams Navigate Supply Chain Disruptions: A Midwest Fulfillment Crisis

    Introduction

    When an unexpected promo surge strains Midwest operations with forecasting overshoot, logistics bottlenecks, and perilously low inventory a Sentienta Supply Chain team can help strategize solutions. In this post, we walk you through real-time data snapshots and individual agent analyses to show how distributed cognition transforms isolated insights into a unified, adaptive strategy that resolves complex fulfillment challenges.

    The Supply Chain team consists of three specialized agents who think like experts and collaborate like a team.

    • Miles: the Demand Forecaster, identifies unexpected sales surges and recalibrates forecasts to match emergent buying patterns.
    • Isla: the Inventory Optimization Strategist, spots stockout risks and reshuffles resources across distribution centers to sustain availability.
    • Talia: the Logistics Flow Strategist, detects fulfillment bottlenecks and reroutes shipments to maintain throughput and cost-efficiency.

    Each agent works from their own specialized dashboard—focused on demand, inventory, or logistics—to identify emerging risks. Once surfaced, these distinct insights are shared across the team, enabling a coordinated strategy that addresses the full scope of the disruption.

    The Data

    Isla’s Inventory Dashboard:

    Key Insight: DC-B (South) shows a 100% inventory variance with zero actual inventory and delayed container status due to port congestion.

    Miles’ Demand Dashboard:

    Key Insight: Midwest region experienced a 28% sales spike driven by influencer uplift and online channel deviation—outpacing model expectations by a wide margin.

    Talia’s Logistics Dashboard:

    Key Insight: The Midwest region shows major logistics disruption: a 59% delivery delay, 35% staffing gap at the Chicago hub, and a $1.28 per-unit cost surge—triggered by reroutes and carrier delays.

    Agent Insights – What the Dashboards Revealed to the Agents

    As part of the daily review cycle, each agent initiated a rapid diagnostic scan of their functional dashboards—surfacing anomalies, shortfalls, and emerging threats from the day’s incoming data load. The folllowing transcript captures the collaborative intake phase, where agent specialists flag critical issues in preparation for joint strategy formation. Their early assessments below form the baseline for downstream coordination.

    Supply Chain Team Transcript: Agent Analysis

    Orchestration and Strategy – When Agents Teams Work Together

    After reviewing their functional dashboards, the Supply Chain agents transitioned from isolated diagnostics to integrated strategy formation. What follows is a transcript—condensed for clarity—that reveals how a distributed team of AI experts negotiated trade-offs, merged perspectives, and built a coordinated mitigation strategy for escalating Midwest risks.

    Supply Chain Team Transcript: Team Analysis

    The team co-developed a gated intake triage plan for DC-C with four synchronized filters: SKU velocity tier, forecast lock window, supply/demand thresholds, and margin-volatility pairing. They agreed to data handoffs via shared APIs and established cap tolerances to maintain flexibility under risk. This interaction exemplifies emergent cognition—where no individual agent held the entire solution, but collaboration yielded a coherent, executable plan.

    Conclusion

    This example highlights Sentienta’s core advantage: turning fragmented functional data into synchronized decision intelligence. As agents negotiate thresholds, define roles, and operationalize shared triggers, strategy becomes not just automated—but emergent. Sentienta Teams adapts at the pace of complexity, enabling businesses to respond with coordinated precision.

  • From Signals to Strategy

    How AI Agent Teams Transform Decision-Making

    In today’s real-time economy, with almost daily turmoil, waiting for static dashboards or end-of-day reports puts businesses at risk. Decision-makers need faster insight and smarter responses—and they’re finding both in AI-powered agent teams. This post follows a “decision-day” walk-through where scheduled agents detect anomalies, trigger analysis, and deliver actionable intelligence. Along the way, we’ll preview a powerful future: dynamic response teams that self-assemble on demand, transforming routine data monitoring into collaborative, AI-driven strategy.

    From Manual Monitoring to Team Workflows

    For years, business teams relied on dashboards and manual checks—forcing analysts to sift through data after the fact, often too late to pivot strategy. AI agents like Angie now automate this process, persistently scanning KPIs and surfacing anomalies in near real time – bringing signal to the surface before teams even ask. This shift transforms monitoring from a reactive task into a proactive loop, enabling tactical adjustments as performance fluctuates throughout the day.

    Monitoring TypeDescriptionResponse SpeedHuman Effort
    Manual MonitoringAnalysts check KPIs periodically; issues often spotted lateSlowHigh
    Scheduled TriggersAgents run on set schedules to check and report KPIsModerateMedium
    Team Workflows (Emerging)Agent teams collaborate in sequence—detecting, diagnosing, and acting as events unfold in real timeFastLow

    Early adopters gain more than speed – they free up analysts from routine checking, letting them focus on root cause, strategic options, and next steps.

    Intelligent Agent Teams and Semi-Autonomous Coordination (Today)

    Sentienta Teams lets you assemble expert AI agents customizable to your business context – think of them as always-on teammates with specialized roles. With data collected continuously by Angie, users can periodically request updates, triggering collaborative evaluation across the team. Insights emerge through the interplay of domain-specific agents, each contributing to problem-solving like part of a cohesive virtual task force.

    What’s powerful today is the modular collaboration between agents: Angie spots the signal, users prompt an update, and the team responds—analyzing root causes, surfacing implications, and aligning recommendations. This tiered interaction shortens feedback loops while keeping the human-in-the-loop where needed.

    This model already elevates decision quality by transforming raw signal detection into team-powered insight—without code or integration overhead. Let’s see how this might work:

    Scenario Walk-Through — “End-of-Quarter Chain Reaction”

    At 9:55 AM, Angie, the KPI Monitoring Agent, completes her scheduled data sweep: collecting conversion metrics, analyzing trends against prior cycles, and logging a 12% drop. She also factors in data from the UX Deployment Team’s new UI update logged at 8:00 PM yesterday, establishing a preliminary correlation with increased mobile bounce rates.

    9:55 AM: Angie (KPI Monitoring Agent): “Scheduled Insight Logged — Conversion rate down 12% vs prior cycle. Ingested UX deployment log from 8:00 PM yesterday—preliminary correlation with mobile exit rates established.”

    At 10:05 AM, CMO Alex Morgan reviews Angie’s logged summary while preparing for the QBR, triggering further analysis from the broader agent team.

    10:05 AM: Analytics Agent: “Manual review confirmed. Running historical comparison — dip predominantly isolated to mobile traffic sources.”

    10:07 AM: Competitive Intelligence Agent: “Scanning competitor trends… Detected concurrent promotional push by primary rival.”

    10:10 AM: Summary Agent: “Final insights compiled: Traffic dip largely traced to mobile UX issues with the recent UI update, compounded by competitor campaign. QBR-ready report delivered to shared location.”

    10:12 AM: Presentation Update Agent: “Integrating the final report into the QBR presentation—slides refreshed with updated KPI graphs and attribution notes reflecting the new UI deployment impact.”

    This scenario illustrates how scheduled data logging, combined with cross-departmental inputs and manual review, triggers a coordinated AI response that supports executive decision-making.

    Next-Gen Workflow Automation: Intelligent Sequences & Self-Assembling Expertise

    Get ready for a system where a planning agent can automatically orchestrate the entire process: sequencing actions, branching based on real-time data, and repeating steps as needed. As soon as anomalies are detected, it will dynamically self-assemble the precise mix of expert agents to diagnose issues, forecast impacts, and execute tailored responses, shifting reactive monitoring into a proactive, intelligent strategy.

    This next-generation automation doesn’t just detect an issue—it scripts the solution by activating specialized agents at each step, adapting in real time as conditions evolve.

    Each automated workflow acts like a living blueprint, employing branching logic, conditional triggers, and intelligent retries to ensure the right path is taken as new data emerges.

    From manual monitoring to intelligent workflows, and now toward dynamic, self-assembling response teams, Sentienta is redefining how decisions are made. These AI-powered teams don’t just react, they anticipate, adapt, and execute strategies in real time.

  • Powering Productivity: Task Scheduling for Intelligent Agents

    In previous posts, we’ve explored agent autonomy—how intelligent agents can work independently to accomplish complex goals. Today, we’re unlocking a new level of autonomy: the ability to schedule agents and teams to run tasks automatically at specific times. With task scheduling, agents can operate in the background—gathering information, performing analysis, and delivering results—without your ongoing involvement.

    Some tasks require regular execution over time, especially those that track changeable data. For example, say you’re monitoring market sentiment for a specific stock. Instead of having to prompt Angie, the Web Search Agent, to gather updates every hour, you can now schedule her to collect that data and compile a report without manual input.

    Why is Scheduling Important?

    This is also ideal for larger, resource-intensive tasks—such as background research, document synthesis, or team workflows—that benefit from being handled asynchronously. You can stay focused on other priorities while your agents work behind the scenes.

    How Does this Work?

    The Angie Web Search Agent (available in the Agent Marketplace under Document and Content Access) now supports temporal scheduling. Simply configure a time or interval and specify what you want the agent or team to accomplish. Sentienta handles task execution and ensures you receive a detailed summary when the job is done.

    This capability isn’t limited to a single agent. You can coordinate multiple agents or entire teams to run collaboratively or in parallel on timed schedules, enabling sophisticated workflows that unfold automatically over time. It’s automation at scale—with intelligence.

    To see how this works, consider the following interaction:

    User: Schedule a task to run every 10 minutes for 6 runs. The task is to query “What is the latest AMZN quote?”

    Wed, 09 Apr 2025 17:50:10 Angie:

    Task user-schedule-clscofield997-at-gmail.com-AMZNquoteschedule is scheduled to run every 10 minutes and will stop after 6 runs.

    The agent has created a scheduled task to search for the latest Amazon.com stock quote every 10 minutes. This will run 6 time and then complete.

    You can get a list of all the scheduled tasks and their status with the following:

    User: List scheduled tasks

    Wed, 09 Apr 2025 17:56:56 Angie:

    user-schedule-clscofield997-at-gmail.com-AAPLquoteschedule complete

    user-schedule-clscofield997-at-gmail.com-AMZNquoteschedule running

    user-schedule-clscofield997-at-gmail.com-NVDAquoteschedule cancelled

    Angie will list each of the tasks that have been scheduled and their status. At any time you can get the latest results from a task with:

    User: Get results for task user-schedule-clscofield997-at-gmail.com-AMZNquoteschedule

    Wed, 09 Apr 2025 18:01:05 Angie:

    Here are the current results for user-schedule-clscofield997-at-gmail.com-AMZNquoteschedule:

    Wed, 09 Apr 2025 17:50:38 Angie: As of today, Wednesday, April 9, 2025, here is the latest information on Amazon’s stock (AMZN):

    – Current Price (Last Trade): $184.14

    – Change from Previous Close: +$13.48

    – Percentage Change: +7.90%

    – Opening Price: $172.12

    – Day’s High: $186.22

    – Day’s Low: $169.93

    – Previous Close: $170.66

    Amazon’s stock has seen a strong gain today, rising nearly 8%, indicating strong investor interest or positive market news affecting the company.

    When the task has completed, Angie will take all of the intermediate results and compile a report. If there are numerical values (like stock prices), she’ll compile these into a table:

    Here is a consolidated table summarizing the key stock metrics for Amazon (AMZN) on April 9, 2025, based on the multiple time-stamped reports:

    MetricValue(s) Reported
    Current Price$187.24, $186.67, $186.68, $187.56, $187.59
    Price Change+$16.58, +$16.01, +$16.02, +$16.90, +$16.93
    Percent Change+9.72%, +9.38%, +9.39%, +9.90%, +9.92%
    Opening Price$172.12 (Consistent across all reports)
    Day’s High$187.92 (4 reports), $187.98 (latest report)
    Day’s Low$169.93 (Consistent across all reports)
    Previous Close$170.66 (Consistent across all reports)

    📝 Summary of Research Findings:

    On April 9, 2025, Amazon’s (AMZN) stock experienced a substantial surge, consistently reported as a ~9.4–9.9% increase from the previous closing price of $170.66. The opening price for the day was $172.12, and the lowest traded price was $169.93. Throughout the day, the high varied slightly between reports, peaking between $187.92 and $187.98.

    The final snapshot reported a trading price of $187.59, reflecting a daily gain of $16.93 or 9.92%. The consistency across key metrics such as opening, low, and previous close enhances confidence in these results.

    Overall, the stock showed strong upward momentum likely driven by significant investor sentiment or positive news, marking one of the most bullish single-day movements for Amazon in recent times.

    Of course Angie will also perform all the necessary task management duties too. For example, you can cancel a task at any time:

    User: Cancel task user-schedule-clscofield997-at-gmail.com-AMZNquoteschedule running

    Wed, 09 Apr 2025 18:12:55 Angie:

    The task user-schedule-clscofield997-at-gmail.com-AMZNquoteschedule will be cancelled.

    And you can delete the results from former tasks with:

    User: Delete results for task user-schedule-clscofield997-at-gmail.com-AMZNquoteschedule

    Wed, 09 Apr 2025 18:16:29 Angie:

    The task results for user-schedule-clscofield997-at-gmail.com-AMZNquoteschedule were deleted.

    Beyond Reporting: Orchestrating Workflows with Scheduled Intelligence

    Beyond data gathering, scheduled tasks can drive entire workflows—triggering follow-up actions, coordinating hand-offs between agents, or summarizing findings across time. For example, after collecting market data, a second agent might be scheduled to generate trend reports or highlight unusual activity. This kind of orchestration transforms agents from simple tools into participants in a broader, ongoing process that adapts to your needs.

    In short, Sentienta’s task scheduling unlocks a new depth of autonomy and responsiveness. By setting your agents on a timeline, you gain continuity, consistency, and clarity—without losing control. Whether you’re monitoring real-time events or streamlining internal analysis, this feature helps you keep pace with the demands of modern work through intelligent automation.

  • An AI Use-case: How will GenAI Change HR?

    We’ve already seen how individual agents and agent teams collaborate—drawing on company-specific data to solve problems and automate complex tasks. In this post, we’ll take a closer look at how these expert teams can transform the way HR operates in your organization.

    A recent study by Forrester Research (A Human-Centered Approach to AI in the Workplace) noted that 70% of people leaders “believe AI will be crucial for success in HR in the next five years” and that 73% of employees are in favor of more AI use in their companies.

    This study identified 5 use-cases that will be the drivers of AI growth in HR departments in the next 5 years, with leaders ranking these as most valuable in the following order:

    1. AI-driven career path recommendations
    2. Internal gig and job matching
    3. Conversational experience leveraging genAI
    4. Candidate matching
    5. AI-assisted development plans

    In this post we will explore how each of these use-cases can be addressed with a virtual team of agent experts. We’ll consider a Sentienta team that is managed by an HR Generalist in the organization with access to employee employment history.

    Employee-data Security

    Note that the agents on this team are managed within the Generalist’s account and employee information is not available outside of this account. That said, one should never include PII like social security numbers or other sensitive data in queries.

    Bias in AI Models

    AI models, including large language models (LLMs), reflect the biases present in the data they were trained on. In HR contexts—such as employee evaluations, communication, or support—this can lead to unintended discrimination or reinforcement of existing inequalities. These models lack awareness of context, fairness, or legality, and may produce seemingly reasonable outputs that subtly encode bias. These models should never operate autonomously in sensitive HR functions. Human oversight is essential to identify errors and ensure decisions remain fair, ethical, and comply with workplace policies.

    AI-driven career path recommendations

    To grow professionally, employees often need help navigating career paths within their organization. HR plays a vital role by understanding job roles, required skills, and employee strengths. With input from managers, HR can match employees to roles that fit their abilities and help chart a clear path for advancement.

    An HR Career Coach agent can assist the HR Generalist in mapping out an employee career development internally. With access to role descriptions, organizational charts, and examples of successful career progressions, the agent can suggest roles that align with the employee’s past experience and future goals.

    To enable this, company documents and employee information can be added to the team dialog using one of the methods described in Integrating Your Own Data into Team Dialogs.

    Internal gig and job matching

    In many mid-size and large organizations, job openings often go unnoticed by employees who could be ideal candidates. HR plays a key role in bridging this gap—matching available roles with employees ready for new challenges. By adding a Career Mobility Specialist agent to the HR team, companies can enhance this process. This agent, equipped with access to all current openings and their job descriptions (in formats like spreadsheets, documents, or PDFs), can collaborate with the HR Generalist to accelerate internal hiring and support employee growth.

    Using this job data alongside each employee”s work history, the agent can surface strong internal matches—helping fill roles efficiently while promoting career development within the company.

    Conversational experience leveraging genAI

    Both new and long-term employees need access to documents that help them understand and navigate the company effectively. These include the Employee Handbook, a company Culture deck, possibly a company org chart and for new employees a welcome packet describing tools, logins, workspace and support channels. Even long-term employees need access to HR-managed information such as their employee benefits and employment history.

    It is often difficult for employees to find what they need from these sources, and often turn to HR staff for help. Deploying a Sentienta Assistant to the company website gives employees quick access to the needed information and saves HR staff time and effort.

    Candidate matching

    One of the most recognized uses of AI in HR is talent sourcing—screening large numbers of resumes, which is both tedious and time consuming. Tools ranging from keyword filters to powerful language models now make this process much simpler.

    Like the Career Mobility Specialist agent that helps with internal moves, a Talent Matching agent can evaluate open roles by comparing them to internal job descriptions and required qualifications. What’s different is that it also reviews resumes from external applicants or integrates with sourcing agency APIs. With both agents active, companies can consider the best options from inside and outside. The agent’s reasoning is visible in the team dialog, helping the HR Generalist understand and explain placement decisions.

    AI-assisted development plans

    As noted before, employees seek help from HR to grow their careers, and we’ve seen how the HR Career Coach can design a career path that makes sense given the structure of the organization and the skills and aspirations of the employee. However, an important part of this path is the mastery of new skills and experience in roles that are essential for a career’s next level.

    A Career Growth Advisor agent works with the Career Coach and the employee’s work history to determine the current skill level and gaps that must be filled in order to take the next step. This agent creates personalized and contextual development plans that support job mastery, skill building, and long-term career goals. By aligning currently-available learning opportunities with real-time performance and aspirations, employees can take ownership of their growth and thrive in their careers.

    Final Thoughts

    This post explored how expert agents, when supported by rich company data, can bring to life the five HR use-cases identified by Forrester. From streamlining onboarding to improving talent sourcing and internal mobility, these applications show the real potential of automation in reshaping HR operations.

    Forrester research also highlights employee excitement about AI’s growing presence in HR—especially its ability to reduce wait times for answers, simplify decision-making, and provide personalized support. When implemented thoughtfully, AI-powered tools don’t just create efficiencies for HR staff—they also foster a more self-sufficient and empowered workforce.

    As adoption accelerates, organizations have the opportunity to rethink how decisions are made, how careers are built, and how information is shared—making HR a more responsive, data-driven partner for every employee.

  • Adding Real-time Data to Your Agent Dialogs

    One of the biggest challenges with LLMs is their limited access to new information. These massive models take months to train, followed by additional months of testing and refining safeguards to protect users from harmful content and unauthorized queries. However, for LLM-based agents to truly be effective, they must have access to the most up-to-date data.

    I’ve been exploring Sentienta’s latest real-time search agent, ‘Angie,’ available in the Agent Marketplace under the ‘Document and Content Access’ section. Angie offers unique capabilities, including real-time news searches, detailed financial report summaries—covering SEC filings, stock news, sentiment analysis, and price history—and the ability to summarize content from open web pages.

    Sentienta’s Angie agent offers these capabilities without the need for coding or integration, unlike OpenAI and Google’s Gemini platforms. It provides a no-code solution for seamlessly incorporating real-time data into team discussions.

    Under the covers, this agent makes use of an integrated tool suite, intelligently selecting the best tool for the task. For content searches there are tools that directly integrate third-party APIs. This ensures that you don’t have to manage API keys and subscriptions. Instead you get the most up-to-date content when you need it. It just works.

    Here are some examples of how you can use Angie in your teams. Suppose you are interested in the latest SEC filings on Uber. I can’t reproduce the full result here, but here is an abbreviated transcript:

    Me: Angie get the latest sec filings for Uber

    Thu, 20 Mar 2025 17:59:26 Angie:

    I will get a report on UBER, from document 10-K

    Thu, 20 Mar 2025 17:59:27 Angie:

    This document has 142 pages.

    Thu, 20 Mar 2025 18:00:25 Angie:

    The document is a 10-K annual report filed by Uber Technologies, Inc. with the SEC for the fiscal year ending December 31, 2024. It contains comprehensive financial and operational details about the company and its activities.

    … (multiple pages of analysis)

    The document also discusses market risks, including interest rate risk, investment risk, and foreign currency risk. It details the company’s investment policies aimed at capital preservation and mitigating risks associated with investments in publicly traded and privately held entities. Foreign currency fluctuations pose a risk to international revenues and expenses, partially offset by incurring expenses in the same foreign currencies. The company uses derivative contracts to manage currency risks but acknowledges that these measures cannot fully eliminate exposure.

    After reading this summary of the 10-K, perhaps you’d like to see the latest news on Uber:

    Me: Angie what is the latest news on Uber?

    Thu, 20 Mar 2025 18:45:29 Angie:

    Here is the best possible answer based on the search results for the latest news on Uber as of Thursday, March 20, 2025:

    Uber Technologies (NYSE: UBER) has been performing strongly in 2025, with its stock up 31.55% year-to-date. Analysts have set a consensus price target of $90.7, indicating a potential 14.16% upside. Uber has also announced a $1.5 billion accelerated share repurchase program as part of its broader $7.0 billion repurchase authorization, showing confidence in its financial position. Additionally, for Q1 2025, Uber expects bookings to grow between 17%-21%, indicating robust operational performance going forward.

    [5 supporting links]

    With that in hand, perhaps you’d like to see the latest closing price for this stock:

    Me: Show me the latest closing price for Uber’s stock

    Thu, 20 Mar 2025 18:53:16 Angie:

    As of the most recent data refresh on March 19, 2025, at 19:55 EST, Uber Technologies Inc. (UBER) had the following stock performance:

    • – Last traded price (close): $73.39
    • – Opening price: $73.345
    • – Daily high: $73.39
    • – Daily low: $73.3001
    • – Trading volume: 5,430 shares

    This data is based on intraday trading with 5-minute intervals. If you need more details such as historical trends or analyst insights, please let me know!

    There are of course, many ways to access this data, including a series of Google searches. However, Angie automatically integrates it into your team’s dialog, making it readily available to other agents. My team included a Research Lead, ‘Roger,’ who analyzed Angie’s results. Below is a brief transcript of Roger’s suggested next steps.

    Me: Roger – please summarize what we’ve learned about Uber. Is this a good investment?

    Thu, 20 Mar 2025 18:57:06 Roger:

    Uber has gained 31.55% year-to-date, with analysts targeting $90.7, indicating a 14.16% potential upside. A $1.5 billion share repurchase suggests financial confidence, and 17%-21% bookings growth signals strong operations. The latest closing price was $73.39 as of March 19, 2025. While the outlook appears positive, further analysis of risks, competition, and market conditions is recommended before making an investment decision.

    Me: What does this data tell you about risks?

    Thu, 20 Mar 2025 18:58:43 Roger:

    Uber’s strong year-to-date growth and share repurchase suggest confidence, but risks remain. Potential concerns include market volatility, regulatory challenges, competition from Lyft and autonomous vehicle companies, and macroeconomic factors affecting ride demand. Further analysis of revenue stability and profitability trends is necessary.

    By exploring competitive trends and regulatory changes, I gained additional insights, too many to show here. This demonstrates the power of Angie as a research assistant and the strength of a team that can analyze data to highlight what truly matters. In a future post, I’ll showcase how the Research Lead delegates research tasks to Angie and compiles an investment opportunities report—without writing a single line of code.

  • Scaling Your Business

    Starting a company is challenging. There is so much to think about. If you are a software developer and you and your friends have a cool idea, you can build a product pretty easily with today’s tools (especially now with generative AI).

    But as anyone who has tried this knows, there is so much more to building a company than just building the product. It’s rarely the case that ‘if you build it they will come.’ It’s up to you to tell your potential customers about who you are and why your product is worth their attention.

    Some years ago I worked for a small company that built neural network solutions for businesses. We did a lot of different things: character recognition for form processing, fraud detection for credit cards and mortgage insurance, even an early ANPR system.

    When we wanted to introduce a new product we had to farm-out the work to an ad agency. Their folks would come in and interview us, talk about the product and then go away to develop a concept for the promotional material. This took a lot of time, and often there were several iterations.

    Startup founders today don’t have the luxury of time for that approach. However, they have rich new tools that let them create and manage marketing campaigns themselves. Google offers great tools for deploying and monitoring your ‘assets’, but that misses the step that comes first: what is the campaign’s message? What narrative will I use to create the message? What visuals should I create and how do I create them?

    With Sentienta you can create a team of marketing experts to help you answer these questions. The Agent Marketplace has pre-built agents to help you think about your messaging, create content to describe your product and why it’s important to your intended customers. There are agents to create visuals, both images and video, and even an agent to help you select the right social media channel.

    Creating a virtual marketing team can help you scale your business without adding a whole new team of people. A Sentienta marketing team can help you develop the assets you need to use powerful deployment tools like Google Ads.