This principle was instrumental in shaping our data-focused enterprise architecture transformation in 2023, making data a core pillar alongside loan origination and servicing. Given that the company’s future growth depends on it, the focus on data was essential.
Dr. Johnathan Flowers of American University recently sparked a conversation on Bluesky regarding a statement from the organizers of NaNoWriMo, which endorsed the use of generative AI technologies, such as LLM chatbots, in this year’s event. Dr. Flowers expressed concern about the implication that AI assistance was necessary for accessibility, arguing that it could undermine the creativity and agency of individuals with disabilities. He believes that art often serves as a unique space where barriers imposed by disability can be transcended without relying on external help or engaging in forced intimacy. For Dr. Flowers, suggesting the need for AI support may inadvertently diminish the perceived capabilities of disabled and marginalized artists. Since the announcement, NaNoWriMo organizers have revised their stance in response to criticism, though much of the social media discussion has become unproductive. In earlier discussions, the author has explored the implications of generative AI in art, focusing on the human connection that art typically fosters, which AI-generated content may not fully replicate. However, they now wish to address the role of AI as a tool for accessibility. Not being personally affected by physical disability, the author approaches this topic from a social scientific perspective. They acknowledge that the views expressed are personal and not representative of any particular community or organization. Defining AI In a recent presentation, the author offered a new definition of AI, drawing from contemporary regulatory and policy discussions: AI: The application of specific forms of machine learning to perform tasks that would otherwise require human labor. This definition is intentionally broad, encompassing not just generative AI but also other machine learning applications aimed at automating tasks. AI as an Accessibility Tool AI has potential to enhance autonomy and independence for individuals with disabilities, paralleling technological advancements seen in fields like the Paris Paralympics. However, the author is keen to explore what unique benefits AI offers and what risks might arise. Benefits Risks AI and Disability The author acknowledges that this overview touches only on some key issues related to AI and disability. It is crucial for those working in machine learning to be aware of these dynamics, striving to balance benefits with potential risks and ensuring equitable access to technological advancements. Like Related Posts Salesforce OEM AppExchange Expanding its reach beyond CRM, Salesforce.com has launched a new service called AppExchange OEM Edition, aimed at non-CRM service providers. Read more Salesforce Jigsaw Salesforce.com, a prominent figure in cloud computing, has finalized a deal to acquire Jigsaw, a wiki-style business contact database, for Read more Health Cloud Brings Healthcare Transformation Following swiftly after last week’s successful launch of Financial Services Cloud, Salesforce has announced the second installment in its series Read more Top Ten Reasons Why Tectonic Loves the Cloud The Cloud is Good for Everyone – Why Tectonic loves the cloud You don’t need to worry about tracking licenses. Read more
In the evolving world of AI, retrieval-augmented generation (RAG) systems have become standard for handling straightforward queries and generating contextually relevant responses. However, as demand grows for more sophisticated AI applications, there is a need for systems that move beyond simple retrieval tasks. Enter AI agents—autonomous entities capable of executing complex, multi-step processes, maintaining state across interactions, and dynamically adapting to new information. LangGraph, a powerful extension of the LangChain library, is designed to help developers build these advanced AI agents, enabling stateful, multi-actor applications with cyclic computation capabilities. AI Assistants Using LangGraph. In this insight, we’ll explore how LangGraph revolutionizes AI development and provide a step-by-step guide to building your own AI agent using an example that computes energy savings for solar panels. This example will demonstrate how LangGraph’s unique features enable the creation of intelligent, adaptable, and practical AI systems. What is LangGraph? LangGraph is an advanced library built on top of LangChain, designed to extend Large Language Model (LLM) applications by introducing cyclic computational capabilities. While LangChain allows for the creation of Directed Acyclic Graphs (DAGs) for linear workflows, LangGraph enhances this by enabling the addition of cycles—essential for developing agent-like behaviors. These cycles allow LLMs to continuously loop through processes, making decisions dynamically based on evolving inputs. LangGraph: Nodes, States, and Edges The core of LangGraph lies in its stateful graph structure: LangGraph redefines AI development by managing the graph structure, state, and coordination, allowing for the creation of sophisticated, multi-actor applications. With automatic state management and precise agent coordination, LangGraph facilitates innovative workflows while minimizing technical complexity. Its flexibility enables the development of high-performance applications, and its scalability ensures robust and reliable systems, even at the enterprise level. Step-by-step Guide Now that we understand LangGraph’s capabilities, let’s dive into a practical example. We’ll build an AI agent that calculates potential energy savings for solar panels based on user input. This agent can function as a lead generation tool on a solar panel seller’s website, providing personalized savings estimates based on key data like monthly electricity costs. This example highlights how LangGraph can automate complex tasks and deliver business value. Step 1: Import Necessary Libraries We start by importing the essential Python libraries and modules for the project. pythonCopy codefrom langchain_core.tools import tool from langchain_community.tools.tavily_search import TavilySearchResults from langchain_core.prompts import ChatPromptTemplate from langchain_core.runnables import Runnable from langchain_aws import ChatBedrock import boto3 from typing import Annotated from typing_extensions import TypedDict from langgraph.graph.message import AnyMessage, add_messages from langchain_core.messages import ToolMessage from langchain_core.runnables import RunnableLambda from langgraph.prebuilt import ToolNode Step 2: Define the Tool for Calculating Solar Savings Next, we define a tool to calculate potential energy savings based on the user’s monthly electricity cost. pythonCopy code@tool def compute_savings(monthly_cost: float) -> float: “”” Tool to compute the potential savings when switching to solar energy based on the user’s monthly electricity cost. Args: monthly_cost (float): The user’s current monthly electricity cost. Returns: dict: A dictionary containing: – ‘number_of_panels’: The estimated number of solar panels required. – ‘installation_cost’: The estimated installation cost. – ‘net_savings_10_years’: The net savings over 10 years after installation costs. “”” def calculate_solar_savings(monthly_cost): cost_per_kWh = 0.28 cost_per_watt = 1.50 sunlight_hours_per_day = 3.5 panel_wattage = 350 system_lifetime_years = 10 monthly_consumption_kWh = monthly_cost / cost_per_kWh daily_energy_production = monthly_consumption_kWh / 30 system_size_kW = daily_energy_production / sunlight_hours_per_day number_of_panels = system_size_kW * 1000 / panel_wattage installation_cost = system_size_kW * 1000 * cost_per_watt annual_savings = monthly_cost * 12 total_savings_10_years = annual_savings * system_lifetime_years net_savings = total_savings_10_years – installation_cost return { “number_of_panels”: round(number_of_panels), “installation_cost”: round(installation_cost, 2), “net_savings_10_years”: round(net_savings, 2) } return calculate_solar_savings(monthly_cost) Step 3: Set Up State Management and Error Handling We define utilities to manage state and handle errors during tool execution. pythonCopy codedef handle_tool_error(state) -> dict: error = state.get(“error”) tool_calls = state[“messages”][-1].tool_calls return { “messages”: [ ToolMessage( content=f”Error: {repr(error)}n please fix your mistakes.”, tool_call_id=tc[“id”], ) for tc in tool_calls ] } def create_tool_node_with_fallback(tools: list) -> dict: return ToolNode(tools).with_fallbacks( [RunnableLambda(handle_tool_error)], exception_key=”error” ) Step 4: Define the State and Assistant Class We create the state management class and the assistant responsible for interacting with users. pythonCopy codeclass State(TypedDict): messages: Annotated[list[AnyMessage], add_messages] class Assistant: def __init__(self, runnable: Runnable): self.runnable = runnable def __call__(self, state: State): while True: result = self.runnable.invoke(state) if not result.tool_calls and ( not result.content or isinstance(result.content, list) and not result.content[0].get(“text”) ): messages = state[“messages”] + [(“user”, “Respond with a real output.”)] state = {**state, “messages”: messages} else: break return {“messages”: result} Step 5: Set Up the LLM with AWS Bedrock We configure AWS Bedrock to enable advanced LLM capabilities. pythonCopy codedef get_bedrock_client(region): return boto3.client(“bedrock-runtime”, region_name=region) def create_bedrock_llm(client): return ChatBedrock(model_id=’anthropic.claude-3-sonnet-20240229-v1:0′, client=client, model_kwargs={‘temperature’: 0}, region_name=’us-east-1′) llm = create_bedrock_llm(get_bedrock_client(region=’us-east-1′)) Step 6: Define the Assistant’s Workflow We create a template and bind the tools to the assistant’s workflow. pythonCopy codeprimary_assistant_prompt = ChatPromptTemplate.from_messages( [ ( “system”, ”’You are a helpful customer support assistant for Solar Panels Belgium. Get the following information from the user: – monthly electricity cost Ask for clarification if necessary. ”’, ), (“placeholder”, “{messages}”), ] ) part_1_tools = [compute_savings] part_1_assistant_runnable = primary_assistant_prompt | llm.bind_tools(part_1_tools) Step 7: Build the Graph Structure We define nodes and edges for managing the AI assistant’s conversation flow. pythonCopy codebuilder = StateGraph(State) builder.add_node(“assistant”, Assistant(part_1_assistant_runnable)) builder.add_node(“tools”, create_tool_node_with_fallback(part_1_tools)) builder.add_edge(START, “assistant”) builder.add_conditional_edges(“assistant”, tools_condition) builder.add_edge(“tools”, “assistant”) memory = MemorySaver() graph = builder.compile(checkpointer=memory) Step 8: Running the Assistant The assistant can now be run through its graph structure to interact with users. python import uuidtutorial_questions = [ ‘hey’, ‘can you calculate my energy saving’, “my montly cost is $100, what will I save”]thread_id = str(uuid.uuid4())config = {“configurable”: {“thread_id”: thread_id}}_printed = set()for question in tutorial_questions: events = graph.stream({“messages”: (“user”, question)}, config, stream_mode=”values”) for event in events: _print_event(event, _printed) Conclusion By following these steps, you can create AI Assistants Using LangGraph to calculate solar panel savings based on user input. This tutorial demonstrates how LangGraph empowers developers to create intelligent, adaptable systems capable of handling complex tasks efficiently. Whether your application is in customer support, energy management, or other domains, LangGraph provides the Like Related Posts Salesforce OEM AppExchange Expanding its reach beyond CRM, Salesforce.com has launched
AI Agent Workflows: The Ultimate Guide to Choosing Between LangChain and LangGraph Explore two transformative libraries—LangChain and LangGraph—both created by the same developer, designed to build Agentic AI applications. This guide dives into their foundational components, differences in handling functionality, and how to choose the right tool for your use case. Language Models as the Bridge Modern language models have unlocked revolutionary ways to connect users with AI systems and enable AI-to-AI communication via natural language. Enterprises aiming to harness Agentic AI capabilities often face the pivotal question: “Which tools should we use?” For those eager to begin, this question can become a roadblock. Why LangChain and LangGraph? LangChain and LangGraph are among the leading frameworks for crafting Agentic AI applications. By understanding their core building blocks and approaches to functionality, you’ll gain clarity on how each aligns with your needs. Keep in mind that the rapid evolution of generative AI tools means today’s truths might shift tomorrow. Note: Initially, this guide intended to compare AutoGen, LangChain, and LangGraph. However, AutoGen’s upcoming 0.4 release introduces a foundational redesign. Stay tuned for insights post-launch! Understanding the Basics LangChain LangChain offers two primary methods: Key components include: LangGraph LangGraph is tailored for graph-based workflows, enabling flexibility in non-linear, conditional, or feedback-loop processes. It’s ideal for cases where LangChain’s predefined structure might not suffice. Key components include: Comparing Functionality Tool Calling Conversation History and Memory Retrieval-Augmented Generation (RAG) Parallelism and Error Handling When to Choose LangChain, LangGraph, or Both LangChain Only LangGraph Only Using LangChain + LangGraph Together Final Thoughts Whether you choose LangChain, LangGraph, or a combination, the decision depends on your project’s complexity and specific needs. By understanding their unique capabilities, you can confidently design robust Agentic AI workflows. Like Related Posts Salesforce OEM AppExchange Expanding its reach beyond CRM, Salesforce.com has launched a new service called AppExchange OEM Edition, aimed at non-CRM service providers. Read more The Salesforce Story In Marc Benioff’s own words How did salesforce.com grow from a start up in a rented apartment into the world’s Read more Salesforce Jigsaw Salesforce.com, a prominent figure in cloud computing, has finalized a deal to acquire Jigsaw, a wiki-style business contact database, for Read more Health Cloud Brings Healthcare Transformation Following swiftly after last week’s successful launch of Financial Services Cloud, Salesforce has announced the second installment in its series Read more
Zendesk Launches AI Agent Builder and Enhances Agent Copilot Zendesk has unveiled its AI Agent Builder, a key feature in a series of significant updates across its platform. This new tool enables customer service teams to create bots—now referred to as “AI Agents”—using natural language descriptions. For example, a user might input: “A customer wants to return a product.” The AI Agent Builder will recognize the scenario and automatically create a framework for the AI Agent, which can then be reviewed, tested, and deployed. This framework might include essential steps like checking the order number, verifying the items for return, and cross-referencing the return policy. Matthias Goehler, CTO for EMEA at Zendesk, explains, “You can define any number of workflows in the same straightforward manner. The best part is that business users can do this without needing to design complex flowcharts or decision trees.” However, developers may still need to consult an API when creating AI Agents that interact with multiple third-party applications. Other Enhancements to Zendesk’s AI Agents The AI Agent Builder simplifies the automation of customer interactions that involve multiple steps. For more straightforward queries, Zendesk can connect a single AI Agent to trusted knowledge sources, allowing it to autonomously provide answers. Recently, the vendor has expanded this capability to email and strengthened its partnership with Poly.AI to integrate conversational AI capabilities into the voice channel. Goehler remarked, “When I first heard a Poly bot, I thought it was a human; it even had subtle dialects and varied pacing.” This natural-sounding voice, combined with real-time data processing, enables the bot to understand customer intent and guide them through various processes. Zendesk aims to help customers automate up to 80 percent of their service inquiries. However, Goehler acknowledges that some situations will always require human intervention, whether due to case complexity or customer preferences. Therefore, the company continues to enhance its Agent Copilot, which now includes several new features. The “Enhanced” Zendesk Agent Copilot One of the most exciting new features in Agent Copilot is its “Procedure” capability. This allows contact centers to define specific procedures for the Copilot to execute on behalf of live agents. Users can specify these procedures in natural language, such as: “Do this first, then this, and finally this.” During live interactions, agents can request the Copilot to carry out tasks like scheduling appointments or sending shipping labels. The Copilot can also proactively suggest procedures, share recommended responses, and offer guidance through its new “auto-assist” mode. While the live agent remains in control, they can approve the Copilot’s suggestions, allowing it to handle much of the workload. Goehler noted, “If the agent wants to adjust something, they can do that, too. The AI continues to suggest steps and solutions.” This feature is particularly beneficial for companies facing high staff turnover, as it allows new agents to quickly adapt with consistent, high-quality guidance. Zendesk has also introduced Agent Copilot for Voice, making many of its capabilities accessible during customer calls. Agents will receive live call insights and relevant knowledge base content to enhance their interactions. Elsewhere at Zendesk 2024 has been a transformative year for Zendesk. The company has entered the workforce engagement management (WEM) market with acquisitions of Klaus and Tymeshift. This follows the integration of Ultimate, which laid the groundwork for the new Zendesk AI Agents and significantly enhanced the vendor’s conversational AI expertise. Additionally, Zendesk has developed a customer messaging app in collaboration with Meta, established a venture arm for AI startups, and announced new partnerships with AWS and Anthropic. Notably, Zendesk has gained attention for introducing an “industry-first” outcome-based pricing model. This move is significant as many CCaaS and CRM vendors, facing pressure from AI solutions that reduce headcounts, have traditionally relied on seat-based pricing models. By adopting outcome-based pricing, Zendesk ensures that customers only pay more when they achieve desired outcomes, addressing a key challenge in the industry. Like Related Posts Salesforce OEM AppExchange Expanding its reach beyond CRM, Salesforce.com has launched a new service called AppExchange OEM Edition, aimed at non-CRM service providers. Read more The Salesforce Story In Marc Benioff’s own words How did salesforce.com grow from a start up in a rented apartment into the world’s Read more Salesforce Jigsaw Salesforce.com, a prominent figure in cloud computing, has finalized a deal to acquire Jigsaw, a wiki-style business contact database, for Read more Health Cloud Brings Healthcare Transformation Following swiftly after last week’s successful launch of Financial Services Cloud, Salesforce has announced the second installment in its series Read more
Tectonic’s Expertise in Salesforce Nonprofit Cloud: Transforming Fundraising for Nonprofits Salesforce’s Nonprofit Cloud (NPC) is revolutionizing how organizations manage their fundraising, offering tools specifically designed to meet the unique needs of the nonprofit sector. A standout feature of Nonprofit Cloud is its comprehensive fundraising functionality, which goes beyond simple transaction management to support the entire lifecycle of donor engagement. Central to understanding this functionality is the “three P’s” concept—Pursuit, Promise, and Payment. These three stages enable nonprofits to effectively track and manage donor relationships and contributions. Pursuit: Tracking the Opportunity The first “P” in Salesforce’s Nonprofit Cloud Fundraising process is Pursuit. This refers to the opportunity record, where the organization is actively seeking donations but no financial transaction has occurred yet. For example, a nonprofit might be pursuing a major donation of $500,000 from a corporate sponsor. At this stage, fundraisers track their progress through various phases of the opportunity, whether they win or lose the donation bid. The focus here is on relationship-building and securing commitments rather than managing financial transactions. This early-stage tracking lays the foundation for a more organized approach as the process advances. Promise: Earninging the Commitment Once a donor—whether an individual or a corporation—has committed to contributing, the Promise phase begins. Here, the Opportunity record transforms into a Gift Commitment in Salesforce. For instance, when the company officially pledges the $500,000 donation, this formalizes their promise. The Gift Commitment record is dynamic and can be modified over time to reflect changes, such as adjusting the amount to $400,000 or setting up recurring donations. This flexibility enables nonprofits to track pledges over time and maintain accurate records of what has been promised versus what has been received. Financial teams especially benefit from this capability, as it aids in reporting and financial planning. Payment: Completing the Financial Act The final “P” is Payment, capturing the financial transaction. This is where the Gift Transaction record comes into play, reflecting the completion of the financial act. For example, once the company has paid $250,000 of the promised $400,000, the Payment record updates to reflect this. Payment records can either stand alone for one-time donations or be linked to Gift Commitments or a Gift Commitment Schedule for installment payments or recurring donations. This structure gives nonprofits the flexibility to track all stages of financial fulfillment and adjust their fundraising strategies accordingly. Leveraging the Three P’s for Success The Pursuit, Promise, and Payment framework provides nonprofits with a clear, structured approach to managing the entire donor lifecycle. This system also eases the transition from Salesforce’s legacy Nonprofit Success Pack (NPSP) to the new Nonprofit Cloud framework. By effectively tracking donation pursuits, managing gift commitments, and documenting payments, nonprofits can maintain a comprehensive, real-time view of their fundraising efforts. This streamlined process not only improves data management but also enhances transparency, fostering trust with donors. The Future of Fundraising with Salesforce Nonprofit Cloud Salesforce’s Nonprofit Cloud Fundraising functionality, anchored by the three P’s, represents a significant evolution in nonprofit technology. By offering tools that manage every stage of donor engagement—from pursuit to payment—Salesforce empowers nonprofits to maximize their fundraising potential. Organizations can cultivate stronger donor relationships, track commitments more accurately, and ensure financial transactions are completed and documented efficiently. This holistic approach enables nonprofits to make informed decisions, boost donor trust, and drive their missions forward. Want to learn more about how Tectonic can help streamline donation processes, track total payments, maintain a full 360° history of the donation cycle, and create funder-worthy visualizations? Contact us at [email protected]. Like Related Posts Salesforce OEM AppExchange Expanding its reach beyond CRM, Salesforce.com has launched a new service called AppExchange OEM Edition, aimed at non-CRM service providers. Read more The Salesforce Story In Marc Benioff’s own words How did salesforce.com grow from a start up in a rented apartment into the world’s Read more Salesforce Jigsaw Salesforce.com, a prominent figure in cloud computing, has finalized a deal to acquire Jigsaw, a wiki-style business contact database, for Read more Health Cloud Brings Healthcare Transformation Following swiftly after last week’s successful launch of Financial Services Cloud, Salesforce has announced the second installment in its series Read more
Since OpenAI introduced its “Strawberry” AI models, something intriguing has unfolded. The o1-preview and o1-mini models have quickly gained attention for their superior step-by-step reasoning, offering a structured glimpse into problem-solving. However, behind this polished façade, a hidden layer of the AI’s mind remains off-limits—an area OpenAI is determined to keep out of reach. Unlike previous models, the o1 series conceals its raw thought processes. Users only see the refined, final answer, generated by a secondary AI, while the deeper, unfiltered reasoning is locked away. Naturally, this secrecy has only fueled curiosity. Hackers, researchers, and enthusiasts are already working to break through this barrier. Using jailbreak techniques and clever prompt manipulations, they are seeking to uncover the AI’s raw chain of thought, hoping to reveal what OpenAI has concealed. Rumors of partial breakthroughs have circulated, though nothing definitive has emerged. Meanwhile, OpenAI closely monitors these efforts, issuing warnings and threatening account bans to those who dig too deep. On platforms like X, users have reported receiving warnings merely for mentioning terms like “reasoning trace” in their interactions with the o1 models. Even casual inquiries into the AI’s thinking process seem to trigger OpenAI’s defenses. The company’s warnings are explicit: any attempt to expose the hidden reasoning violates their policies and could result in revoked access to the AI. Marco Figueroa, leader of Mozilla’s GenAI bug bounty program, publicly shared his experience after attempting to probe the model’s thought process through jailbreaks—he quickly found himself flagged by OpenAI. Now I’m on their ban list,” Figueroa revealed. So, why all the secrecy? OpenAI explained in a blog post titled Learning to Reason with LLMs that concealing the raw thought process allows for better monitoring of the AI’s decision-making without interfering with its cognitive flow. Revealing this raw data, they argue, could lead to unintended consequences, such as the model being misused to manipulate users or its internal workings being copied by competitors. OpenAI acknowledges that the raw reasoning process is valuable, and exposing it could give rivals an edge in training their own models. However, critics, such as independent AI researcher Simon Willison, have condemned this decision. Willison argues that concealing the model’s thought process is a blow to transparency. “As someone working with AI systems, I need to understand how my prompts are being processed,” he wrote. “Hiding this feels like a step backward.” Ultimately, OpenAI’s decision to keep the AI’s raw thought process hidden is about more than just user safety—it’s about control. By retaining access to these concealed layers, OpenAI maintains its lead in the competitive AI race. Yet, in doing so, they’ve sparked a hunt. Researchers, hackers, and enthusiasts continue to search for what remains hidden. And until that veil is lifted, the pursuit won’t stop. Like Related Posts Salesforce OEM AppExchange Expanding its reach beyond CRM, Salesforce.com has launched a new service called AppExchange OEM Edition, aimed at non-CRM service providers. Read more Salesforce Jigsaw Salesforce.com, a prominent figure in cloud computing, has finalized a deal to acquire Jigsaw, a wiki-style business contact database, for Read more Health Cloud Brings Healthcare Transformation Following swiftly after last week’s successful launch of Financial Services Cloud, Salesforce has announced the second installment in its series Read more Top Ten Reasons Why Tectonic Loves the Cloud The Cloud is Good for Everyone – Why Tectonic loves the cloud You don’t need to worry about tracking licenses. Read more
Exploring Emerging LLM Agent Types and Architectures The Evolution Beyond ReAct AgentsThe shortcomings of first-generation ReAct agents have paved the way for a new era of LLM agents, bringing innovative architectures and possibilities. In 2024, agents have taken center stage in the AI landscape. Companies globally are developing chatbot agents, tools like MultiOn are bridging agents to external websites, and frameworks like LangGraph and LlamaIndex Workflows are helping developers build more structured, capable agents. However, despite their rising popularity within the AI community, agents are yet to see widespread adoption among consumers or enterprises. This leaves businesses wondering: How do we navigate these emerging frameworks and architectures? Which tools should we leverage for our next application? Having recently developed a sophisticated agent as a product copilot, we share key insights to guide you through the evolving agent ecosystem. What Are LLM-Based Agents? At their core, LLM-based agents are software systems designed to execute complex tasks by chaining together multiple processing steps, including LLM calls. These agents: The Rise and Fall of ReAct Agents ReAct (reason, act) agents marked the first wave of LLM-powered tools. Promising broad functionality through abstraction, they fell short due to their limited utility and overgeneralized design. These challenges spurred the emergence of second-generation agents, emphasizing structure and specificity. The Second Generation: Structured, Scalable Agents Modern agents are defined by smaller solution spaces, offering narrower but more reliable capabilities. Instead of open-ended design, these agents map out defined paths for actions, improving precision and performance. Key characteristics of second-gen agents include: Common Agent Architectures Agent Development Frameworks Several frameworks are now available to simplify and streamline agent development: While frameworks can impose best practices and tooling, they may introduce limitations for highly complex applications. Many developers still prefer code-driven solutions for greater control. Should You Build an Agent? Before investing in agent development, consider these criteria: If you answered “yes,” an agent may be a suitable choice. Challenges and Solutions in Agent Development Common Issues: Strategies to Address Challenges: Conclusion The generative AI landscape is brimming with new frameworks and fervent innovation. Before diving into development, evaluate your application needs and consider whether agent frameworks align with your objectives. By thoughtfully assessing the tools and architectures available, you can create agents that deliver measurable value while avoiding unnecessary complexity. Like Related Posts Salesforce OEM AppExchange Expanding its reach beyond CRM, Salesforce.com has launched a new service called AppExchange OEM Edition, aimed at non-CRM service providers. Read more The Salesforce Story In Marc Benioff’s own words How did salesforce.com grow from a start up in a rented apartment into the world’s Read more Salesforce Jigsaw Salesforce.com, a prominent figure in cloud computing, has finalized a deal to acquire Jigsaw, a wiki-style business contact database, for Read more Health Cloud Brings Healthcare Transformation Following swiftly after last week’s successful launch of Financial Services Cloud, Salesforce has announced the second installment in its series Read more
For as long as machines have existed, humans have struggled to communicate effectively with them. The rise of large language models (LLMs) has transformed this dynamic, making “prompting” the bridge between our intentions and AI’s actions. By providing pre-trained models with clear instructions and context, we can ensure they understand and respond correctly. As UX practitioners, we now play a key role in facilitating this interaction, helping humans and machines truly connect. The UX discipline was born alongside graphical user interfaces (GUIs), offering a way for the average person to interact with computers without needing to write code. We introduced familiar concepts like desktops, trash cans, and save icons to align with users’ mental models, while complex code ran behind the scenes. Now, with the power of AI and the transformer architecture, a new form of interaction has emerged—natural language communication. This shift has changed the design landscape, moving us from pure graphical interfaces to an era where text-based interactions dominate. As designers, we must reconsider where our focus should lie in this evolving environment. A Mental Shift In the era of command-based design, we focused on breaking down complex user problems, mapping out customer journeys, and creating deterministic flows. Now, with AI at the forefront, our challenge is to provide models with the right context for optimal output and refine the responses through iteration. Shifting Complexity to the Edges Successful communication, whether with a person or a machine, hinges on context. Just as you would clearly explain your needs to a salesperson to get the right product, AI models also need clear instructions. Expecting users to input all the necessary information in their prompts won’t lead to widespread adoption of these models. Here, UX practitioners play a critical role. We can design user experiences that integrate context—some visible to users, others hidden—shaping how AI interacts with them. This ensures that users can seamlessly communicate with machines without the burden of detailed, manual prompts. The Craft of Prompting As designers, our role in crafting prompts falls into three main areas: Even if your team isn’t building custom models, there’s still plenty of work to be done. You can help select pre-trained models that align with user goals and design a seamless experience around them. Understanding the Context Window A key concept for UX designers to understand is the “context window“—the information a model can process to generate an output. Think of it as the amount of memory the model retains during a conversation. Companies can use this to include hidden prompts, helping guide AI responses to align with brand values and user intent. Context windows are measured in tokens, not time, so even if you return to a conversation weeks later, the model remembers previous interactions, provided they fit within the token limit. With innovations like Gemini’s 2-million-token context window, AI models are moving toward infinite memory, which will bring new design challenges for UX practitioners. How to Approach Prompting Prompting is an iterative process where you craft an instruction, test it with the model, and refine it based on the results. Some effective techniques include: Depending on the scenario, you’ll either use direct, simple prompts (for user-facing interactions) or broader, more structured system prompts (for behind-the-scenes guidance). Get Organized As prompting becomes more common, teams need a unified approach to avoid conflicting instructions. Proper documentation on system prompting is crucial, especially in larger teams. This helps prevent errors and hallucinations in model responses. Prompt experimentation may reveal limitations in AI models, and there are several ways to address these: Looking Ahead The UX landscape is evolving rapidly. Many organizations, particularly smaller ones, have yet to realize the importance of UX in AI prompting. Others may not allocate enough resources, underestimating the complexity and importance of UX in shaping AI interactions. As John Culkin said, “We shape our tools, and thereafter, our tools shape us.” The responsibility of integrating UX into AI development goes beyond just individual organizations—it’s shaping the future of human-computer interaction. This is a pivotal moment for UX, and how we adapt will define the next generation of design. Content updated October 2024. Like Related Posts Salesforce OEM AppExchange Expanding its reach beyond CRM, Salesforce.com has launched a new service called AppExchange OEM Edition, aimed at non-CRM service providers. Read more Salesforce Jigsaw Salesforce.com, a prominent figure in cloud computing, has finalized a deal to acquire Jigsaw, a wiki-style business contact database, for Read more Health Cloud Brings Healthcare Transformation Following swiftly after last week’s successful launch of Financial Services Cloud, Salesforce has announced the second installment in its series Read more Top Ten Reasons Why Tectonic Loves the Cloud The Cloud is Good for Everyone – Why Tectonic loves the cloud You don’t need to worry about tracking licenses. Read more
