- gettectonic.com

21Jul

Salesforce and Inforge

Salesforce’s Influence and the Emergence of Inforge in MiamiTech Salesforce is a cornerstone of customer relationship management (CRM) for over 150,000 businesses globally, generating billions in annual revenue and playing a vital role in streamlining operations and enhancing customer satisfaction. The Challenge with Salesforce Despite its powerful capabilities, Salesforce can be complex, and finding skilled talent to manage this robust CRM system is often challenging. However, Miami startups now have a solution thanks to Inforge, a firm founded by three prominent figures in the #MiamiTech community. Inforge’s Founding and Mission Inforge, established by Javier Ramirez in September 2020, bridges the gap by connecting Salesforce talent from Latin America with businesses in the United States. Ramirez, who began as a freelance Salesforce developer on Upwork, quickly made a name for himself by exceeding client expectations. Seeing the increasing demand for Salesforce expertise, he built a team of skilled developers from LatAm, focusing on delivering innovative solutions across various industries. Leadership and Vision Joining Ramirez are Felipe Sommer and Alan Bebchik, each bringing substantial experience and expertise. Sommer, co-founder of the Miami EdTech giant Nearpod and an investor or advisor for numerous startups, expressed his excitement for Inforge’s mission. Bebchik, with a background at tech giants like Google and Uber, highlighted Miami’s thriving tech ecosystem as a significant advantage for Inforge’s growth and access to the American market. Nurturing Talent with “La Masia” Inforge not only focuses on strategic location and client satisfaction but also on nurturing talent through its “La Masia” program, inspired by FC Barcelona’s renowned training academy. This initiative grooms young, talented individuals from LatAm into Salesforce consultants, offering them career opportunities while providing American businesses with top-tier services at competitive costs. Operational Approach and Clientele Inforge’s projects typically start with a discovery phase, followed by detailed solution design, incremental development, and rigorous testing before final deployment and training. The firm’s goal is to automate cumbersome manual processes, ensure data integrity, and streamline operations. Their diverse clientele includes tech companies, educational institutions, non-profits, and manufacturing firms. Future Prospects Looking ahead, Inforge’s leadership is enthusiastic about the firm’s growth and potential. Bebchik pointed out the extensive opportunities within the Salesforce ecosystem, emphasizing the company’s commitment to expansion while maintaining a strong sense of camaraderie and passion for innovation. Ramirez is particularly focused on providing his team with challenging projects to foster professional growth. Sommer, reflecting on his 20 years in Miami’s tech scene, envisions a bright future for Inforge. He believes the company will evolve into product development, identifying key market needs and creating impactful solutions. 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

July 21, 2024in Salesforce

21Jul

LLMs Turn CSVs into Knowledge Graphs

Neo4j Runway and Healthcare Knowledge Graphs Recently, Neo4j Runway was introduced as a tool to simplify the migration of relational data into graph structures. LLMs Turn CSVs into Knowledge Graphs. According to its GitHub page, “Neo4j Runway is a Python library that simplifies the process of migrating your relational data into a graph. It provides tools that abstract communication with OpenAI to run discovery on your data and generate a data model, as well as tools to generate ingestion code and load your data into a Neo4j instance.” In essence, by uploading a CSV file, the LLM identifies the nodes and relationships, automatically generating a Knowledge Graph. Knowledge Graphs in healthcare are powerful tools for organizing and analyzing complex medical data. These graphs structure information to elucidate relationships between different entities, such as diseases, treatments, patients, and healthcare providers. Applications of Knowledge Graphs in Healthcare Integration of Diverse Data Sources Knowledge graphs can integrate data from various sources such as electronic health records (EHRs), medical research papers, clinical trial results, genomic data, and patient histories. Improving Clinical Decision Support By linking symptoms, diagnoses, treatments, and outcomes, knowledge graphs can enhance clinical decision support systems (CDSS). They provide a comprehensive view of interconnected medical knowledge, potentially improving diagnostic accuracy and treatment effectiveness. Personalized Medicine Knowledge graphs enable the development of personalized treatment plans by correlating patient-specific data with broader medical knowledge. This includes understanding relationships between genetic information, disease mechanisms, and therapeutic responses, leading to more tailored healthcare interventions. Drug Discovery and Development In pharmaceutical research, knowledge graphs can accelerate drug discovery by identifying potential drug targets and understanding the biological pathways involved in diseases. Public Health and Epidemiology Knowledge graphs are useful in public health for tracking disease outbreaks, understanding epidemiological trends, and planning interventions. They integrate data from various public health databases, social media, and other sources to provide real-time insights into public health threats. Neo4j Runway Library Neo4j Runway is an open-source library created by Alex Gilmore. The GitHub repository and a blog post describe its features and capabilities. Currently, the library supports OpenAI LLM for parsing CSVs and offers the following features: The library eliminates the need to write Cypher queries manually, as the LLM handles all CSV-to-Knowledge Graph conversions. Additionally, Langchain’s GraphCypherQAChain can be used to generate Cypher queries from prompts, allowing for querying the graph without writing a single line of Cypher code. Practical Implementation in Healthcare To test Neo4j Runway in a healthcare context, a simple dataset from Kaggle (Disease Symptoms and Patient Profile Dataset) was used. This dataset includes columns such as Disease, Fever, Cough, Fatigue, Difficulty Breathing, Age, Gender, Blood Pressure, Cholesterol Level, and Outcome Variable. The goal was to provide a medical report to the LLM to get diagnostic hypotheses. Libraries and Environment Setup pythonCopy code# Install necessary packages sudo apt install python3-pydot graphviz pip install neo4j-runway # Import necessary libraries import numpy as np import pandas as pd from neo4j_runway import Discovery, GraphDataModeler, IngestionGenerator, LLM, PyIngest from IPython.display import display, Markdown, Image Load Environment Variables pythonCopy codeload_dotenv() OPENAI_API_KEY = os.getenv(‘sk-openaiapikeyhere’) NEO4J_URL = os.getenv(‘neo4j+s://your.databases.neo4j.io’) NEO4J_PASSWORD = os.getenv(‘yourneo4jpassword’) Load and Prepare Medical Data pythonCopy codedisease_df = pd.read_csv(‘/home/user/Disease_symptom.csv’) disease_df.columns = disease_df.columns.str.strip() for i in disease_df.columns: disease_df[i] = disease_df[i].astype(str) disease_df.to_csv(‘/home/user/disease_prepared.csv’, index=False) Data Description for the LLM pythonCopy codeDATA_DESCRIPTION = { ‘Disease’: ‘The name of the disease or medical condition.’, ‘Fever’: ‘Indicates whether the patient has a fever (Yes/No).’, ‘Cough’: ‘Indicates whether the patient has a cough (Yes/No).’, ‘Fatigue’: ‘Indicates whether the patient experiences fatigue (Yes/No).’, ‘Difficulty Breathing’: ‘Indicates whether the patient has difficulty breathing (Yes/No).’, ‘Age’: ‘The age of the patient in years.’, ‘Gender’: ‘The gender of the patient (Male/Female).’, ‘Blood Pressure’: ‘The blood pressure level of the patient (Normal/High).’, ‘Cholesterol Level’: ‘The cholesterol level of the patient (Normal/High).’, ‘Outcome Variable’: ‘The outcome variable indicating the result of the diagnosis or assessment for the specific disease (Positive/Negative).’ } Data Analysis and Model Creation pythonCopy codedisc = Discovery(llm=llm, user_input=DATA_DESCRIPTION, data=disease_df) disc.run() # Instantiate and create initial graph data model gdm = GraphDataModeler(llm=llm, discovery=disc) gdm.create_initial_model() gdm.current_model.visualize() Adjust Relationships pythonCopy codegdm.iterate_model(user_corrections=”’ Let’s think step by step. Please make the following updates to the data model: 1. Remove the relationships between Patient and Disease, between Patient and Symptom and between Patient and Outcome. 2. Change the Patient node into Demographics. 3. Create a relationship HAS_DEMOGRAPHICS from Disease to Demographics. 4. Create a relationship HAS_SYMPTOM from Disease to Symptom. If the Symptom value is No, remove this relationship. 5. Create a relationship HAS_LAB from Disease to HealthIndicator. 6. Create a relationship HAS_OUTCOME from Disease to Outcome. ”’) # Visualize the updated model gdm.current_model.visualize().render(‘output’, format=’png’) img = Image(‘output.png’, width=1200) display(img) Generate Cypher Code and YAML File pythonCopy code# Instantiate ingestion generator gen = IngestionGenerator(data_model=gdm.current_model, username=”neo4j”, password=’yourneo4jpasswordhere’, uri=’neo4j+s://123654888.databases.neo4j.io’, database=”neo4j”, csv_dir=”/home/user/”, csv_name=”disease_prepared.csv”) # Create ingestion YAML pyingest_yaml = gen.generate_pyingest_yaml_string() gen.generate_pyingest_yaml_file(file_name=”disease_prepared”) # Load data into Neo4j instance PyIngest(yaml_string=pyingest_yaml, dataframe=disease_df) Querying the Graph Database cypherCopy codeMATCH (n) WHERE n:Demographics OR n:Disease OR n:Symptom OR n:Outcome OR n:HealthIndicator OPTIONAL MATCH (n)-[r]->(m) RETURN n, r, m Visualizing Specific Nodes and Relationships cypherCopy codeMATCH (n:Disease {name: ‘Diabetes’}) WHERE n:Demographics OR n:Disease OR n:Symptom OR n:Outcome OR n:HealthIndicator OPTIONAL MATCH (n)-[r]->(m) RETURN n, r, m MATCH (d:Disease) MATCH (d)-[r:HAS_LAB]->(l) MATCH (d)-[r2:HAS_OUTCOME]->(o) WHERE l.bloodPressure = ‘High’ AND o.result=’Positive’ RETURN d, properties(d) AS disease_properties, r, properties(r) AS relationship_properties, l, properties(l) AS lab_properties Automated Cypher Query Generation with Gemini-1.5-Flash To automatically generate a Cypher query via Langchain (GraphCypherQAChain) and retrieve possible diseases based on a patient’s symptoms and health indicators, the following setup was used: Initialize Vertex AI pythonCopy codeimport warnings import json from langchain_community.graphs import Neo4jGraph with warnings.catch_warnings(): warnings.simplefilter(‘ignore’) NEO4J_USERNAME = “neo4j” NEO4J_DATABASE = ‘neo4j’ NEO4J_URI = ‘neo4j+s://1236547.databases.neo4j.io’ NEO4J_PASSWORD = ‘yourneo4jdatabasepasswordhere’ # Get the Knowledge Graph from the instance and the schema kg = Neo4jGraph( url=NEO4J_URI, username=NEO4J_USERNAME, password=NEO4J_PASSWORD, database=NEO4J_DATABASE ) kg.refresh_schema() print(textwrap.fill(kg.schema, 60)) schema = kg.schema Initialize Vertex AI pythonCopy codefrom langchain.prompts.prompt import PromptTemplate from langchain.chains import GraphCypherQAChain from langchain.llms import VertexAI vertexai.init(project=”your-project”, location=”us-west4″) llm = VertexAI(model=”gemini-1.5-flash”) Create the Prompt Template pythonCopy codeprompt_template = “”” Let’s think step by

July 21, 2024in Generative AI

21Jul

Advanced RAG

Significant Changes in Context Windows and Token Costs The first significant change in the AI world is the substantial increase in the context window size and the decrease in token costs. For example, the context window size of the largest model, Claude from Anthropic, exceeds 200,000 tokens. According to the latest news, Gemini’s context window can reach up to 10 million tokens. Under these conditions, Retrieval-Augmented Generation (RAG) may not be required for many tasks, as all necessary data can fit into the context window. This shift has been observed in several financial and analytical projects where tasks were completely solved without using a vector database as intermediate storage. The trend of reducing token costs and increasing context window sizes is likely to continue, diminishing the need for external mechanisms for large language models (LLMs). However, they remain necessary for the time being. Advanced RAG. If the context size is still insufficient, different methods of summarization and context compression have been devised. LangChain has introduced a class aimed at this: ConversationSummaryMemory. pythonCopy codellm = OpenAI(temperature=0) conversation_with_summary = ConversationChain( llm=llm, memory=ConversationSummaryMemory(llm=OpenAI()), verbose=True ) conversation_with_summary.predict(input=”Hi, what’s up?”) Knowledge Graphs As the amount of data LLMs must navigate grows, the ability to navigate this data becomes increasingly important. Without the ability to analyze the data structure and other attributes, it’s impossible to use them effectively. For example, suppose the data source is a company’s wiki with a page containing the company’s phone number, but this isn’t explicitly indicated anywhere. How does the LLM understand that this is the company’s phone number? It doesn’t, which is why standard RAG won’t provide any information about the company’s phone number (as it sees no connection). A person can understand that this is the company’s phone number from the convention of how the data is stored (i.e., from the structure or metadata). For LLMs, this problem is solved with Knowledge Graphs with metadata (also known as Knowledge Maps), which means the LLM has not only the raw data but also information about the storage structure and the connections between different data entities. This approach is also known as Graph Retrieval-Augmented Generation (GraphRAG). Graphs are excellent for representing and storing heterogeneous and interconnected information in a structured form, easily capturing complex relationships and attributes among different types of data, which vector databases struggle with. Example of a Knowledge Graph Creating a Knowledge Graph typically involves collecting and structuring data, requiring a deep understanding of both the subject area and graph modeling. This process can largely be automated with LLMs. Thanks to their understanding of language and context, LLMs can automate significant parts of the Knowledge Graph creation process. By analyzing textual data, these models can identify entities, understand their relationships, and suggest how best to represent them in a graph structure. Advanced RAG This ensemble of a vector database and a knowledge graph generally improves accuracy and often includes a search through a regular database or by keywords (e.g., Elasticsearch). Knowledge Graph Retriever Example For example, a user asks a question about the company’s phone number. If this is done in code, the entities from the question can be formatted in JSON or using with_structured_output from LangChain. These entities are then searched for in the Knowledge Graph. How this is done depends on where the graph is stored. pythonCopy codedocuments = parse_and_load_data_from_wiki_including_metadata() graph_store = NebulaGraphStore( space_name=”Company Wiki”, tags=[“entity”] ) storage_context = StorageContext.from_defaults(graph_store=graph_store) index = KnowledgeGraphIndex.from_documents( documents, max_triplets_per_chunk=2, space_name=”Company Wiki”, tags=[“entity”] ) query_engine = index.as_query_engine() response = query_engine.query(“Tell me more about our Company”) The search differs from a vector database search in that it searches for attributes and related entities, not similar vectors. Returning to the initial question, if the wiki structure was transferred to the graph correctly, the company’s phone number would be added as a related entity in the graph. The data from the graph and the vector database search are then passed to the LLM to generate a complete answer. Challenges and Solutions Access Control Access to data may not be uniform. In the same wiki, there may be roles and permissions, and not every user can see all information. This problem exists for both graph and vector database searches, requiring access management. Role-Based Access Control (RBAC), Attribute-Based Access Control (ABAC), and Relationship-Based Access Control (ReBAC) are common methods. Permissions and categories are also forms of metadata, which must be preserved at the data ingestion stage in the knowledge graph and vector database. When searching in the vector database, it is necessary to check whether the role or other access attributes match what the user has access to. Some commercial vector databases already include this functionality. Data embedded in the LLM during training relies on the LLM’s reasonableness, which is not recommended. Ingestion and Parsing Data needs to be inserted into the graph and the vector database. For the graph, the format is critical as it reflects the data structure and serves as metadata. Parsing data, especially from PDFs, can be challenging. Frameworks like LLama Parse attempt this with varying degrees of success. However, OCR or recognizing a document image can sometimes be easier. Improving Answer Advanced RAG Several approaches aim to improve answer quality beyond using knowledge graphs: Corrective Retrieval Augmented Generation (CRAG) CRAG addresses incorrect RAG results by automating correction processes. LangGraph can implement this approach, which essentially forms a state machine. Self-RAG Self-reflective RAG fine-tunes the LLM to generate self-reflection tokens in addition to regular ones, helping build a state machine for better results. HyDe HyDe (Hypothetical Document Embeddings) modifies the usual RAG retrieval process by using the LLM to generate a response and then searching the vector database with that response. This is useful when users’ questions are too abstract and require more context. These methods, including CRAG, Self-RAG, and HyDe, provide various ways to enhance the performance of LLMs and improve the quality of their answers. 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

July 21, 2024in Salesforce

20Jul

Salesforce Research Produces INDICT

Automating and assisting in coding holds tremendous promise for speeding up and enhancing software development. Yet, ensuring that these advancements yield secure and effective code presents a significant challenge. Balancing functionality with safety is crucial, especially given the potential risks associated with malicious exploitation of generated code. Salesforce Research Produces INDICT. In practical applications, Large Language Models (LLMs) often struggle with ambiguous or adversarial instructions, sometimes leading to unintended security vulnerabilities or facilitating harmful attacks. This isn’t merely theoretical; empirical studies, such as those on GitHub’s Copilot, have revealed that a substantial portion of generated programs—about 40%—contained vulnerabilities. Addressing these risks is vital for unlocking the full potential of LLMs in coding while safeguarding against potential threats. Current strategies to mitigate these risks include fine-tuning LLMs with safety-focused datasets and implementing rule-based detectors to identify insecure code patterns. However, fine-tuning alone may not suffice against sophisticated attack prompts, and creating high-quality safety-related data can be resource-intensive. Meanwhile, rule-based systems may not cover all vulnerability scenarios, leaving gaps that could be exploited. To address these challenges, researchers at Salesforce Research have introduced the INDICT framework. INDICT employs a novel approach involving dual critics—one focused on safety and the other on helpfulness—to enhance the quality of LLM-generated code. This framework facilitates internal dialogues between the critics, leveraging external knowledge sources like code snippets and web searches to provide informed critiques and iterative feedback. INDICT operates through two key stages: preemptive and post-hoc feedback. In the preemptive stage, the safety critic assesses potential risks during code generation, while the helpfulness critic ensures alignment with task requirements. External knowledge sources enrich their evaluations. In the post-hoc stage, after code execution, both critics review outcomes to refine future outputs, ensuring continuous improvement. Evaluation of INDICT across eight diverse tasks and programming languages demonstrated substantial enhancements in both safety and helpfulness metrics. The framework achieved a remarkable 10% absolute improvement in code quality overall. For instance, in CyberSecEval-1 benchmarks, INDICT enhanced code safety by up to 30%, with over 90% of outputs deemed secure. Additionally, the helpfulness metric showed significant gains, surpassing state-of-the-art baselines by up to 70%. INDICT’s success lies in its ability to provide detailed, context-aware critiques that guide LLMs towards generating more secure and functional code. By integrating safety and helpfulness feedback, the framework sets new standards for responsible AI in coding, addressing critical concerns about functionality and security in automated software development. 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

July 20, 2024in Salesforce

20Jul

Forecasting With Foundation Models

On Hugging Face, there are 20 models tagged as “time series” at the time of writing. While this number is relatively low compared to the 125,950 results for the “text-generation-inference” tag, time series forecasting with foundation models has attracted significant interest from major companies such as Amazon, IBM, and Salesforce, which have developed their own models: Chronos, TinyTimeMixer, and Moirai, respectively. Currently, one of the most popular time series models on Hugging Face is Lag-Llama, a univariate probabilistic model developed by Kashif Rasul, Arjun Ashok, and their co-authors. Open-sourced in February 2024, the authors claim that Lag-Llama possesses strong zero-shot generalization capabilities across various datasets and domains. Once fine-tuned, they assert it becomes the best general-purpose model of its kind. In this insight, we showcase experience fine-tuning Lag-Llama and tests its capabilities against a more classical machine learning approach, specifically an XGBoost model designed for univariate time series data. Gradient boosting algorithms like XGBoost are widely regarded as the pinnacle of classical machine learning (as opposed to deep learning) and perform exceptionally well with tabular data. Therefore, it is fitting to benchmark Lag-Llama against XGBoost to determine if the foundation model lives up to its promises. The results, however, are not straightforward. The data used for this exercise is a four-year-long series of hourly wave heights off the coast of Ribadesella, a town in the Spanish region of Asturias. The data, available from the Spanish ports authority data portal, spans from June 18, 2020, to June 18, 2024. For the purposes of this study, the series is aggregated to a daily level by taking the maximum wave height recorded each day. This aggregation helps illustrate the concepts more clearly, as results become volatile with higher granularity. The target variable is the maximum height of the waves recorded each day, measured in meters. Several reasons influenced the choice of this series. First, the Lag-Llama model was trained on some weather-related data, making this type of data slightly challenging yet manageable for the model. Second, while meteorological forecasts are typically produced using numerical weather models, statistical models can complement these forecasts, especially for long-range predictions. In the era of climate change, statistical models can provide a baseline expectation and highlight deviations from typical patterns. The dataset is standard and requires minimal preprocessing, such as imputing a few missing values. After splitting the data into training, validation, and test sets, with the latter two covering five months each, the next step involves benchmarking Lag-Llama against XGBoost on two univariate forecasting tasks: point forecasting and probabilistic forecasting. Point forecasting gives a specific prediction, while probabilistic forecasting provides a confidence interval. While Lag-Llama was primarily trained for probabilistic forecasting, point forecasts are useful for illustrative purposes. Forecasts involve several considerations, such as the forecast horizon, the last observations fed into the model, and how often the model is updated. This study uses a recursive multi-step forecast without updating the model, with a step size of seven days. This means the model produces batches of seven forecasts at a time, using the latest predictions to generate the next set without retraining. Point forecasting performance is measured using Mean Absolute Error (MAE), while probabilistic forecasting is evaluated based on empirical coverage or coverage probability of 80%. The XGBoost model is defined using Skforecast, a library that facilitates the development and testing of forecasters. The ForecasterAutoreg object is created with an XGBoost regressor, and the optimal number of lags is determined through Bayesian optimization. The resulting model uses 21 lags of the target variable and various hyperparameters optimized through the search. The performance of the XGBoost forecaster is assessed through backtesting, which evaluates the model on a test set. The model’s MAE is 0.64, indicating that predictions are, on average, 64 cm off from the actual measurements. This performance is better than a simple rule-based forecast, which has an MAE of 0.84. For probabilistic forecasting, Skforecast calculates prediction intervals using bootstrapped residuals. The intervals cover 84.67% of the test set values, slightly above the target of 80%, with an interval area of 348.28. Next, the zero-shot performance of Lag-Llama is examined. Using context lengths of 32, 64, and 128 tokens, the model’s MAE ranges from 0.75 to 0.77, higher than the XGBoost forecaster’s MAE. Probabilistic forecasting with Lag-Llama shows varying coverage and interval areas, with the 128-token model achieving an 84.67% coverage and an area of 399.25, similar to XGBoost’s performance. Fine-tuning Lag-Llama involves adjusting context length and learning rate. Despite various configurations, the fine-tuned model does not significantly outperform the zero-shot model in terms of MAE or coverage. In conclusion, Lag-Llama’s performance, without training, is comparable to an optimized traditional forecaster like XGBoost. Fine-tuning does not yield substantial improvements, suggesting that more training data might be necessary. When choosing between Lag-Llama and XGBoost, factors such as ease of use, deployment, maintenance, and inference costs should be considered, with XGBoost likely having an edge in these areas. The code used in this study is publicly available on a GitHub repository for further exploration. 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

July 20, 2024in Salesforce

19Jul

What is CrowdStrike?

Global Outage Linked to CrowdStrike: What You Need to Know On Friday, a major global outage caused widespread disruptions, including flight cancellations, outages at hospitals and banks, and interruptions for broadcasters and businesses worldwide. Microsoft attributed the issue to a problem related to CrowdStrike, a cybersecurity and cloud technology firm. About CrowdStrike CrowdStrike, based in Austin, Texas, was founded in 2011 and offers a range of cybersecurity and IT tools. The company supports nearly 300 Fortune 500 firms and provides services to major companies such as Target, Salesforce, and T-Mobile. What Happened? The outage affected various public and private sectors globally, including airlines, banks, railways, and hospitals. According to CrowdStrike’s CEO, George Kurtz, the issue originated from a technical defect in a software update for Windows 10 systems, not from a cyberattack. A fix has been implemented, but some Microsoft 365 apps and services may still experience issues. Flight Disruptions Due to technical problems, American Airlines, United, and Delta requested a global ground stop for all flights on Friday morning. This led to the cancellation of at least 540 flights in the U.S. and significant delays at major airports, including Philadelphia International Airport. Stock Market Impact The outage affected the stock prices of both Microsoft and CrowdStrike. Premarket trading saw Microsoft’s stock (MSFT) drop 2.9% to $427.70, while CrowdStrike shares (CRWD) fell nearly 19% to $279.50, according to the Wall Street Journal. Other Effects The outage impacted universities, hospitals, and various organizations that rely on Microsoft systems. Thousands of train services were canceled in the U.S. and Europe, and some broadcast stations went off air. Hospitals, including Penn and Main Line Health in Philadelphia, canceled elective procedures due to technical difficulties. Blue Screens of Death Millions of Windows 10 users encountered “blue screens of death” (BSOD), indicating a critical error with the system. This problem arose from a bug linked to a Windows update, leaving many users unable to reboot their devices. Next Steps for Users Microsoft is rolling out an update to address the bug. CrowdStrike advises affected users to monitor the company’s customer support portal for further assistance. This incident highlights the significant impact of cybersecurity and software issues on global operations, emphasizing the importance of robust IT solutions and rapid response strategies. 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

July 19, 2024in Salesforce

19Jul

Can We Customize Manufacturing Cloud For Our Business?

Yes, Salesforce Manufacturing Cloud Can Be Customized to Meet Your Business Needs Salesforce Manufacturing Cloud is designed to be highly customizable, allowing manufacturing organizations to tailor it to their unique business requirements. Whether it’s adapting the platform to fit specific workflows, integrating with third-party systems, or enhancing reporting capabilities, Salesforce provides robust customization options to meet the specific needs of manufacturers. Here are key ways Salesforce Manufacturing Cloud can be customized: 1. Custom Data Models and Objects Salesforce allows you to create custom objects and fields to track data beyond the standard model. This flexibility enables businesses to manage unique production metrics or product configurations seamlessly within the platform. Customization Options: 2. Sales Agreement Customization Sales Agreements in Salesforce Manufacturing Cloud can be tailored to reflect your business’s specific contract terms and pricing models. You can adjust agreement structures, including the customization of terms, conditions, and rebate tracking. Customization Options: 3. Custom Workflows and Automation Salesforce offers tools like Flow Builder and Process Builder, allowing manufacturers to automate routine tasks and create custom workflows that streamline operations. Customization Options: 4. Integration with Third-Party Systems Salesforce Manufacturing Cloud can integrate seamlessly with ERP systems (like SAP or Oracle), inventory management platforms, and IoT devices to ensure a smooth data flow across departments. Integration Options: 5. Custom Reports and Dashboards With Salesforce’s robust reporting tools, you can create custom reports and dashboards that provide real-time insights into key performance indicators (KPIs) relevant to your manufacturing operations. Customization Options: 6. Custom User Interfaces Salesforce Lightning allows you to customize user interfaces to meet the needs of different roles within your organization, such as production managers or sales teams. This ensures users have quick access to relevant data. Customization Options: Conclusion Salesforce Manufacturing Cloud provides a wide range of customization options to suit the unique needs of your manufacturing business. Whether it’s adjusting data models, automating processes, or integrating with external systems, Manufacturing Cloud can be tailored to meet your operational goals. By leveraging these customizations, manufacturers can optimize their operations, improve data accuracy, and gain real-time insights to boost efficiency. If you need help customizing Salesforce Manufacturing Cloud, Service Cloud, or Sales Cloud for your business, our Salesforce Manufacturing Cloud Services team is here to assist. 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

July 19, 2024in Data, Salesforce, Salesforce Einstein, Salesforce Manufacturing Cloud

19Jul

Google Wiz and Cybersecurity

Google is reportedly in advanced talks to acquire Israeli cybersecurity firm Wiz for up to $23 billion, according to The Wall Street Journal. While the sum is substantial, some have expressed surprising discontent, viewing it as “very good, but not great.” This sentiment revolves around the missed opportunity for an IPO and the loss of an Israeli giant that will no longer grow locally. Additionally, if Wiz had been registered in Israel, the transaction would have generated higher revenues for the state treasury. Google Wiz and Cybersecurity certainly aren’t hard to fathom. Founded by Assaf Rappaport, a former officer from Israel’s elite 8200 intelligence unit, Wiz has quickly risen in value. The unit has a track record of producing tech entrepreneurs, significantly contributing to Israel’s robust tech industry. The potential deal underscores the resilience of Israel’s tech sector, which accounts for about 20% of the country’s output and 15% of jobs, even as the war in Gaza pressures the economy. However, with today’s massive cyber attack inadvertently caused by a cybersecurity company, some may hesitate to make such an investment. The attack, linked to a faulty system update from CrowdStrike, a U.S. firm used by over half of Fortune 500 companies, resulted in widespread disruptions. These included grounding flights, hampering public transit systems, and affecting operations at banks and hospitals globally. CrowdStrike’s CEO, George Kurtz, apologized for the disruptions and noted that the issue had been identified and resolved. The incident, not a security breach or cyberattack, caused Microsoft Windows systems to crash, affecting public transit systems, stock exchanges, and various institutions worldwide. Google Wiz and Cybersecurity Despite this, Google’s acquisition of Wiz appears strategically sound, aiming to enhance its cloud security capabilities and position Google Cloud as a major competitor to Microsoft Azure and Amazon Web Services. The advanced technology from Wiz will help Google close the gap in the fiercely competitive cloud security market. Cybersecurity expert Chuck Brooks sees the acquisition as a game-changer, enhancing Google’s ability to conduct comprehensive threat assessments on IT infrastructure and improving DevOps processes. By integrating Wiz’s framework, Google aims to streamline development jobs and make them more secure. However, such bold mergers are not without risk. Tech advisor Vaclav Vincalek cautions that mega transactions can be dangerous for both companies, citing historical examples like Microsoft’s acquisitions of Skype and Nokia, and Google’s purchase of Motorola. Pierre Bourgeix, CEO and Founder of ESI Convergint, believes the acquisition could position Google to compete head-to-head with Amazon, especially given Microsoft Azure’s recent security breaches. Omri Weinberg, Co-Founder and CRO of DoControl, views the deal as a significant statement about the importance of cloud security. In summary, Google’s potential $23 billion acquisition of Wiz not only highlights the value of Israel’s tech talent but also represents a strategic move to enhance its cloud security capabilities. This positions Google as a major force in the cybersecurity market, with the potential to set new standards for cloud security and influence industry best practices. More on today’s outage Public transit systems in the U.S. reported impacts. The Washington Metropolitan Area Transit Authority in Washington, D.C., said its “website and some of our internal systems are currently down,” but that trains and buses were running as scheduled. In New York City, the Metropolitan Transportation Authority also said its buses and trains were unaffected but that “some MTA customer information systems are temporarily offline due to a worldwide technical outage.” Around the world, the outages disrupted London’s Stock Exchange, caused major train delays in the U.K., sent British broadcaster Sky News off air, forced medical facilities in Europe and the U.S. to cancel some services and caused disruptions at airports in Europe, Singapore, Hong Kong and India. Some U.S. border crossings saw impacts amid the outage: Traffic stalled on the Ambassador Bridge, which connects Detroit with Windsor, Ontario, Canada, as well as at the Detroit-Windsor Tunnel, the Detroit Free Press reported. CBP One, the Customs and Border Patrol app, and the agency’s border wait times website, each appeared to experience outages. On a sweeter note, Krispy Kreme is giving away free doughnuts Friday due to the global tech outage. Dubai International Airport said on X it is operating normally following “a global system outage that affected the check-in process for some airlines.” It added the affected airlines “promptly switched to an alternate system, allowing normal check-in operations to resume swiftly.” Portland, Oregon, Mayor Ted Wheeler issued an emergency declaration Friday over the tech outage, with a statement noting the outages are affecting city servers, employee computers and emergency communications. Meanwhile, the Maryland Department of Emergency Management increased its state activation level from “normal” to “partial,” citing the tech outage. A post on X says a “partial” activation is for incidents that require “significant monitoring or resources,” with additional emergency operations staffing from other agencies, functions and supporting organizations. CrowdStrike is a popular cybersecurity software company created in 2012 by CEO George Kurtz, along with Dmitri Alperovitch, and Gregg Marston. According to its website, CrowdStrike has the “world’s most advanced cloud-native platform that protects and enables the people, processes and technologies that drive modern enterprise.” According to an alert sent by CrowdStrike to its clients and reviewed by Reuters, the company’s “Falcon Sensor” software caused Microsoft Windows to crash and display a blue screen, known informally as the “Blue Screen of Death.” Kurtz said “there was an issue with a Falcon content update for Windows Hosts” but customers “remain fully protected,” according to Kurtz’s post on X. The CrowdStrike outage crashed some computers at colleges Friday and hampered a popular software for enrolling students in K-12 schools for the fall. The University of Rochester, a private school in New York, told students to keep rebooting their systems until the problem was fixed. The University of Alabama’s technology office said its campus computers using Microsoft Windows crashed. Rutgers University and the University of Kentucky also reported disruptions. State and local law enforcement agencies across the country reported disruptions to 911 services after

July 19, 2024in Salesforce

19Jul

Boost Payer Patient Education

As a pediatrician with 15 years of experience in the pediatric emergency department, Cathy Moffitt, MD, understands the critical role of patient education. Now, as Senior Vice President and Aetna Chief Medical Officer at CVS Health, she applies that knowledge to the payer space. “Education is empowerment. It’s engagement. It’s crucial for equipping patients to navigate their healthcare journey. Now, overseeing a large payer like Aetna, I still firmly believe in the power of health education,” Moffitt shared on an episode of Healthcare Strategies. At a payer organization like Aetna, patient education begins with data analytics to better understand the member population. According to Moffitt, key insights from data can help payers determine the optimal time to share educational materials with members. “People are most receptive to education when they need help in the moment,” she explained. If educational opportunities are presented when members aren’t focused on their health needs, the information is less likely to resonate. Aetna’s Next Best Action initiative, launched in 2018, embodies this timing-driven approach. In this program, Aetna employees proactively reach out to members with specific conditions to provide personalized guidance on managing their health. This often includes educational resources delivered at the right moment when members are most open to learning. Data also enables payers to tailor educational efforts to a member’s demographics, including race, sexual orientation, gender identity, ethnicity, and location. By factoring in these elements, payers can ensure their communications are relevant and easy to understand. To enhance this personalized approach, Aetna offers translation services and provides customer service training focused on sensitivity to sexual orientation and gender identity. In addition, updating the provider directory to reflect a diverse network helps members feel more comfortable with their care providers, making them more likely to engage with educational resources. “Understanding our members’ backgrounds and needs, whether it’s acute or chronic illness, allows us to engage them more effectively,” Moffitt said. “This is the foundation of our approach to leveraging data for meaningful patient education.” With over two decades in both provider and payer roles, Moffitt has observed key trends in patient education, particularly its success in mental health and preventive care. She highlighted the role of technology in these areas. Efforts to educate patients about mental health have reduced stigma and increased awareness of mental wellness. Telemedicine has significantly improved access to mental healthcare, according to Moffitt. In preventive care, more people are aware of the importance of cancer screenings, vaccines, wellness visits, and other preventive measures. Moffitt pointed to the rising use of home health visits and retail clinics as contributing factors for Aetna members. Looking ahead, Moffitt sees personalized engagement as the future of patient education. Members increasingly want information tailored to their preferences, delivered through their preferred channels—whether by email, text, phone, or other methods. Omnichannel solutions will be essential to meeting this demand, and while healthcare has already made progress, Moffitt expects even more innovation in the years to come. “I can’t predict exactly where we’ll be in 10 years, just as I couldn’t have predicted where we are now a decade ago,” Moffitt said. “But we will continue to evolve and meet the needs of our members with the technological advancements we’re committed to.” Contact Us To discover how Salesforce can advance your patient payer education, contact Tectonic today. 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

July 19, 2024in Salesforce Health and Life Sciences Solutions, Salesforce Implementation Services, Salesforce Managed Services

19Jul

Private Connectivity Between Salesforce and On-Premise Network

Salesforce is an AWS Partner and a trusted global leader in customer relationship management (CRM). Hyperforce is the next-generation Salesforce architecture, built on Amazon Web Services (AWS). Private Connectivity Between Salesforce and On-Premise Network explained. When business applications developed on Hyperforce are integrated with on-premises systems, traffic in both directions will flow over the internet. For customers in heavily regulated industries such as the public sector and financial services, programmatic access of the Salesforce APIs hosted on Hyperforce from on-premises systems is required to traverse a private connection. Conversely, accessing on-premises systems from business applications running in Hyperforce is required to use a private connection. In this insight, AWS describes how AWS Direct Connect and AWS Transit Gateway can be used in conjunction with Salesforce Private Connect to facilitate the private, bidirectional exchange of organizational data. Architectural overview How to use AWS Direct Connect to establish a dedicated, managed, and reliable connection to Hyperforce. The approach used a public virtual interface to facilitate connectivity to public Hyperforce endpoints. The approach in this insight demonstrates the use of a private or transit virtual interface to establish a dedicated, private connection to Hyperforce using Salesforce Private Connect. Approach AWS Direct Connect is set up between the on-premises network and a virtual private cloud (VPC) residing inside a customer’s AWS account to provide connectivity from the on-premises network to AWS. The exchange of data between the customer VPC and Salesforce’s transit VPC is facilitated through the Salesforce Private Connect feature, based on AWS PrivateLink technology. AWS PrivateLink allows consumers to securely access a service located in a service provider’s VPC as if it were located in the consumer’s VPC. Using Salesforce Private Connect, traffic is routed through a fully managed network connection between your Salesforce organization and your VPC instead of over the internet. The following table shows the definitions of inbound and outbound connections in the context of Salesforce Private Connect: Direction Inbound Outbound Description Traffic that flows into Salesforce Traffic that flows out of Salesforce Use cases AWS to Salesforce Salesforce to AWS On-premises network to Salesforce Salesforce to on-premises network Inbound and Outbound This pattern can only be adopted for Salesforce services supported by Salesforce Private Connect, such as Experience Cloud, Financial Services Cloud, Health Cloud, Platform Cloud, Sales Cloud, and Service Cloud. Check the latest Salesforce documentation for the specific Salesforce services that are supported. Furthermore, this architecture is only applicable to the inbound and outbound exchange of data and does not pertain to the access of the Salesforce UI. The following diagram shows the end-to-end solution of how private connectivity is facilitated bidirectionally. In this example, on-premises servers located on the 10.0.1.0/26 network are required to privately exchange data with applications running on the Hyperforce platform. Figure 1: Using AWS Direct Connect and Salesforce Private Connect to establish private, bidirectional connectivity Prerequisites for Private Connectivity Between Salesforce and On-Premise Network In order to implement this solution, the following prerequisites are required on both the Salesforce and AWS side. Salesforce Refer to Salesforce documentation for detailed requirements on migrating your Salesforce organization to Hyperforce. AWS Network flow between on-premises data center and Salesforce API The following figure shows how both inbound and outbound traffic flows through the architecture. Figure 2: Network flow between on-premises data center and Salesforce Inbound Outbound Considerations for Private Connectivity Between Salesforce and On-Premise Network Before you set up the private, bidirectional exchange of organizational data with AWS Direct Connect, AWS Transit Gateway, and Salesforce Private Connect, review these considerations. Resiliency We recommend that you set up multiple AWS Direct Connect connections to provide resilient communication paths to the AWS Region, especially if the traffic between your on-premises resources and Hyperforce is business-critical. Refer to the AWS documentation on how to achieve high and maximum resiliency for your AWS Direct Connect deployments. For inbound traffic flow, we recommend that the VPC endpoint is configured across Availability Zones for high availability. Configure customer DNS records for the Salesforce API with IP addresses associated with the VPC endpoint and implement the DNS failover or load-balancing mechanism on the customer side. For outbound traffic flow, we recommend that you configure your Network Load Balancer with two or more Availability Zones for high availability. Security For inbound traffic flow, source IP addresses used by the incoming connection are displayed in the Salesforce Private Connect inbound configuration. We recommend that these IP ranges be used in Salesforce configurations that permit the enforcement of source IP. Refer to the Salesforce documentation Restrict Access to Trusted IP Ranges for a Connected App to learn how you can use these IP ranges can to control access to the Salesforce APIs. You access Salesforce APIs using an encrypted TLS connection. AWS Direct Connect also offers a number of additional data in transit encryption options, including support for private IP VPNs over AWS Direct Connect and MAC security. An IP virtual private network (VPN) encrypts end-to-end traffic using an IPsec VPN tunnel, while MAC Security (MACsec) provides point-to-point encryption between devices. For outbound traffic flow, we recommend that you configure TLS listeners on your Network Load Balancers to ensure that traffic to the Network Load Balancer is encrypted. Cost optimization If your use case is to solely facilitate access to Salesforce, you can use a virtual private gateway and a private VIF instead to optimize deployment costs. However, if you plan to implement a hub-spoke network transit hub interconnecting multiple VPCs, we recommend the use of a transit gateway and a transit VIF for a more scalable approach. Refer to the Amazon Virtual Private Cloud Connectivity Options whitepaper and AWS Direct Connect Quotas for the pros and cons of each approach. Conclusion Salesforce and AWS continue to innovate together to provide multiple connectivity approaches to meet customer requirements. This post demonstrated how AWS Direct Connect can be used in conjunction with Salesforce Private Connect to secure end-to-end exchanges of data in industries where the use of the internet is not an option. 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

July 19, 2024in Hyperforce

19Jul

Lead Generation 101

Lead Generation 101 In today’s world, where people are bombarded with countless messages and offers daily, marketers need to find effective ways to capture attention and generate genuine interest in their products and services. According to the State of the Connected Customer report, customer preferences and expectations are the top influences on digital strategy for Chief Marketing Officers (CMOs). The ultimate goal of lead generation is to build interest over time that leads to successful sales. Here’s a comprehensive guide to understanding lead generation, the role of artificial intelligence (AI), and the steps you need to take to effectively find and nurture leads. What is Lead Generation? Lead generation is the process of creating interest in a product or service and converting that interest into a sale. By focusing on the most promising prospects, lead generation enhances the efficiency of the sales cycle, leading to better customer acquisition and higher conversion rates. Leads are typically categorized into three types: The lead generation process starts with creating awareness and interest. This can be achieved by publishing educational blog posts, engaging users on social media, and capturing leads through sign-ups for email newsletters or “gated” content such as webinars, virtual events, live chats, whitepapers, or ebooks. Once you have leads, you can use their contact information to engage them with personalized communication and targeted promotions. Effective Lead Generation Strategies To successfully move prospects from interest to buyers, focus on the following strategies: How Lead Qualification and Nurturing Work To effectively evaluate and nurture leads, consider the following: Methods for Nurturing Leads Once you’ve established your lead scoring and grading, consider these nurturing methods: Current Trends in Lead Generation AI is increasingly influencing lead generation by offering advanced tools and strategies: Measuring Success in Lead Generation To evaluate the effectiveness of your lead generation efforts, track the following key metrics: Best Practices for Lead Generation To optimize lead generation efforts and build strong customer relationships, follow these best practices: Effective lead generation is essential for building trust and fostering meaningful customer relationships. By implementing these strategies and best practices, you can enhance your lead generation efforts and drive better business results. 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

July 19, 2024in Marketing Automation

19Jul

Salesforce API Gen

Function-calling agent models, a significant advancement within large language models (LLMs), encounter challenges in requiring high-quality, diverse, and verifiable datasets. These models interpret natural language instructions to execute API calls crucial for real-time interactions with various digital services. However, existing datasets often lack comprehensive verification and diversity, resulting in inaccuracies and inefficiencies. Overcoming these challenges is critical for deploying function-calling agents reliably in real-world applications, such as retrieving stock market data or managing social media interactions. Salesforce API Gen. Current approaches to training these agents rely on static datasets that lack thorough verification, hampering adaptability and performance when encountering new or unseen APIs. For example, models trained on restaurant booking APIs may struggle with tasks like stock market data retrieval due to insufficient relevant training data. Addressing these limitations, researchers from Salesforce AI Research propose APIGen, an automated pipeline designed to generate diverse and verifiable function-calling datasets. APIGen integrates a multi-stage verification process to ensure data reliability and correctness. This innovative approach includes format checking, actual function executions, and semantic verification, rigorously verifying each data point to produce high-quality datasets. Salesforce API Gen APIGen initiates its data generation process by sampling APIs and query-answer pairs from a library, formatting them into standardized JSON format. The pipeline then progresses through a series of verification stages: format checking to validate JSON structure, function call execution to verify operational correctness, and semantic checking to align function calls, execution results, and query objectives. This meticulous process results in a comprehensive dataset comprising 60,000 entries, covering 3,673 APIs across 21 categories, accessible via Huggingface. The datasets generated by APIGen significantly enhance model performance, achieving state-of-the-art results on the Berkeley Function-Calling Benchmark. Models trained on these datasets outperform multiple GPT-4 models, demonstrating substantial improvements in accuracy and efficiency. For instance, a model with 7 billion parameters achieves an accuracy of 87.5%, surpassing previous benchmarks by a notable margin. These outcomes underscore the robustness and reliability of APIGen-generated datasets in advancing the capabilities of function-calling agents. In conclusion, APIGen presents a novel framework for generating high-quality, diverse datasets for function-calling agents, addressing critical challenges in AI research. Its multi-stage verification process ensures data reliability, empowering even smaller models to achieve competitive results. APIGen opens avenues for developing efficient and powerful language models, emphasizing the pivotal role of high-quality data in AI 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 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

July 19, 2024in Salesforce

18Jul

Verified First Expands Salesforce HR Capabilities

Expand the abilities of Salesforce as an HR platform with integrated background screening! Easily order background checks within Salesforce. With a few simple clicks, you can access Verified First’s background screening solutions, including robust background and drug screen packages, all within Salesforce. Plus, the report results are available on the Contact/Candidate page, meaning you’ll never have to leave Salesforce! Verified First Expands Salesforce HR Capabilities. So, get ready to: Verified First Expands Salesforce HR Capabilities Verified First has the only app on the Salesforce AppExchange that lets you background check and drug screen your applicants. Our seamless integration sets up in seconds and delivers the report results into Salesforce. Works seamlessly with other Salesforce apps such as Bullhorn for Salesforce, Bullhorn Jobscience, Sage, FinancialForce, and the Nonprofit Success Pack. About Verified First There are hundreds of background screening service providers to choose from, so what makes Verified First stand out? Compared to popular background screening companies, Verified First offers robust screening services with industry-leading customer care and cutting-edge technology. Unlike the big-box providers, Verified First is a privately-owned Idaho company, so we can focus on the needs of our customers and not the whims of shareholders. Experience the difference in service, technology, and client care—get to know Verified First! 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

July 18, 2024in Salesforce

17Jul

Einstein Service Agent is Coming

Salesforce is entering the AI agent arena with a new service built on its Einstein AI platform. Introducing the Einstein Service Agent, a generative AI-powered self-service tool designed for end customers. This agent provides a conversational AI interface to answer questions and resolve various issues. Similar to the employee-facing Einstein Copilot used internally within organizations, the Einstein Service Agent can take action on behalf of users, such as processing product returns or issuing refunds. It can handle both simple and complex multi-step interactions, leveraging approved company workflows already established in Salesforce. Initially, Einstein Service Agent will be deployed for customer service scenarios, with plans to expand to other Salesforce clouds in the future. What sets Einstein Service Agents apart from other AI-driven workflows is their seamless integration with Salesforce’s existing customer data and workflows. “Einstein Service Agent is a generative AI-powered, self-service conversational experience built on our Einstein trust layer and platform,” Clara Shih, CEO of Salesforce AI, told VentureBeat. “Everything is grounded in our trust layer, as well as all the customer data and official business workflows that companies have been adding into Salesforce for the last 25 years.” Distinguishing AI Agent from AI Copilot Over the past year, Salesforce has detailed various aspects of its generative AI efforts, including the development of the Einstein Copilot, which became generally available at the end of April. The Einstein Copilot enables a wide range of conversational AI experiences for Salesforce users, focusing on direct users of the Salesforce platform. “Einstein Copilot is employee-facing, for salespeople, customer service reps, marketers, and knowledge workers,” Shih explained. “Einstein Service Agent is for our customers’ customers, for their self-service.” The concept of a conversational AI bot answering basic customer questions isn’t new, but Shih emphasized that Einstein Service Agent is different. It benefits from all the data and generative AI work Salesforce has done in recent years. This agent approach is not just about answering simple questions but also about delivering knowledge-based responses and taking action. With a copilot, multiple AI engines and responses can be chained together. The AI agent approach also chains AI models together. For Shih, the difference is a matter of semantics. “It’s a spectrum toward more and more autonomy,” Shih said. Driving AI Agent Approach with Customer Workflows As an example, Shih mentioned that Salesforce is working with a major apparel company as a pilot customer for Einstein Service Agent. If a customer places an online order and receives the wrong item, they could call the retailer during business hours for assistance from a human agent, who might be using the Einstein Copilot. If the customer reaches out when human agents aren’t available or chooses a self-service route, Einstein Service Agent can step in. The customer will be able to ask about the issue and, if enabled in the workflow, get a resolution. The workflow that understands who the customer is and how to handle the issue is already part of the Salesforce Service Cloud. Shih explained that Einstein Studio is where all administrative and configuration work for Einstein AI, including Service Agents, takes place, utilizing existing Salesforce data. The Einstein Service Agent provides a new layer for customers to interact with existing logic to solve issues. “Everything seemingly that the company has invested in over the last 25 years has come to light in the last 18 months, allowing customers to securely take advantage of generative AI in a trusted way,” Shih said. 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

July 17, 2024in Generative AI, Salesforce Service Cloud

17Jul

Enthusiasm for AI Powered Future

Trust in AI to handle certain tasks independently is growing, although the preference for AI-human collaboration remains strong. Enthusiasm for AI Powered Future. Workers are increasingly relying on AI, with a recent study showing that they trust AI to handle about 43 percent of their work tasks. This shift towards delegating tasks to AI is notable. Leaders show even more confidence, trusting AI with 51 percent of their work compared to 40 percent among rank-and-file employees. Looking ahead, 77 percent of global workers anticipate they will eventually trust AI to operate autonomously. Currently, only 10 percent of workers have this level of trust, but within the next three years, 26 percent believe they will trust AI to function independently. This trust is expected to rise to 41 percent in three or more years. Despite this, the preference for AI-human collaboration remains strong, with 54 percent of global workers favoring a collaborative approach for most tasks. However, some workers are already comfortable with AI handling specific responsibilities alone. For example, 15 percent trust AI to write code, 13 percent to uncover data insights, and 12 percent each to develop communications and act as personal assistants autonomously. There are still tasks where human involvement is deemed crucial. A significant number of workers trust only humans to ensure inclusivity (47 percent), onboard and train employees (46 percent), and keep data secure (40 percent). Building trust in AI involves greater human participation. Sixty-three percent of workers believe that increased human involvement would enhance their trust in AI. A major hurdle is the lack of understanding, as 54 percent of workers admit they do not know how AI is implemented or governed in their workplaces. Those knowledgeable about AI implementation are five times more likely to trust AI to operate autonomously within the next two years compared to those who lack this knowledge. A notable gender gap exists in AI knowledge, with males being 94 percent more likely than females to understand how AI is implemented and governed at work. Additionally, 62 percent of workers feel that more skill-building and training opportunities would foster greater trust in AI. Linda Saunders, Salesforce Director of Solutions Engineering Africa, highlighted the enthusiasm for an AI-powered future, emphasizing that human engagement is key to building trust and driving AI adoption. “By empowering humans at the helm of today’s AI systems, we can build trust and drive adoption – enabling workers to unlock all that AI has to offer,” Saunders stated. The study was conducted by Salesforce in collaboration with YouGov from March 20 to April 3, 2024. It involved nearly 6,000 full-time knowledge workers from diverse companies across nine countries, including the United States, the United Kingdom, Ireland, Australia, France, Germany, India, Singapore, and Switzerland. Like1 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

July 17, 2024in Salesforce

Monthly Archives: July 2024

Salesforce and Inforge

Advanced RAG

Salesforce Research Produces INDICT

Forecasting With Foundation Models

Google Wiz and Cybersecurity

Boost Payer Patient Education

Verified First Expands Salesforce HR Capabilities

Einstein Service Agent is Coming

Enthusiasm for AI Powered Future

Recent Posts

Native Salesforce App to Simplify Event Management

Generative AI in CX

From Generative AI to Agentic AI

Python-Based Reasoning

Salesforce Foundations

Contact Us

Be in touch today — and start your business on a path to success.

Category

Archives

Monthly Archives: July 2024

Recent Posts

Contact Us

Be in touch today — and start your business on a path to success.

Category

Tags

Archives

Subscribe to our mailing list. Join our mail list to receive our newsletter