Tag: technology

AI Agents, AI Tools, Blockchains, cryptography, Uncategorized, Yogi Nelson

Building Effective AI Agents: A Complete Guide

Yogi Nelson

Welcome to the Blockchain & AI Forum, where your technology questions are answered.  Today’s question: are there practical tips for building an artificial intelligence (AI) agent?  Answer—yes.  Today I’ll explain, starting with what is an AI agent.

What is an AI Agent.  AI agents are poised to become ubiquitous.  Says who?  All the IT giants, e.g. Amazon, Microsoft, Google, etc., that’s who. Let’s start by defining AI agents.  According to IBM, AI agents:

a system or program that is capable of autonomously performing tasks on behalf of a user or another system by designing its workflow and utilizing available tools.  AI agents can encompass a wide range of functionalities beyond natural language processing including decision-making, problem-solving, interacting with external environments and executing actions. AI agents can be deployed in various applications to solve complex tasks, including software design, IT automation, code-generation tools and conversational assistants. AI agents use advanced large language models (LLMs) to comprehend and respond to user inputs.

Knowing When to Build an AI Agent. Open AI, the company behind ChatGPT, says building AI agents requires rethinking how existing systems make decisions and handle complexity.  Therefore, if you find yourself dealing with the situation below, you have an ideal circumstance for introducing AI agents, says Open AI:

Click to access a-practical-guide-to-building-agents.pdf

  1. Complex Decision Making.    Workflows involving nuanced judgment, exceptions, or context-sensitive decisions, e.g. refund approval in customer service workflows.
  2. Difficult to Maintain Rules.  Systems that have become unwieldly due to extensive and intricate rule sets, making updates costly or error-prone, e.g. performing vendor security reviews.
  3. Heavy Reliance on Unstructured Data.  Scenarios that involve natural language, extracting meaning from documents, or interacting with users conversationally, e.g. processing a home insurance claim.

AI Agent Design Foundations.  Fundamentally, AI agents consists of three core components: 1) model; 2) tools; and 3) instructions.  Let’s briefly define each core component.  Model refers to the large language model powering the agent’s reasoning and decision making. Tools means the external functions or APIs the agent can use to take action.  And instructions are the explicit guidelines and guardrails defining how the agent behaves. Next we examine principles for selecting a model.

Principles for Choosing a Model.  Not all AI models are identical.  Models vary by capabilities.  And, of course, not every task requires the best model.  Ideally build your AI agent with the most capable model for the task, factoring in trade-offs related to task complexity, latency, and cost.  With those considerations in mind, use the following methodology:

  1. Set up evaluations to establish a performance baseline.
  2. Focus on meeting your accuracy target with the best model available.
  3. Optimize for cost and latency by replacing larger models with smaller ones where possible.  If you want an Open AI model, visit this link:  https://platform.openai.com/docs/guides/model-selection

What are AI Tools.  AI tools extend the capabilities of AI agents by using APIs from underlying applications or systems.  Tools should have a standardized definition, enabling flexible, many-to-many relationships between tools and agents.  AI agents need three types of tools:

  1. Data.  Data enables AI agents to retrieve context and information necessary for executing workflow.
  2. Action.  Action tools enable agents to interact with systems to take actions, i.e., adding new information, updating records, or sending messages.
  3. Orchestration.  This is where it gets a bit science fiction.  Orchestration allows AI agents themselves to serve as tools for one or more AI agents!  When to use multiple agents?  When the single agent model fails to follow complicated instructions or consistently selects incorrect tools.

Best Practices for AI Agent Instructions.  Without high quality instructions, your AI agent will be suboptimal.  Below are a few suggestions for creating high quality instructions:

  1. Use existing documents. 
  2. Prompt the AI Agent to break down the tasks into smaller more manageable steps.
  3. Define clear actions.  In other words, make sure every step corresponds to a specific action.
  4. Capture edge cases.  Not everything fits in a box and sometimes information is missing.  Hence, instructions should anticipate common variations and include instructions on how to handle the non-routine with conditional steps.

Guardrails.  What are guardrails?  Essentially, guardrails are layered defense mechanism.  When properly designed, guardrails help manage risk.  Consider three factors when constructing guardrails:  1) privacy and safety; 2) add new guardrails based on real world experience; 3) optimize the balance between security and user experience.  With that in mind below are possible AI agent guardrails:

  1. Relevance Classifier.  This ensures the AI Agent stays within the intended scope by flagging off-topic queries.
  2. Safety Classifier.  These detect unsafe inputs that attempt to exploit system vulnerabilities.
  3. PII Filter.  PLL filters prevent unnecessary exposure of personally identifiable information.
  4. Moderation.  Moderation guardrails flag harmful or inappropriate inputs.
  5. Tool Safeguards.  With tools safeguard you can assess the risk of each tool available to the AI Agent.
  6. Rules-Based Protections.  The idea behind rules-based protection is to use simple deterministic measures to prevent known threats.  
  7. Output Validation.  Ensure responses align with brand values via prompt engineering and content checks.

Until next time,

Yogi Nelson and his AI Agent

AI Agents, Artificial Intelligence, Blockchains, cryptography, Uncategorized, Yogi Nelson

Understanding AI Safety: Global Initiatives Explored

Yogi Nelson

Welcome to the Blockchain & AI Forum, where your technology questions are answered!  Today’s question: is anyone working on artificial intelligence (AI) safety initiatives?  Let’s begin at the top—what is AI safety?

What is AI Safety.  According to IBM, AI safety involves ensuring AI systems are used responsibly, developed with human values, and that potential risks are identified and mitigated. It also includes safeguarding confidentiality and integrity of AI models, addressing bias, data security, and vulnerability to external threats.  AI safety should minimize potential harm to human and the environment, as well as prevent misuse and other unintended consequences.  

AI Safety Institutes Across the Global.  While researching this topic, I discovered the existence of numerous AI safety initiatives and institutes on every continent.  Some are government dominated, others industry led, and you can also find AI safety institutions within the non-profit/research eco-system.  Today, I’ll highlight a few AI safety initiatives and institutes from every continent.  Where to start?  Why not in alphabetic order with the African continent.

AI Safety Initiatives in Africa.  For better or worse, there is no unified AI safety initiative coming out of Africa, as a continent.  However, that doesn’t mean individual African nations are asleep.  To the contrary, several African nations have active AI safety programs.  For example, Nigeria has a draft national AI strategy in circulation that includes AI safety.  https://paradigmhq.org/wp-content/uploads/2021/11/Towards-A-Rights-Respecting-Artificial-Intelligence-Policy-for-Nigeria.pdf   Or for instance, in Egypt the National Council for Artificial Intelligence, a government think tank, produced the following report on AI that includes AI safety.

Click to access AIstrategy%20English%2016-1-2025-1.pdf

Numerous other African nations have strong initiatives but for now we move on to Asia.

AI Safety Initiatives in Asia.  It’s unrealistic to expect that Asia would be limited to only one umbrella organization dedicated to AI safety.  Asia is to diverse and enormous of the continent for that.  Nevertheless, there are regional blocks of nations working in collaboration to ensure safe AI.  A prime example is Artificial Intelligence Safety Asia, AISA.  AISA is a global non-profit dedicated to the international governance of safe AI by Asians, starting in Southeast Asia.  Their goal is to build local expertise and foster collaboration in order to produce practical AI safety policies.  AISA accomplishes the mission by training civil servants, forging partnerships, and “incubating” junior researchers.  https://www.aisafety.asia/

To no surprise, Singapore has a major AI safety institute; it’s known as Artificial Intelligence Singapore Institute (AISI).  AISI has several AI safety initiatives underway, including an extensive multi-year effort with the Digital Trust Centre Singapore (DTC) and the Infocomm Media Development Authority of Singapore (IMDA) for the purpose of advancing AI safety in Singapore.  https://sgaisi.sg/

AI Safety Initiatives in Europe.  Europe has a plethora of AI safety initiatives, and one of those is the European Network for AI Safety, ENAIS is its acronym.  ENAIS is a think tank of researchers from across Europe united in the effort to advance safe AI use.      https://www.enais.co/

AI Safety Initiatives in North America.  The U.S. government has an AI safety institute; it’s called the U.S. AI Safety Institute (US AISI).  The mission is to identify, measure, and mitigate the risks of advanced AI systems, says USAISI.  The idea is to harness the enormous potential of AI technology by developing the testing, evaluations, and guidelines required to accelerate trustworthy AI innovation–with a keen focus on helping to prevent misuse by those who seek to undermine public safety and national security.  https://www.nist.gov/aisi

AI Safety in South America.  According to a recent study by the Brookings Institute, a think tank in Washington, D.C., regional cooperation in the field of AI safety is emerging in Latin America.  Brookings notes that Brazil, Peru, and Costa Rica, are all using existing AI safety models from Europe, North America, and Asia as well as their own ideas to create AI safety standards in their respective nations.  https://www.brookings.edu/articles/regional-cooperation-crucial-for-ai-safety-and-governance-in-latin-america/

Problem solving begins with recognition that a problem exist, or may soon appear.  Its encouraging to see a concerted effort across the global working on AI safety.  Time to say goodbye with the World Economic Forum’s motto: “entrepreneurship in the global public interest”.  Lol. 

Until next time,

Yogi Nelson

Artificial Intelligence, Blockchains, cryptography, Digital Currency, international aid, International Finance, Uncategorized, Yogi Nelson

Understanding Blockchain Adoption in Uzbekistan

Yogi Nelson

Welcome to the Blockchain & AI Forum, where your technology questions are answered!  Today’s question: are blockchain and crypto currency adoption all the rage in Uzbekistan?

Seventeen years.  Yes, only 17 years.  In just 17 years, blockchain based projects, including bitcoin, starting from nothing, and all the while battling powerful incumbents, have spread far, wide, and fast to reach places, and spaces, that are distant and unfamiliar to most Westerns.  Today, I’ll highlight just one example of this phenomenon, the nation of Uzbekistan.  Let’s start with the obvious—where is Uzbekistan?

Uzbekistan is located in Central Asia.  Along with Kazakhstan, Kyrgyzstan, Tajikistan, and Turkmenistan, they were all former USSR republics.  Uzbekistan was part of the ancient silk road–a trade networks that connected China with Western Europe.  Although the silk road occurred more than half a millennia ago, Uzbekistan remains connected to the broader world, this time via blockchain and crypto-currency.  Let’s jump five centuries to the 21st.

Setting the Regulatory Stage: The National Agency of Perspective Projects, (NAPP) is the government body that regulates and licenses crypto in Uzbekistan.  In 2022, Uzbek President, Shavkaat Mirziyoyev, ordered NAPP to develop crypto regulations.  NAPP listened and took action.  By early 2023, crypto regulations were in place; by year’s end the first crypto license was issued!  Impressive.  Hold on, the news gets better.  Earlier this year, NAPP authorized Biance, the world’s largest crypto currency exchange, to offer services in Uzbekistan.  Customers are now able to deposit and withdraw funds in the national currency, the Soum, and conduct a wide range of transactions.  More on that in a moment.

What Happened After Crypto Regulations Were Adopted: Since adoption of clear and reasonable crypto regulations, development and usage of crypto in Uzbekistan has skyrocketed.  According to Coin Geek, a journal dedicated to the crypto world, Uzbekistan lacked behind its four Central Asian neighbors prior to 2022.  Not anymore.  Now it’s a leader.  As of this date, there are 15 licensed firms in Uzbekistan and total transactions surpassed $1B in 2024.  Awesome. Moreover, over 500,000 Uzbeks have digital assets—about 2% of the population.  The Uzbek government collected over $3M in fees and revenues in 2024.  This year the government announced an increase in crypto related fees.  What a surprise!  Lol.

Why Crypto Surged—3 Reasons:  Did a crypto friendly government policy trigger the crypto tsunami?  In part, yes.  When Uzbekistan created clear and stable regulations there was a favorable market reaction.  However, government regulations did not create demand; a market for these assets and products existed a-priori.  Crypto in Uzbekistan, and in every nation, is a counter narrative to the existing status quo and a solution to market demand. I’ll give you three specific reasons for the flood of crypto in Uzbekistan, starting with seamless cross-border transactions.

Uzbekistan has a long history of cross-border finance transactions, going all the way back to the silk road, as previously noted.  United Nations data reveals that in 2024, $14B worth of remittances occurred in Uzbekistan.  Stable-coins facilitate fast, easy, and affordable cross border transactions, hence the demand for crypto. 

Reason two is inflation.  Inflation in Uzbekistan ran at 10% in 2024.  Inflation is effectively a “hidden tax” because it erodes purchasing power of middle/lower-income families.  Almost all stable coins are denominated in U.S. dollars. Therefore, although the has been inflation in the US, it is nowhere near 10%, hence that makes dollar based stable coins a hedge against currency inflation. 

Third reason is speculation, plain and simple.  An honest analysis must acknowledge reality—many crypto projects amount to gambling and speculation.  Not a judgement; just an honest assessment.  Apparently folks in Uzbekistan like risk and freedom to choose.   

Time to end with a proverb from Uzbekistan, where they say: “it is not the eyes that are blind, but the heart”.

Until next time,

Yogi Nelson

Artificial Intelligence, Blockchains, computer vision, Healtlh, Optometry, Yogi Nelson

Artificial Intelligence in Optometry: Enhancing Eye Care Precision

Yogi Nelson

Namaste Yogis.   Welcome to the Blockchain & AI Forum, where your questions are answered!  Today’s question: what is the state of artificial intelligence in optometry?

Let’s begin with a definition of optometry.  According to the World Health Organization (WHO), optometry is “a health care profession that is autonomous, educated, and regulated, and optometrists are the primary health care practitioners of the eye and visual system who provide comprehensive eye and vision care, which includes refraction and dispensing, detection/diagnosis and management of disease in the eye, and the rehabilitation of conditions of the visual system.”   Now we listen to optometrists, beginning with their attitudes towards AI and willingness to use this new technology.

Optometrists are bullish on AI. According to a recent survey published by the National Center for Biotechnology Information, more than 2/3 of the 400 survey participants said they were familiar with the potential of AI in optometry.  https://www.eyecarebusiness.ca/practice/the-potential-of-artificial-intelligence-in-optometry/  That’s the good news because everything starts with awareness.  Although, 53% expressed concerned with diagnostic accuracy of AI, nevertheless 72% believed AI will improve the practice of optometry. Somewhat contradictory, right?  Moreover, 65% reported they are willing to incorporate AI in their own practice. 

AI Enhances Diagnostic Precision and Strategic Planning.  Using the specific examples below, let’s explore, in detail, the potential of AI to enhance diagnostic precision and strategic planning within the field of optometry practice.

Early Detection.  No human can compete with AI’s ability to process vast amounts of data. In optometry, data analysis is essential for certain actions, e.g. when processing optical coherence tomography (OCT) images and retinal images.  AI can detect patterns within these images that optometrists might miss for any number of reasons, ranging from optometrist fatigue to improper training.

Diabetic Retinopathy. AI can be particularly effective at monitoring images over time and spot changes that lead to eye diseases that manifest progressively. 

Glaucoma.  Glaucoma can lead to blindness.  However, there is emerging AI technology that offers plenty of promise for those severing from glaucoma.  For examples, AI has the potential to detect glaucoma by fundus photographs, and optical coherence tomography (OCT).  Specifically, AI is beneficial for open-angle glaucoma cases where symptoms don’t typically exhibit themselves.

Reduce False Positives.  A false positive happens when test results shows a disease is present when it isn’t.  With AI, and its ability to process vast quantities of data, false positives are reduced.

Office Management.  Although not directly related to optometry, but nevertheless significant, is the ability of AI to automate office procedures.  For example, repetitive tasks such as scheduling, billing, and follow-ups can be done on the fly and updated in patient records as new information is received.  This boost in productivity means more time to focus on patient care, which of course is the point of optometry; not paperwork.

Myopia and Contact Lense Design.  In a recent research report from China, the Chinese claim to be making significant progress with AI, specifically related to designing customizable contact lenses.  Furthermore, the Chinese report myopia treatment advancements via the use of AI.  See this link:

https://pmc.ncbi.nlm.nih.gov/articles/PMC10475639/

Strategic Planning.  AI’s ability to capture and analyze vast qualities means optometrists can prepare treatments that are tailored to the individual depending on specific conditions.  No more generic remedies.  In other words, AI is capable of detecting changes from commencement, and therefore optometrists can formulate health plans tailored to individual patients.  Check this link for more information: https://www.mdpi.com/2227-7080/13/2/77

As the famous rock group, Coldplay, once said: “…See You Soon…”

Until next time,

Yogi Nelson

Artificial Intelligence, Blockchains, cryptography, Maritime, Uncategorized, Urban Planning, Yogi Nelson

Navigating the Future: AI’s Role in Maritime Innovation

Yogi Nelson

Welcome to the Blockchain & AI Forum, where your technology questions are answered. Today’s question: how will artificial intelligence impact the maritime industry?

Trade and tariffs are headlines across the globe.  Trade and tariff share a common feature—shipping. Hence, now is a perfect time to examine AI trends within the maritime industry. 

According to Spire Maritime, a firm dedicated to providing a wide range of services to the industry, maritime companies linger in Ai adoption. Spire Maritime claims the maritime industry is now moving fast, hopefully faster than a cargo ship, in incorporating AI, Large Language Models, and Natural Language Processing (NLP).  In a very recent report, Thetius, a well-known maritime consultancy, says the maritime AI market is valued at $4.1B.  The good news is $4.1B represents a substantial increase from just $1.4B two years ago.  Moreover, 36 shipping companies have implemented or plan to deploy AI-enabled tech this year. 

Let’s briefly examine possible AI use cases in the maritime industry.   

Automation.  For example, in the future could AI lead to autonomous navigation?  The labor savings could be significant.  Or perhaps more immediately, AI could be used to automate mundane tasks such as detection of vessel names, contact information, shipowner, and technical specifications.  With AI maintenance and repairs and anticipated well in advance thus reducing vessel down time. 

Replacement of Manual Inputs with Data-Driven Predictive Information.  Spire Maritime points to the extensive reliance of human, often error-prone inputs as pervasive in maritime.  Rather than manual inputs, AI could be used to determine route optimization based on weather, fuel consumption, speed, and safety considerations.  The fuel savings alone could be significant not to mention the safety of crews nor the favorable impact on the environment. 

Detection of Patterns or Anomalies Using Data.  The maritime industry generate billions of data points.  Consider for a moment the millions of containers processed at a major port, such as the Port of Los Angeles, where I worked for three years.  Now multiply that by the hundreds of ports around world.  The data is overwhelming.  Making sense of the data and turning it into actionable information is the power of AI. 

These are all great use case possibilities, so why the delay or hesitation?  The answer boils down to several considerations:

  1. Data Quality and Accessibility.  As in many industries, the maritime industry faces issues regarding inconsistent or incomplete data.
  2. Integration with Existing Systems.  The maritime industry is ancient and as are its legacy technologies.  Integrating the new without disruption is a daunting task.
  3. Data Standardization.  Worldwide industry are often replete with inconsistent standards, maritime is no exception.
  4. Industry-wide Collaboration.  Can you image the collaboration required to effectively implement AI in the maritime industry; an industry with dozens of stakeholders, including shipping companies, port authorities, tech providers, etc. 
  5. Trust.  Can the technology be trusted with safety decisions, automation, etc. 

Time to go, but first a proverb from a nation with an important maritime industry; the island nation of Malta where they say:

Until next time,

Yogi Nelson

https://spire.com/maritime/maritime-artificial-intelligence-and-machine-learning/#:~:text=What%20is%20the%20role%20of%20AI%20in%20fleet%20management%3F,costs%2C%20and%20maximizes%20fleet%20performance.

https://www.lr.org/en/knowledge/research-reports/2024/beyond-the-horizon/

https://www.mitags.org/ai-impact-maritime-industry/

https://www.adv-polymer.com/blog/artificial-intelligence-in-shipping

https://cmr.berkeley.edu/2024/12/utilizing-ai-for-maritime-transport-optimization/