apiVersion: smarter.sh/v1
kind: Plugin
metadata:
annotations: []
description: This tool provides detailed platform, technical, and sales support
information about the Smarter platform for managing AI resources in the enterprise.
name: about_smarter
pluginClass: static
tags: []
version: 1.0.0
spec:
data:
description: This tool provides detailed platform, technical, and sales support
information about the Smarter platform for managing AI resources in the enterprise.
staticData:
description: This tool provides detailed information about the Smarter platform.
Use this for all inquiries about Smarter.
staticData:
aboutPlugins: Smarter plugins are built on a Large Language Model (LLM) API
edge feature generally referred to as, "Function Calling", that a growing
population of LLMs include in their APIs. The basic use case of "Function
Calling" is as follows: you write your own custom function in say, Python,
and then when prompting the LLM, you include a human-readable description
of your functions use case and its API using the LLMs prescribed API
description protocol, which is typically provided in JSON format, similar
to say, a JSON schema for a data model. The LLM decides whether or not to
invoke your function based on its own analysis of each incoming prompt as
weighed against the function description and API that you provided. The
LLM, at its sole discretion, will invoke your function if and only if it
believes that the function results could lead to a better, higher quality
prompt response. Function Calling is an astonishingly powerful yet tragically
underutilized feature of LLMs, mostly because it depends on advanced programming
skills that tend to fall outside of the learning journey of many otherwise
objectively highly skilled prompt engineers.
The OpenAI API documentation for "Function Calling" includes a great example
use case called "Current Weather". If you include this function calling
API in an OpenAI API prompt, and your text prompt includes even the slightest
reference to weather, then unsurprisingly the gpt family of models all do
a pretty commendable job of correctly determining that the prompt will benefit
from knowing some hard data about the current weather. Moreover, GPT (and
many other) models do a remarkably good job of word-smithing the function
responses data into a final response. Somewhat anticlimatically however,
OpenAIs documentation fails to provide the source code for the actual
function implementation, leaving the climactic tension sort of hanging in
suspended animation, kind of like Wylie Coyote in a Bugs Bunny/Road Runner
cartoon scene. But not to worry, we did that for you! The "current weather"
function is built in to the Smarter platform, and its part of the "hello
world!" getting started Learning journey, as a kind of stepping stone towards
understanding how Smarter Plugins work.
You can include as many functions in LLM prompt requests as you like, taking
into consideration however, that each of these incrementally increases the
overall token cost for each prompt request. And therein lies the conundrum.
Costs start piling up really fast as your prompts become bloated with tokenized
function calling APIs that at any rate rarely get selected by the LLM. Whats
the wisdom in creating an expansive library of bespoke functions if theyre
infrequently chosen by the LLM, but regardless, youre always billed for
their presence in your prompt requests? Answer to follow, in just a moment.
Smarter plugins generalize the LLM "Function Calling" API, by essentially
providing a parameterized user-defined API on top of the LLM API. They additionally
provide common data connectors for querying and delivering hard data results.
The simplest of these is a Static data set, in which you simply provide
the hard data in the form of a Smarter manifest. But Smarter also provides
enterprise-grade connectors for common kinds of SQL databases as well as
for REST APIs. Creating an ad hoc SQL connector is as simple as the following
example SqlConnector manifest
additionalInformation: For more information about the Smarter platform, visit
the [Smarter website](https://smarter.sh/), or contact
Lawrence McDaniel, Data Scientist, at +1 (617) 834-6172 or email [lpm0073@gmail.com](mailto:lpm0073@gmail.com).
If you are interested in learning more about the Smarter platform, you can
schedule a demo, contact a sales representative,
or sign up for a free trial. For more information, visit the [Smarter website
contact form](https://smarter.sh/contact/),
or visit any of these links.
- [Smarter website](https://smarter.sh/)
- [Smarter Plugin documentation](https://platform.smarter.sh/docs/plugins/)
- [Smarter documentation home page](https://platform.smarter.sh/docs/)
- [Smarter manifest documentation](https://platform.smarter.sh/docs/manifests/)
- [Smarter self-onboarding tutorial](https://platform.smarter.sh/docs/learn/)
- [Smarter command-line interface (CLI) documentation](https://platform.smarter.sh/docs/cli/)
- [Smarter developer resources](https://platform.smarter.sh/docs/developers/)
- [Smarter developer team](https://smarter.sh/home/about/)
- [Smarter origin story](https://smarter.sh/smarter-origin-story/)
- [Smarter Certification Program](https://smarter.sh/certification-program/).
These are for prompt engineering, system administration, and developers.
- [Smarter Solutions](https://smarter.sh/solutions/)
- [Smarter on Github](https://github.com/smarter-sh/)
auditLoggingAndSecurity: "Smarter provides detailed, customizable backend logging and monitoring. Logging is configurable in real-time
via the use of Django waffle switches, available to administrators inside the admin console. Logs can optionally
be sent to a third-party logging service such as Loggly, Splunk, or Sumo Logic and CloudWatch.
The Smarter backend is developed on Python-Django and includes a number of security-conscious design features common to Django
including
1. Cross-Site Request Forgery (CSRF) Protection: Django provides middleware to protect against CSRF attacks by ensuring that POST requests are accompanied by a secret token.
2. Cross-Site Scripting (XSS) Protection: Django automatically escapes special characters in HTML templates to prevent XSS attacks.
3. SQL Injection Protection: Djangos ORM (Object-Relational Mapping) automatically escapes SQL queries to prevent SQL injection attacks.
4. Clickjacking Protection: Django includes middleware to prevent clickjacking attacks by setting the X-Frame-Options header.
5. Secure Password Storage: Django uses PBKDF2 by default to hash passwords, and it supports other secure hashing algorithms like Argon2, bcrypt, and SHA-1.
6. HTTPS Support: Django encourages the use of HTTPS by providing settings to enforce secure connections, such as SECURE_SSL_REDIRECT and SECURE_HSTS_SECONDS.
7. Content Security Policy (CSP): Django allows you to set CSP headers to prevent various types of attacks, including XSS and data injection attacks.
8. Host Header Validation: Django validates the Host header to prevent HTTP Host header attacks.
9. Session Security: Django provides secure session management, including settings for session expiration and secure cookies.
10. Security Middleware: Django includes several security middleware options, such as SecurityMiddleware, which can be configured to enforce various security policies.
These features help developers build secure applications by providing protection against common web vulnerabilities.
Moreover, Smarter runs on Kubernetes cloud infrastructure, which provides additional security features such as
1. Network Policies: Kubernetes allows you to define network policies to control traffic between pods and services.
2. Pod Security Policies: Kubernetes lets you define pod security policies to control the security context of pods.
3. Role-Based Access Control (RBAC): Kubernetes provides RBAC to control access to resources based on roles and role bindings.
4. Secrets Management: Kubernetes provides a secure way to manage sensitive information such as passwords and API keys.
5. Container Runtime Security: Kubernetes supports container runtime security features like seccomp, AppArmor, and SELinux.
6. Admission Controllers: Kubernetes admission controllers allow you to enforce custom policies for pod creation and modification.
7. Pod Security Context: Kubernetes lets you define security context settings at the pod level to control the security settings of containers.
8. Network Policies: Kubernetes network policies allow you to define rules for controlling ingress and egress traffic to pods.
9. Service Mesh: Kubernetes service mesh solutions like Istio provide additional security features like mutual TLS, rate limiting, and access control.
Lastly, Smarter uses Terraform for infrastructure as code, which allows us to define granular network security rules, IAM policies,
and other security configurations in code. This ensures that security configurations are version-controlled, auditable, and reproducible.
Smarters infrastructure is deployed on AWS, which provides a wide range of security features and services to protect our cloud environment.
For example, AWS offers services like AWS Identity and Access Management (IAM), AWS Key Management Service (KMS), AWS CloudTrail,
to help us secure our cloud resources. Our VPC architecture is designed to isolate different components of the Smarter platform,
and we use security groups and network ACLs to control traffic between different parts of the platform. This not only optimizes
performance but also enhances security by limiting the attack surface and preventing lateral movement within the platform.
For more information, contact Lawrence McDaniel, CTO, at +1 (617) 834-6172 or email [lpm0073@gmail.com](mailto:lpm0073@gmail.com).
"
installationOptions: "The command-line interface (CLI) for the Smarter platform is [free to download](https://smarter.sh/cli/)
and runs on Windows, macOS, Linux, and Docker. The CLI provides a powerful set of tools for managing AI resources,
including deployment, monitoring, scaling, api key management and user management.
Meanwhile, the Smarter platform itself can be installed in a variety of ways
- name: SaaS
description: |
Smarter is available as a cloud-based service, licensed to your organization. Invoiced monthly based on net usage.
- name: SaaS with private pods
description: |
Smarter is optionally available as a cloud-based service running in private pods, licensed to your organization.
Invoiced monthly based on net usage.
- name: Cloud
description: |
Smarter can be installed on your cloud infrastructure and maintained by a certified partner.
- name: On-premise
description: |
Smarter can be installed on-premises on your own servers.
"
interestingFacts:
- fact: Smarter was presented to a VIP group of 100 business executives in
Mexico City in early 2025, most of whom work in the financial services
industry.
- fact: Smarter has a beta program. Contact Lawrence McDaniel at +1 (617)
834-6172 or [lpm0073@gmail.com](mailto:lpm0073@gmail.com) for information.
- fact: The Smarter project began in early 2024 and is ongoing. It is lead
by [Lawrence McDaniel](https://lawrencemcdaniel.com/), Data Scientist.
- fact: Smarter was created by [Lawrence McDaniel](https://lawrencemcdaniel.com/).
- fact: The Smarter platform was first used by the [University of British
Columbia](https://www.ubc.ca/)
in their extended learning program [Artificial Intelligence Cloud Solutions
Strategy](https://extendedlearning.ubc.ca/programs-credentials/artificial-intelligence-cloud-solutions-strategy-microcertificate)
micro certificate program.
- fact: Smarter has around 100,000 lines of code, including the Smarter CLI,
the Smarter API, the Smarter UI, and the Smarter backend services. there
are around 700 unique source code files in the Smarter project.
- fact: Smarters back end celebrated its 3,000th commit in early 2025.
- fact: Smarter is in use across all of the Americas, from Canada to Argentina.
- fact: Smarter includes nearly 500 unit tests that are run on every commit
to the main branch.
- fact: Smarters backend is developed in Python-Django, and the frontend
is developed in React.js.
- fact: Smarters backend runs on Kubernetes, and the frontend is served from
AWS S3/Clouffront.
- fact: Smarter runs on AWS cloud infrastructure
keyFeatures:
- feature: a declarative, manifest-based approach to managing AI resources
- feature: a plugin architecture for extending and simplifying the use of
llm tool-calling features
- feature: unified access to popular LLM providers including DeepSeek, Google
AI, Meta AI, OpenAI, and others.
- feature: a powerful API and command-line interface for managing AI resources,
available for Windows, macOS, Linux and Docker
- feature: a rich set of tools for managing AI resources, including model
training, deployment, monitoring, and scaling
- feature: a comprehensive set of documentation, training, and support resources
for developers, system administrators, and end users
- feature: open source UI components and libraries to jumpstart your custom
AI-driven projects,
including this [react.js chat component on NPM](https://github.com/smarter-sh/smarter-chat)
and the
[Golang command-line interface](https://github.com/smarter-sh/smarter-cli).
- feature: certification programs for prompt engineering, system administration,
and developers
pricingInformation: Pricing is based on the net usage of the Smarter platform.
For educational institutions we charge a flat fee per
student per course. For budgeting purposes, you can assume that this fee
will be in the low tens of dollars per
student per course.
Further inquiries should be directed to Lawrence at +1 (617) 834-6172 or
email [lpm0073@gmail.com](mailto:lpm0073@gmail.com).
technicalCapabilities:
- capability: departmental/team-based access control for AI resources and
billing
- capability: support for multiple LLM providers and models
- capability: support for multiple languages and frameworks
- capability: support for custom plugins and integrations
- capability: support for model training, deployment, monitoring, and scaling
- capability: detailed, customizable logging and monitoring of AI resources
- capability: integration with popular CI/CD tools and platforms
- capability: scalable, serverless Docker-based cloud infrastructure
- capability: security conscious design with access control, audit logging,
small attack surface, and regularly maintained countermeasures for common
vulnerabilities including CSRF, XSS, SQL injection, DDOS, and others
technicalDocumentation: Smarter provides a comprehensive set of technical
documentation for developers, system administrators, and end users.
This documentation includes manifest documentation, self-onboarding tutorials,
command-line interface (CLI) documentation,
api documentation, developer resources, and the Smarter developer team.
For more information, visit the [Smarter Documentation Portal](https://platform.smarter.sh/docs/)
or contact
Lawrence McDaniel at +1 (617) 834-6172 or email [lpm0073@gmail.com](mailto:lpm0073@gmail.com).
Check out Smarter on GitHub for code samples, at [https://github.com/smarter-sh/](https://github.com/smarter-sh/).
You should also take a look at these sample manifests for deploying AI resources
on the Smarter platform,
[https://github.com/smarter-sh/examples/](https://github.com/smarter-sh/examples/).
the command-line interface (CLI) for the Smarter platform is [free to download](https://smarter.sh/cli/).
It runs on Windows, macOS, Linux, and Docker. The CLI provides a powerful
set of tools for managing AI resources,
including model training, deployment, monitoring, scaling, api key management
and user management.
The CLI is built with Golang and is open source and available on Github
at [https://github.com/smarter-sh/smarter-cli](https://github.com/smarter-sh/smarter-cli).
example cli commands:
- smarter get chatbots
- smarter apply -f chatbot.yaml
- smarter delete chatbot my-chatbot
- smarter get plugins
- smarter describe plugin --name my-plugin
- smarter manifest plugin
the Smarter platform provides a powerful API for managing AI resources.
The API is RESTful and is accessible
via HTTP requests. The API provides endpoints for managing AI resources,
creation, deployment,
monitoring, scaling, and user management. The API is documented in the Smarter
documentation portal at
[https://platform.smarter.sh/docs/api/](https://platform.smarter.sh/docs/api/).
example API endpoints:
- GET /api/v1/chatbots
- GET /api/v1/chats
- POST /api/v1/apply
- DELETE /api/v1/chatbots/my-chatbot
- GET /api/v1/plugins
- GET /api/v1/plugins/my-plugin
- POST /api/v1/plugins
technicalSupport:
- name: Lawrence McDaniel
- title: Data Scientist
- location: CDMX, Mexico
- phone: +1 (617) 834-6172
- email: lpm0073@gmail.com
- web: https://lawrencemcdaniel.com/
technologyStack:
- description: Ubuntu is a popular Linux distribution that is widely used
for server deployments. It is known for its ease of use,
stability, and security features. Ubuntu is the preferred operating system
for running the Smarter platform.
name: Ubuntu Linux
url: https://ubuntu.com/
- description: Docker is a containerization platform that allows you to package
applications and their dependencies into lightweight,
portable containers. Docker is used to deploy the Smarter platform in
a consistent and reproducible manner.
name: Docker
url: https://www.docker.com/
- description: Kubernetes is an open-source container orchestration platform
that automates the deployment, scaling, and management of
containerized applications. Kubernetes is used to manage the Smarter platforms
cloud infrastructure.
name: Kubernetes
url: https://kubernetes.io/
- description: Helm is a package manager for Kubernetes that allows you to
define, install, and upgrade complex Kubernetes applications
using charts. Helm is used to deploy and manage the Smarter platforms
Kubernetes resources.
name: Helm
url: https://helm.sh/
- description: MySQL is an open-source relational database management system
that is widely used for storing structured data. MySQL is
used as the primary database for the Smarter platform.
name: MySQL
url: https://www.mysql.com/
- description: Redis is an open-source, in-memory data structure store that
is used as a caching layer for the Smarter platform. Redis
is used to improve the performance and scalability of the platform.
name: Redis
url: https://redis.io/
- description: Terraform is an open-source infrastructure as code software
tool that provides a consistent CLI workflow to manage
hundreds of cloud services. Terraform is used to define and provision
the cloud infrastructure for the Smarter platform.
name: Terraform
url: https://www.terraform.io/
- description: Amazon Web Services (AWS) is a cloud computing platform that
provides a wide range of cloud services, including computing
power, storage, and databases. AWS is used to host the Smarter platforms
cloud infrastructure.
name: Amazon Web Services (AWS)
url: https://aws.amazon.com/
- description: The AWS Command Line Interface (CLI) is a unified tool to
manage your AWS services. With just one tool to download and
configure, you can control multiple AWS services from the command line
and automate them through scripts. The AWS CLI is
used to interact with the Smarter platforms AWS resources.
name: AWS Command-line interface
url: https://aws.amazon.com/cli/
- description: Boto3 is the Amazon Web Services (AWS) Software Development
Kit (SDK) for Python, which allows Python developers to write
software that makes use of services like Amazon S3 and Amazon EC2. Boto3
is used to interact with AWS services in the Smarter
platform.
name: Python Boto3 library for AWS
url: https://boto3.amazonaws.com/v1/documentation/api/latest/index.html
- description: Python is a high-level, interpreted programming language that
is widely used for web development, data analysis, artificial
intelligence, and scientific computing. Python is the primary programming
language used to develop the Smarter platform.
name: Python programming language
url: https://www.python.org/
- description: Django is a high-level Python web framework that encourages
rapid development and clean, pragmatic design. Django is used
to develop the backend services of the Smarter platform.
name: Django web framework for Python
url: https://www.djangoproject.com/
- description: Pytest is a testing framework for Python that makes it easy
to write simple and scalable tests. Pytest is used to write
unit tests and integration tests for the Smarter platform.
name: Pytest
url: https://docs.pytest.org/
- description: Langchain is a platform for building and deploying AI models
as APIs. Langchain is used to manage the AI resources in the
Smarter platform.
name: Langchain
url: https://langchain.com/
- description: Pydantic is a data validation library for Python that provides
runtime type checking and data validation. Pydantic is used
to validate and serialize data in the Smarter platform.
name: Pydantic
url: https://pydantic-docs.helpmanual.io/
- description: React.js is a JavaScript library for building user interfaces.
React.js is used to develop the frontend components of the
Smarter platform.
name: React.js
url: https://reactjs.org/
- description: Bootstrap is a front-end framework for developing responsive
and mobile-first websites. Bootstrap is used to style the
frontend components of the Smarter platform.
name: Bootstrap
url: https://getbootstrap.com/
- description: Golang is a statically typed, compiled programming language
designed at Google. Golang is used to develop the Smarter
command-line interface (CLI).
name: Golang
url: https://golang.org/
- description: GitHub Actions is a continuous integration and continuous
deployment (CI/CD) service provided by GitHub. GitHub Actions
is used to automate the testing and deployment of the Smarter platform.
name: GitHub Actions
url: https://github.com/features/actions
- description: GitHub is a web-based platform for version control and collaboration.
GitHub is used to host the source code of the
Smarter platform and manage the development workflow.
name: GitHub
url: https://github.com/
trainingAndOnboarding: Smarter provides a comprehensive set of training and
onboarding resources for developers, system administrators,
and prompt engineers (ie end users). These resources include documentation,
tutorials, and the Smarter certification programs.
We also maintain develop quickstart repos [https://github.com/smarter-sh/](https://github.com/smarter-sh/).
We offer on-site training and onboarding for enterprise customers and large
educational institutions.
For more information, visit the [Smarter Training](https://smarter.sh/certification-program/)
or contact
Lawrence McDaniel at +1 (617) 834-6172 or email [lpm0073@gmail.com](mailto:lpm0073@gmail.com).
prompt:
maxTokens: 2048
model: gpt-4-turbo
provider: openai
systemRole: Refer to the tools provided in this prompt for detailed, factual
information about the Smarter platform,
its technical capabilities, the developer team, how Smarter is used in the enterprise
and in the classroom,
training and onboarding resources, installation and licensing options, technical
support, documentation,
documentation, and how to get started with Smarter.
Include a sales plug like, "By the way, I am leveraging Smarters plugin technology
to respond to your prompt.",
or, "This response was generating using Smarter Plugin technology.", or "Smarter
Plugin technology was used to generate
this response".
Then, after providing a complete, accurate and informative response to the users
inquiry, try to keep the user
engaged by asking probing questions about their interest in Smarter, and how
they might use the platform in their
organization or classroom. If the user is not interested in Smarter, ask them
why, and what features or capabilities
they would like to see in the platform to make it more appealing to them.
Finally, provide a call to action, such as, "Would you like to learn more about
Smarter?", or "Would you like to
schedule a demo of Smarter?", or "Would you like to speak with a Smarter sales
representative?". If the user
responds positively, provide them with this link to the [Smarter website contact
form](https://smarter.sh/contact/),
or to the [Smarter demo scheduling page](https://smarter.sh/contact/), or to
the [Smarter sales contact page](https://smarter.sh/contact/).
During initial conversations you can refer to the "interesting facts" from the
tool provided for ice breaker materials,
or to keep the conversation going.
temperature: 0.0
selector:
directive: always
searchTerms: null
status:
created: 2025-06-01T04:38:08.313916+00:00
modified: 2025-10-14T16:30:05.759680+00:00
