SlideShare a Scribd company logo
1 of 12
CONSTRAINTS ENABLED AUTONOMOUS
AGENT MARKETPLACE: DISCOVERY AND
MATCHMAKING
DEBMALYA BISWAS, WIPRO AI
AI AGENTS
In the Generative AI context,
Agents are representative of an
Autonomous Agent that can
execute complex tasks, e.g.,
 make a sale,
 plan a trip,
 make a flight booking,
 book a contractor to do a
house job,
 order a pizza.
AI AGENTS (HIERARCHICAL) COMPOSITION
Given a user task, an AI Agent aims to identify
(compose) an agent (group of agents) capable of
executing the given task. A high-level approach to
solving such complex tasks involves:
 decomposition of the given complex task into a
hierarchy or workflow of) simple tasks, followed by
 composition of agents able to execute the simpler
tasks.
This can be achieved in a dynamic or static manner.
 In the dynamic approach, given a complex user task,
the system comes up with a plan to fulfil the request
depending on the capabilities of available agents at
run-time.
 In the static approach, given a set of agents,
composite agents are defined manually at design-
time combining their capabilities.
AI AGENTS DISCOVERY CHALLENGES – AGENT CAPABILITIES &
CONSTRAINTS
The main focus of this paper
is on the discovery aspect of
agents, i.e., identifying the
agent(s) capable of
executing a given task.
This implies that there exists
a marketplace with a registry
of agents, with a well-defined
description of the agent
capabilities and constraints.
Capability: connects City A to B
Constraint: Flies only on certain
days a week; Needs payment by
Credit Card
CONTRIBUTION
 AI Agents Discovery
 Predicate Logic based
Constraints Model
 Constraints
Composition
 Deterministic
 Non-deterministic
 Agent Matchmaking
PREDICATE LOGIC CONSTRAINTS MODEL
The constraints are specified as logic
predicates in the service description of
the corresponding service published by
its agent.
An agent P provides a set of services
{S1,S2, … , Sn}. Each service S in turn
has a set of associated constraints
{C1,C2, … ,Cm}.
For each constraint C of a service S,
the constraint values maybe
 a single value (e.g., price of a service),
 list of values (e.g., list of destinations
served by an airline), or
 range of values (e.g., minimum,
maximum)
CONSTRAINTS COMPOSITION
Composition: two or
more services
offered by (the same
or) different agents
are composed to
form a new
composite service
with some additional
logic (if required).
* D. Biswas. Generative AI Architecture Patterns. Data Driven Investor (link)
CONSTRAINTS COMPOSITION - DETERMINISTIC
We first consider
deterministic
composition:
component services
invoked in sequence or
parallel.
Agent M composes
composite service SC
from component
services
S1, S2, … , Sn
(provided by providers
P1, P2, … , Pn,
respectively).
CONSTRAINTS COMPOSITION – NON-DETERMINISTIC
Accommodate non-
determinism:
possibility of choice
among the component
services.
 Paths based
approach
 Heuristic approaches
 Pessimistic
 Optimistic
 Probabilistic
 Incremental
AGENT MATCHMAKING
 For a user task G, matchmaking consists of finding
agents capable of executing G’s (sub-)tasks. The
subtasks of G might have their own constraints.
 Given this, the required matchmaking for G can be
achieved with the help of a logic program execution
engine by posing (tasks of) G’s constraints as a
goal against the logic program corresponding to the
service constraints of the respective agents.
 A logic program execution engine specifies, not only
if a goal can be satisfied, but also all the possible
bindings for any unbounded variables of the goal.
CONCLUSION
 In this paper, we focused on the discovery aspect of
Autonomous AI Agents.
 We outlined a constraints based predicate logic
model to specify agent services.
 To enable hierarchical composition, we showed how
the constraints of a composite agent service can be
derived and described in a manner consistent with
respect to the constraints of its component
services.
 Finally, we discussed approximate matchmaking,
and showed how the notion of bounded
inconsistency can be leveraged to discover agents
more efficiently.
Thank
You
&
Question
s
Contact: Debmalya Biswas
LinkedIn:
https://www.linkedin.com/in/debmalya-
biswas-3975261/
Medium:
https://medium.com/@debmalyabiswas

More Related Content

Similar to Constraints Enabled Autonomous Agent Marketplace: Discovery and Matchmaking

Machine Learning Applications in Grid Computing
Machine Learning Applications in Grid ComputingMachine Learning Applications in Grid Computing
Machine Learning Applications in Grid Computing
butest
 
S-CUBE LP: SLA-based Service Virtualization in distributed, heterogenious env...
S-CUBE LP: SLA-based Service Virtualization in distributed, heterogenious env...S-CUBE LP: SLA-based Service Virtualization in distributed, heterogenious env...
S-CUBE LP: SLA-based Service Virtualization in distributed, heterogenious env...
virtual-campus
 
907438-Mobile-Data-Arbitrage-Portal-System-for-Mid-Range-Automotive-Servicers
907438-Mobile-Data-Arbitrage-Portal-System-for-Mid-Range-Automotive-Servicers907438-Mobile-Data-Arbitrage-Portal-System-for-Mid-Range-Automotive-Servicers
907438-Mobile-Data-Arbitrage-Portal-System-for-Mid-Range-Automotive-Servicers
bizquirk
 
Web Modeling-based Approach to Automating Web Services Mediation, Choreograph...
Web Modeling-based Approach to Automating Web Services Mediation, Choreograph...Web Modeling-based Approach to Automating Web Services Mediation, Choreograph...
Web Modeling-based Approach to Automating Web Services Mediation, Choreograph...
Marco Brambilla
 
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
csandit
 
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
cscpconf
 
An approach for software effort estimation using fuzzy numbers and genetic al...
An approach for software effort estimation using fuzzy numbers and genetic al...An approach for software effort estimation using fuzzy numbers and genetic al...
An approach for software effort estimation using fuzzy numbers and genetic al...
csandit
 

Similar to Constraints Enabled Autonomous Agent Marketplace: Discovery and Matchmaking (20)

Multi dimensional customization modelling based on metagraph for saas multi-t...
Multi dimensional customization modelling based on metagraph for saas multi-t...Multi dimensional customization modelling based on metagraph for saas multi-t...
Multi dimensional customization modelling based on metagraph for saas multi-t...
 
Online Property Management System
Online Property Management SystemOnline Property Management System
Online Property Management System
 
Machine Learning Applications in Grid Computing
Machine Learning Applications in Grid ComputingMachine Learning Applications in Grid Computing
Machine Learning Applications in Grid Computing
 
Company presentation
Company presentationCompany presentation
Company presentation
 
S-CUBE LP: SLA-based Service Virtualization in distributed, heterogenious env...
S-CUBE LP: SLA-based Service Virtualization in distributed, heterogenious env...S-CUBE LP: SLA-based Service Virtualization in distributed, heterogenious env...
S-CUBE LP: SLA-based Service Virtualization in distributed, heterogenious env...
 
IRJET- Ad-Click Prediction using Prediction Algorithm: Machine Learning Approach
IRJET- Ad-Click Prediction using Prediction Algorithm: Machine Learning ApproachIRJET- Ad-Click Prediction using Prediction Algorithm: Machine Learning Approach
IRJET- Ad-Click Prediction using Prediction Algorithm: Machine Learning Approach
 
907438-Mobile-Data-Arbitrage-Portal-System-for-Mid-Range-Automotive-Servicers
907438-Mobile-Data-Arbitrage-Portal-System-for-Mid-Range-Automotive-Servicers907438-Mobile-Data-Arbitrage-Portal-System-for-Mid-Range-Automotive-Servicers
907438-Mobile-Data-Arbitrage-Portal-System-for-Mid-Range-Automotive-Servicers
 
Web Service Composition
Web Service CompositionWeb Service Composition
Web Service Composition
 
A wrapper for QuantLib and reference data
A wrapper for QuantLib and reference dataA wrapper for QuantLib and reference data
A wrapper for QuantLib and reference data
 
Designingapplswithnet
DesigningapplswithnetDesigningapplswithnet
Designingapplswithnet
 
Web Modeling-based Approach to Automating Web Services Mediation, Choreograph...
Web Modeling-based Approach to Automating Web Services Mediation, Choreograph...Web Modeling-based Approach to Automating Web Services Mediation, Choreograph...
Web Modeling-based Approach to Automating Web Services Mediation, Choreograph...
 
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
 
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
 
An approach for software effort estimation using fuzzy numbers and genetic al...
An approach for software effort estimation using fuzzy numbers and genetic al...An approach for software effort estimation using fuzzy numbers and genetic al...
An approach for software effort estimation using fuzzy numbers and genetic al...
 
Introduction to Google Guice
Introduction to Google GuiceIntroduction to Google Guice
Introduction to Google Guice
 
RPA Consultant Certified in UiPath and Automation Anywhere
RPA Consultant Certified in  UiPath and Automation Anywhere RPA Consultant Certified in  UiPath and Automation Anywhere
RPA Consultant Certified in UiPath and Automation Anywhere
 
RAILWAY RESERVATION SYSTEM OOSE PROJECT.docx
RAILWAY RESERVATION SYSTEM OOSE PROJECT.docxRAILWAY RESERVATION SYSTEM OOSE PROJECT.docx
RAILWAY RESERVATION SYSTEM OOSE PROJECT.docx
 
Immune-Inspired Method for Selecting the Optimal Solution in Semantic Web Ser...
Immune-Inspired Method for Selecting the Optimal Solution in Semantic Web Ser...Immune-Inspired Method for Selecting the Optimal Solution in Semantic Web Ser...
Immune-Inspired Method for Selecting the Optimal Solution in Semantic Web Ser...
 
Agent-Based Technologies (Mobile-C) - IK
Agent-Based Technologies (Mobile-C) - IKAgent-Based Technologies (Mobile-C) - IK
Agent-Based Technologies (Mobile-C) - IK
 
Applying Code Customizations to Magento 2
Applying Code Customizations to Magento 2 Applying Code Customizations to Magento 2
Applying Code Customizations to Magento 2
 

More from Debmalya Biswas

Privacy Policies Change Management for Smartphones
Privacy Policies Change Management for SmartphonesPrivacy Policies Change Management for Smartphones
Privacy Policies Change Management for Smartphones
Debmalya Biswas
 

More from Debmalya Biswas (15)

Responsible Generative AI Design Patterns
Responsible Generative AI Design PatternsResponsible Generative AI Design Patterns
Responsible Generative AI Design Patterns
 
Sustainable & Composable Generative AI
Sustainable & Composable Generative AISustainable & Composable Generative AI
Sustainable & Composable Generative AI
 
Data-Driven (Reinforcement Learning-Based) Control
Data-Driven (Reinforcement Learning-Based) ControlData-Driven (Reinforcement Learning-Based) Control
Data-Driven (Reinforcement Learning-Based) Control
 
Regulating Generative AI - LLMOps pipelines with Transparency
Regulating Generative AI - LLMOps pipelines with TransparencyRegulating Generative AI - LLMOps pipelines with Transparency
Regulating Generative AI - LLMOps pipelines with Transparency
 
MLOps for Compositional AI
MLOps for Compositional AIMLOps for Compositional AI
MLOps for Compositional AI
 
A Privacy Framework for Hierarchical Federated Learning
A Privacy Framework for Hierarchical Federated LearningA Privacy Framework for Hierarchical Federated Learning
A Privacy Framework for Hierarchical Federated Learning
 
Edge AI Framework for Healthcare Applications
Edge AI Framework for Healthcare ApplicationsEdge AI Framework for Healthcare Applications
Edge AI Framework for Healthcare Applications
 
Compositional AI: Fusion of AI/ML Services
Compositional AI: Fusion of AI/ML ServicesCompositional AI: Fusion of AI/ML Services
Compositional AI: Fusion of AI/ML Services
 
Ethical AI - Open Compliance Summit 2020
Ethical AI - Open Compliance Summit 2020Ethical AI - Open Compliance Summit 2020
Ethical AI - Open Compliance Summit 2020
 
Privacy Preserving Chatbot Conversations
Privacy Preserving Chatbot ConversationsPrivacy Preserving Chatbot Conversations
Privacy Preserving Chatbot Conversations
 
Reinforcement Learning based HVAC Optimization in Factories
Reinforcement Learning based HVAC Optimization in FactoriesReinforcement Learning based HVAC Optimization in Factories
Reinforcement Learning based HVAC Optimization in Factories
 
Delayed Rewards in the context of Reinforcement Learning based Recommender ...
Delayed Rewards in the context of Reinforcement Learning based Recommender ...Delayed Rewards in the context of Reinforcement Learning based Recommender ...
Delayed Rewards in the context of Reinforcement Learning based Recommender ...
 
Building an enterprise Natural Language Search Engine with ElasticSearch and ...
Building an enterprise Natural Language Search Engine with ElasticSearch and ...Building an enterprise Natural Language Search Engine with ElasticSearch and ...
Building an enterprise Natural Language Search Engine with ElasticSearch and ...
 
Privacy-Preserving Outsourced Profiling
Privacy-Preserving Outsourced ProfilingPrivacy-Preserving Outsourced Profiling
Privacy-Preserving Outsourced Profiling
 
Privacy Policies Change Management for Smartphones
Privacy Policies Change Management for SmartphonesPrivacy Policies Change Management for Smartphones
Privacy Policies Change Management for Smartphones
 

Recently uploaded

Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
panagenda
 

Recently uploaded (20)

Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
 
ERP Contender Series: Acumatica vs. Sage Intacct
ERP Contender Series: Acumatica vs. Sage IntacctERP Contender Series: Acumatica vs. Sage Intacct
ERP Contender Series: Acumatica vs. Sage Intacct
 
AI presentation and introduction - Retrieval Augmented Generation RAG 101
AI presentation and introduction - Retrieval Augmented Generation RAG 101AI presentation and introduction - Retrieval Augmented Generation RAG 101
AI presentation and introduction - Retrieval Augmented Generation RAG 101
 
Overview of Hyperledger Foundation
Overview of Hyperledger FoundationOverview of Hyperledger Foundation
Overview of Hyperledger Foundation
 
Powerful Start- the Key to Project Success, Barbara Laskowska
Powerful Start- the Key to Project Success, Barbara LaskowskaPowerful Start- the Key to Project Success, Barbara Laskowska
Powerful Start- the Key to Project Success, Barbara Laskowska
 
ECS 2024 Teams Premium - Pretty Secure
ECS 2024   Teams Premium - Pretty SecureECS 2024   Teams Premium - Pretty Secure
ECS 2024 Teams Premium - Pretty Secure
 
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
 
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdfSimplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
 
What's New in Teams Calling, Meetings and Devices April 2024
What's New in Teams Calling, Meetings and Devices April 2024What's New in Teams Calling, Meetings and Devices April 2024
What's New in Teams Calling, Meetings and Devices April 2024
 
Integrating Telephony Systems with Salesforce: Insights and Considerations, B...
Integrating Telephony Systems with Salesforce: Insights and Considerations, B...Integrating Telephony Systems with Salesforce: Insights and Considerations, B...
Integrating Telephony Systems with Salesforce: Insights and Considerations, B...
 
WebAssembly is Key to Better LLM Performance
WebAssembly is Key to Better LLM PerformanceWebAssembly is Key to Better LLM Performance
WebAssembly is Key to Better LLM Performance
 
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
 
WSO2CONMay2024OpenSourceConferenceDebrief.pptx
WSO2CONMay2024OpenSourceConferenceDebrief.pptxWSO2CONMay2024OpenSourceConferenceDebrief.pptx
WSO2CONMay2024OpenSourceConferenceDebrief.pptx
 
Portal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russePortal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russe
 
Using IESVE for Room Loads Analysis - UK & Ireland
Using IESVE for Room Loads Analysis - UK & IrelandUsing IESVE for Room Loads Analysis - UK & Ireland
Using IESVE for Room Loads Analysis - UK & Ireland
 
Linux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdf
Linux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdfLinux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdf
Linux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdf
 
Where to Learn More About FDO _ Richard at FIDO Alliance.pdf
Where to Learn More About FDO _ Richard at FIDO Alliance.pdfWhere to Learn More About FDO _ Richard at FIDO Alliance.pdf
Where to Learn More About FDO _ Richard at FIDO Alliance.pdf
 
Long journey of Ruby Standard library at RubyKaigi 2024
Long journey of Ruby Standard library at RubyKaigi 2024Long journey of Ruby Standard library at RubyKaigi 2024
Long journey of Ruby Standard library at RubyKaigi 2024
 
The Value of Certifying Products for FDO _ Paul at FIDO Alliance.pdf
The Value of Certifying Products for FDO _ Paul at FIDO Alliance.pdfThe Value of Certifying Products for FDO _ Paul at FIDO Alliance.pdf
The Value of Certifying Products for FDO _ Paul at FIDO Alliance.pdf
 
Designing for Hardware Accessibility at Comcast
Designing for Hardware Accessibility at ComcastDesigning for Hardware Accessibility at Comcast
Designing for Hardware Accessibility at Comcast
 

Constraints Enabled Autonomous Agent Marketplace: Discovery and Matchmaking

  • 1. CONSTRAINTS ENABLED AUTONOMOUS AGENT MARKETPLACE: DISCOVERY AND MATCHMAKING DEBMALYA BISWAS, WIPRO AI
  • 2. AI AGENTS In the Generative AI context, Agents are representative of an Autonomous Agent that can execute complex tasks, e.g.,  make a sale,  plan a trip,  make a flight booking,  book a contractor to do a house job,  order a pizza.
  • 3. AI AGENTS (HIERARCHICAL) COMPOSITION Given a user task, an AI Agent aims to identify (compose) an agent (group of agents) capable of executing the given task. A high-level approach to solving such complex tasks involves:  decomposition of the given complex task into a hierarchy or workflow of) simple tasks, followed by  composition of agents able to execute the simpler tasks. This can be achieved in a dynamic or static manner.  In the dynamic approach, given a complex user task, the system comes up with a plan to fulfil the request depending on the capabilities of available agents at run-time.  In the static approach, given a set of agents, composite agents are defined manually at design- time combining their capabilities.
  • 4. AI AGENTS DISCOVERY CHALLENGES – AGENT CAPABILITIES & CONSTRAINTS The main focus of this paper is on the discovery aspect of agents, i.e., identifying the agent(s) capable of executing a given task. This implies that there exists a marketplace with a registry of agents, with a well-defined description of the agent capabilities and constraints. Capability: connects City A to B Constraint: Flies only on certain days a week; Needs payment by Credit Card
  • 5. CONTRIBUTION  AI Agents Discovery  Predicate Logic based Constraints Model  Constraints Composition  Deterministic  Non-deterministic  Agent Matchmaking
  • 6. PREDICATE LOGIC CONSTRAINTS MODEL The constraints are specified as logic predicates in the service description of the corresponding service published by its agent. An agent P provides a set of services {S1,S2, … , Sn}. Each service S in turn has a set of associated constraints {C1,C2, … ,Cm}. For each constraint C of a service S, the constraint values maybe  a single value (e.g., price of a service),  list of values (e.g., list of destinations served by an airline), or  range of values (e.g., minimum, maximum)
  • 7. CONSTRAINTS COMPOSITION Composition: two or more services offered by (the same or) different agents are composed to form a new composite service with some additional logic (if required). * D. Biswas. Generative AI Architecture Patterns. Data Driven Investor (link)
  • 8. CONSTRAINTS COMPOSITION - DETERMINISTIC We first consider deterministic composition: component services invoked in sequence or parallel. Agent M composes composite service SC from component services S1, S2, … , Sn (provided by providers P1, P2, … , Pn, respectively).
  • 9. CONSTRAINTS COMPOSITION – NON-DETERMINISTIC Accommodate non- determinism: possibility of choice among the component services.  Paths based approach  Heuristic approaches  Pessimistic  Optimistic  Probabilistic  Incremental
  • 10. AGENT MATCHMAKING  For a user task G, matchmaking consists of finding agents capable of executing G’s (sub-)tasks. The subtasks of G might have their own constraints.  Given this, the required matchmaking for G can be achieved with the help of a logic program execution engine by posing (tasks of) G’s constraints as a goal against the logic program corresponding to the service constraints of the respective agents.  A logic program execution engine specifies, not only if a goal can be satisfied, but also all the possible bindings for any unbounded variables of the goal.
  • 11. CONCLUSION  In this paper, we focused on the discovery aspect of Autonomous AI Agents.  We outlined a constraints based predicate logic model to specify agent services.  To enable hierarchical composition, we showed how the constraints of a composite agent service can be derived and described in a manner consistent with respect to the constraints of its component services.  Finally, we discussed approximate matchmaking, and showed how the notion of bounded inconsistency can be leveraged to discover agents more efficiently.