How Planview constructed a scalable AI Assistant for portfolio and venture administration utilizing Amazon Bedrock

This publish is co-written with Lee Rehwinkel from Planview.

Companies in the present day face quite a few challenges in managing intricate initiatives and applications, deriving helpful insights from huge information volumes, and making well timed choices. These hurdles continuously result in productiveness bottlenecks for program managers and executives, hindering their capacity to drive organizational success effectively.

Planview, a number one supplier of linked work administration options, launched into an formidable plan in 2023 to revolutionize how 3 million world customers work together with their venture administration functions. To understand this imaginative and prescient, Planview developed an AI assistant referred to as Planview Copilot, utilizing a multi-agent system powered by Amazon Bedrock.

Creating this multi-agent system posed a number of challenges:

• Reliably routing duties to acceptable AI brokers
• Accessing information from numerous sources and codecs
• Interacting with a number of software APIs
• Enabling the self-serve creation of latest AI expertise by completely different product groups

To beat these challenges, Planview developed a multi-agent structure constructed utilizing Amazon Bedrock. Amazon Bedrock is a completely managed service that gives API entry to foundation models (FMs) from Amazon and different main AI startups. This permits builders to decide on the FM that’s greatest suited to their use case. This method is each architecturally and organizationally scalable, enabling Planview to quickly develop and deploy new AI expertise to fulfill the evolving wants of their clients.

This publish focuses totally on the primary problem: routing duties and managing a number of brokers in a generative AI structure. We discover Planview’s method to this problem through the growth of Planview Copilot, sharing insights into the design choices that present environment friendly and dependable job routing.

We describe custom-made home-grown brokers on this publish as a result of this venture was applied earlier than Amazon Bedrock Agents was usually accessible. Nevertheless, Amazon Bedrock Agents is now the really useful resolution for organizations wanting to make use of AI-powered brokers of their operations. Amazon Bedrock Brokers can retain reminiscence throughout interactions, providing extra personalised and seamless person experiences. You’ll be able to profit from improved suggestions and recall of prior context the place required, having fun with a extra cohesive and environment friendly interplay with the agent. We share our learnings in our resolution that will help you understanding find out how to use AWS know-how to construct options to fulfill your targets.

Resolution overview

Planview’s multi-agent structure consists of a number of generative AI parts collaborating as a single system. At its core, an orchestrator is accountable for routing questions to varied brokers, accumulating the discovered info, and offering customers with a synthesized response. The orchestrator is managed by a central growth crew, and the brokers are managed by every software crew.

The orchestrator contains two fundamental parts referred to as the router and responder, that are powered by a large language model (LLM). The router makes use of AI to intelligently route person questions to varied software brokers with specialised capabilities. The brokers may be categorized into three fundamental sorts:

• Assist agent – Makes use of Retrieval Augmented Generation (RAG) to supply software assist
• Knowledge agent – Dynamically accesses and analyzes buyer information
• Motion agent – Runs actions throughout the software on the person’s behalf

After the brokers have processed the questions and offered their responses, the responder, additionally powered by an LLM, synthesizes the discovered info and formulates a coherent response to the person. This structure permits for a seamless collaboration between the centralized orchestrator and the specialised brokers, which gives customers an correct and complete solutions to their questions. The next diagram illustrates the end-to-end workflow.

Technical overview

Planview used key AWS companies to construct its multi-agent structure. The central Copilot service, powered by Amazon Elastic Kubernetes Service (Amazon EKS), is accountable for coordinating actions among the many numerous companies. Its duties embrace:

• Managing person session chat historical past utilizing Amazon Relational Database Service (Amazon RDS)
• Coordinating site visitors between the router, software brokers, and responder
• Dealing with logging, monitoring, and accumulating user-submitted suggestions

The router and responder are AWS Lambda features that work together with Amazon Bedrock. The router considers the person’s query and chat historical past from the central Copilot service, and the responder considers the person’s query, chat historical past, and responses from every agent.

Utility groups handle their brokers utilizing Lambda features that work together with Amazon Bedrock. For improved visibility, analysis, and monitoring, Planview has adopted a centralized immediate repository service to retailer LLM prompts.

Brokers can work together with functions utilizing numerous strategies relying on the use case and information availability:

• Present software APIs – Brokers can talk with functions by means of their current API endpoints
• Amazon Athena or conventional SQL information shops – Brokers can retrieve information from Amazon Athena or different SQL-based information shops to supply related info
• Amazon Neptune for graph information – Brokers can entry graph information saved in Amazon Neptune to assist complicated dependency evaluation
• Amazon OpenSearch Service for doc RAG – Brokers can use Amazon OpenSearch Service to carry out RAG on paperwork

The next diagram illustrates the generative AI assistant structure on AWS.

Router and responder pattern prompts

The router and responder parts work collectively to course of person queries and generate acceptable responses. The next prompts present illustrative router and responder immediate templates. Further immediate engineering can be required to enhance reliability for a manufacturing implementation.

First, the accessible instruments are described, together with their function and pattern questions that may be requested of every instrument. The instance questions assist information the pure language interactions between the orchestrator and the accessible brokers, as represented by instruments.

instruments=""'

applicationHelp

Use this instrument to reply software assist associated questions.
Instance questions:
How do I reset my password?
How do I add a brand new person?
How do I create a job?



dataQuery

Use this instrument to reply questions utilizing software information.
Instance questions:
Which duties are assigned to me?
What number of duties are due subsequent week?
Which job is most in danger?

Subsequent, the router immediate outlines the rules for the agent to both reply on to person queries or request info by means of particular instruments earlier than formulating a response:

system_prompt_router = f'''

Your job is to resolve should you want extra info to completely reply the Person's 
questions.
You obtain your purpose by selecting both 'reply' or 'callTool'.
You could have entry to your chat historical past in  tags.
You even have an inventory of obtainable instruments to help you in  tags.


{chatHistory}


{instruments}


- If the chat historical past comprises enough info to reply the Person's questions, 
select the 'reply' motion.
- To assemble extra info earlier than responding, select the 'callTool' motion.
- You a lot solely select from the instruments within the  tags.
- If no instrument can help with the query, select the 'reply' motion.
- Place your chosen motion inside  tags.
- While you selected the 'callTool' motion, present the  and the  you
wish to ask.
- Your  must be verbose and keep away from utilizing pronouns.
- Begin by offering your step-by-step considering in  tags.
- Then you'll give your reply in  tags.
- Your reply ought to observe the format of one among these three examples:
When selecting the 'reply' motion, your reply ought to observe the beneath instance EXACTLY:


reply


When selecting the 'callTool' motion for a single Instrument:


callTool


applicationHelp
How do I reset my password?




Executing the above, would produce the next end result:
It's also possible to name a number of Instruments utilizing this format:


callTool


dataQuery
What number of duties are assigned to me?


applicationHelp
How do I add a brand new job?





'''

The next is a pattern response from the router element that initiates the dataQuery instrument to retrieve and analyze job assignments for every person:

To find out who has essentially the most duties assigned, I might want to question the appliance information. The "dataQuery" instrument appears most acceptable for this query.



callTool

    
        dataQuery
        Which person has essentially the most duties at present assigned to them?   
    

The next is a pattern response from the responder element that makes use of the dataQuery instrument to fetch details about the person’s assigned duties. It reviews that the person has 5 duties assigned to them.

Primarily based on the chat historical past, I beforehand referred to as the dataQuery instrument to ask "What number of duties are at present assigned to the person?". The instrument responded that the person has 5 duties assigned to them.



In keeping with the information I queried beforehand, you have got 5 duties assigned to you.

Mannequin analysis and choice

Evaluating and monitoring generative AI mannequin efficiency is essential in any AI system. Planview’s multi-agent structure permits evaluation at numerous element ranges, offering complete high quality management regardless of the system’s complexity. Planview evaluates parts at three ranges:

• Prompts – Assessing LLM prompts for effectiveness and accuracy
• AI brokers – Evaluating full immediate chains to keep up optimum job dealing with and response relevance
• AI system – Testing user-facing interactions to confirm seamless integration of all parts

The next determine illustrates the analysis framework for prompts and scoring.

To conduct these evaluations, Planview makes use of a set of fastidiously crafted take a look at questions that cowl typical person queries and edge circumstances. These evaluations are carried out through the growth section and proceed in manufacturing to trace the standard of responses over time. Presently, human evaluators play an important function in scoring responses. To help within the analysis, Planview has developed an inside analysis instrument to retailer the library of questions and observe the responses over time.

To evaluate every element and decide essentially the most appropriate Amazon Bedrock mannequin for a given job, Planview established the next prioritized analysis standards:

• High quality of response – Assuring accuracy, relevance, and helpfulness of system responses
• Time of response – Minimizing latency between person queries and system responses
• Scale – Ensuring the system can scale to hundreds of concurrent customers
• Value of response – Optimizing operational prices, together with AWS companies and generative AI fashions, to keep up financial viability

Primarily based on these standards and the present use case, Planview chosen Anthropic’s Claude 3 Sonnet on Amazon Bedrock for the router and responder parts.

Outcomes and affect

Over the previous yr, Planview Copilot’s efficiency has considerably improved by means of the implementation of a multi-agent structure, growth of a sturdy analysis framework, and adoption of the most recent FMs accessible by means of Amazon Bedrock. Planview noticed the next outcomes between the primary era of Planview Copilot developed mid-2023 and the most recent model:

• Accuracy – Human-evaluated accuracy has improved from 50% reply acceptance to now exceeding 95%
• Response time – Common response instances have been diminished from over 1 minute to twenty seconds
• Load testing – The AI assistant has efficiently handed load assessments, the place 1,000 questions have been submitted simultaneous with no noticeable affect on response time or high quality
• Value-efficiency – The associated fee per buyer interplay has been slashed to at least one tenth of the preliminary expense
• Time-to-market – New agent growth and deployment time has been diminished from months to weeks

Conclusion

On this publish, we explored how Planview was capable of develop a generative AI assistant to handle complicated work administration course of by adopting the next methods:

• Modular growth – Planview constructed a multi-agent structure with a centralized orchestrator. The answer permits environment friendly job dealing with and system scalability, whereas permitting completely different product groups to quickly develop and deploy new AI expertise by means of specialised brokers.
• Analysis framework – Planview applied a sturdy analysis course of at a number of ranges, which was essential for sustaining and enhancing efficiency.
• Amazon Bedrock integration – Planview used Amazon Bedrock to innovate sooner with broad mannequin alternative and entry to varied FMs, permitting for versatile mannequin choice primarily based on particular job necessities.

Planview is migrating to Amazon Bedrock Brokers, which permits the combination of clever autonomous brokers inside their software ecosystem. Amazon Bedrock Brokers automate processes by orchestrating interactions between basis fashions, information sources, functions, and person conversations.

As subsequent steps, you’ll be able to discover Planview’s AI assistant feature constructed on Amazon Bedrock and keep up to date with new Amazon Bedrock features and releases to advance your AI journey on AWS.

About Authors

Sunil Ramachandra is a Senior Options Architect enabling hyper-growth Impartial Software program Distributors (ISVs) to innovate and speed up on AWS. He companions with clients to construct extremely scalable and resilient cloud architectures. When not collaborating with clients, Sunil enjoys spending time with household, operating, meditating, and watching motion pictures on Prime Video.

Benedict Augustine is a thought chief in Generative AI and Machine Studying, serving as a Senior Specialist at AWS. He advises buyer CxOs on AI technique, to construct long-term visions whereas delivering rapid ROI.As VP of Machine Studying, Benedict spent the final decade constructing seven AI-first SaaS merchandise, now utilized by Fortune 100 corporations, driving vital enterprise affect. His work has earned him 5 patents.

Lee Rehwinkel is a Principal Knowledge Scientist at Planview with 20 years of expertise in incorporating AI & ML into Enterprise software program. He holds superior levels from each Carnegie Mellon College and Columbia College. Lee spearheads Planview’s R&D efforts on AI capabilities inside Planview Copilot. Exterior of labor, he enjoys rowing on Austin’s Woman Chook Lake.