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

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

Companies as we speak face quite a few challenges in managing intricate tasks and applications, deriving beneficial insights from large information volumes, and making well timed choices. These hurdles ceaselessly result in productiveness bottlenecks for program managers and executives, hindering their potential to drive organizational success effectively.

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

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

• Reliably routing duties to applicable AI brokers
• Accessing information from numerous sources and codecs
• Interacting with a number of utility APIs
• Enabling the self-serve creation of recent 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 totally managed service that gives API entry to basis fashions (FMs) from Amazon and different main AI startups. This enables builders to decide on the FM that’s finest suited to their use case. This method is each architecturally and organizationally scalable, enabling Planview to quickly develop and deploy new AI expertise to satisfy 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 in the course of the improvement of Planview Copilot, sharing insights into the design choices that present environment friendly and dependable process routing.

We describe personalized home-grown brokers on this publish as a result of this undertaking was applied earlier than Amazon Bedrock Brokers was usually obtainable. Nevertheless, Amazon Bedrock Brokers is now the advisable answer for organizations trying to make use of AI-powered brokers of their operations. Amazon Bedrock Brokers can retain reminiscence throughout interactions, providing extra personalised and seamless consumer experiences. You may 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 answer that can assist you understanding use AWS know-how to construct options to satisfy 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 realized info, and offering customers with a synthesized response. The orchestrator is managed by a central improvement staff, and the brokers are managed by every utility staff.

The orchestrator includes two primary parts known as the router and responder, that are powered by a giant language mannequin (LLM). The router makes use of AI to intelligently route consumer questions to varied utility brokers with specialised capabilities. The brokers will be categorized into three primary varieties:

• Assist agent – Makes use of Retrieval Augmented Technology (RAG) to supply utility assist
• Information agent – Dynamically accesses and analyzes buyer information
• Motion agent – Runs actions inside the utility on the consumer’s behalf

After the brokers have processed the questions and supplied their responses, the responder, additionally powered by an LLM, synthesizes the realized info and formulates a coherent response to the consumer. 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 providers 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 providers. Its duties embody:

• Managing consumer session chat historical past utilizing Amazon Relational Database Service (Amazon RDS)
• Coordinating visitors between the router, utility 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 consumer’s query and chat historical past from the central Copilot service, and the responder considers the consumer’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:

• Current utility APIs – Brokers can talk with functions by way 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 help 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 consumer queries and generate applicable 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 obtainable instruments are described, together with their objective and pattern questions that may be requested of every software. The instance questions assist information the pure language interactions between the orchestrator and the obtainable brokers, as represented by instruments.

instruments=""'

applicationHelp

Use this software to reply utility assist associated questions.
Instance questions:
How do I reset my password?
How do I add a brand new consumer?
How do I create a process?



dataQuery

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

Subsequent, the router immediate outlines the rules for the agent to both reply on to consumer queries or request info by way 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 have got entry to your chat historical past in  tags.
You even have a listing of accessible instruments to help you in  tags.


{chatHistory}


{instruments}


- If the chat historical past incorporates 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 software 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
want to ask.
- Your  needs to 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 comply with the format of one among these three examples:
When selecting the 'reply' motion, your reply ought to comply with the beneath instance EXACTLY:


reply


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


callTool


applicationHelp
How do I reset my password?




Executing the above, would produce the next end result:
You may also 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 process?





'''

The next is a pattern response from the router element that initiates the dataQuery software to retrieve and analyze process assignments for every consumer:

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



callTool

    
        dataQuery
        Which consumer has probably the most duties presently assigned to them?   
    

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

Primarily based on the chat historical past, I beforehand known as the dataQuery software to ask "What number of duties are presently assigned to the consumer?". The software responded that the consumer has 5 duties assigned to them.



In line with the information I queried beforehand, you may have 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 process 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 rigorously crafted take a look at questions that cowl typical consumer queries and edge instances. These evaluations are carried out in the course of the improvement part and proceed in manufacturing to trace the standard of responses over time. At present, human evaluators play a vital position in scoring responses. To assist within the analysis, Planview has developed an inside analysis software to retailer the library of questions and observe the responses over time.

To evaluate every element and decide probably the most appropriate Amazon Bedrock mannequin for a given process, 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 consumer queries and system responses
• Scale – Ensuring the system can scale to 1000’s of concurrent customers
• Price of response – Optimizing operational prices, together with AWS providers 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 influence

Over the previous 12 months, Planview Copilot’s efficiency has considerably improved by way of the implementation of a multi-agent structure, improvement of a strong analysis framework, and adoption of the newest FMs obtainable by way of Amazon Bedrock. Planview noticed the next outcomes between the primary era of Planview Copilot developed mid-2023 and the newest model:

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

Conclusion

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

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

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

As subsequent steps, you’ll be able to discover Planview’s AI assistant function constructed on Amazon Bedrock and keep up to date with new Amazon Bedrock options 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 instant 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 influence. His work has earned him 5 patents.

Lee Rehwinkel is a Principal Information 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. Outdoors of labor, he enjoys rowing on Austin’s Woman Chook Lake.