5.1 C
New York
Saturday, January 18, 2025

Databricks on Databricks – Reworking the Gross sales Expertise utilizing GenAI Brokers


At Databricks, our automation imaginative and prescient is to automate all points of the enterprise, making it higher, sooner, and cheaper.  For the gross sales groups, we’re digitally remodeling our vendor expertise by offering genAI brokers that help the vendor throughout the gross sales lifecycle.  Our objective is to reinforce the vendor expertise with AI capabilities by seamlessly integrating them into their day-to-day duties and offering an easier, simpler approach for sellers to retrieve info property in addition to orchestrate actions by automating repetitive guide administrative duties.  

Our “Area AI Assistant” is constructed on the Databricks Mosaic AI agentic framework and supplies a approach for sellers to question and work together with information throughout a number of information sources.  It integrates with a number of key platforms together with:

 

  1. Our Inside Databricks Lakehouse for account intelligence, gross sales enablement content material, and gross sales playbooks
  2. Our Buyer Relationship Administration Platform (CRM) system
  3. Our Collaboration Platform collates and indexes most of our nonstructured information

The AI utility is used to:

  • Conversationally work together with information throughout a number of information sources utilizing pure language (beginning with English)
  • Potential to obtain and create paperwork primarily based on the data gathered 
  • Take actions primarily based on the information insights (replace fields in our CRM, draft a customized outbound prospecting e-mail, create a tailored buyer proposal, prep for a buyer assembly, and so on. 

The sector assistant responds to seeded prompts primarily based on person and web page context and likewise supplies a chat-like interface for open-ended queries on the above-mentioned datasets.

Enterprise Affect 

Sellers are sometimes overwhelmed with the quantity of knowledge thrown at them.  They want entry to information residing in varied siloed purposes, as a part of their regular day-to-day routine.  They require easy accessibility to account, alternative, and use case information that resides in our CRM, in addition to buyer market insights and account intelligence, together with account consumption information that resides in our lakehouse.  As well as, additionally they want entry to gross sales content material – enablement playbooks, aggressive gross sales collateral in addition to product information base articles and product roadmap paperwork.  It isn’t simply restricted to information retrieval, however the true effectivity beneficial properties happen when the repetitive guide duties they carry out every day primarily based on the information insights they retrieve could be absolutely automated.  That’s precisely what the position of the sphere AI assistant is – assist the sellers within the day-to-day duties together with info retrieval, distilling the insights from the data, and performing actions primarily based on these insights. 

Answer Overview

Utilizing the Databricks Mosaic AI agent framework, we constructed a area AI assistant by integrating each structured and unstructured information from a number of information sources. The answer supplies a complete method personalised and tailor-made for our sellers, out there on-demand in our CRM. A few of the capabilities provided embody: 

 

Buyer insights present a 360-degree buyer account view with: 

  • Monetary information/insights concerning the account
  • Aggressive information panorama 
  • Product consumption by product line and cloud 
  • Buyer assist instances 
  • High Use Instances Driving Income
  • Vendor Suggestions on different use instances which might be provided to related clients 

Information hygiene alerts 

  • Use instances which might be going dwell within the subsequent week/month/quarter
  • High use case blockers 
  • Use instances that lack key info (ie exec enterprise sponsor and so on.)

Gross sales collateral 

  • Gross sales playbooks 
  • Aggressive collateral
  • Assembly summarization 
  • Pitch decks 

Orchestrate motion

  • Replace CRM with the subsequent steps on particular alternatives or use instances 
  • Draft a prospecting e-mail to a brand new buyer contact 
  • Create a customer-facing proposal 

 

The following screenshot shows a couple of sample responses from the field AI assistant. All data in this example summary is fictitious.
The above screenshots present a few pattern responses from the sphere AI assistant. All information on this instance abstract is fictitious.

 

Our area AI assistant answer is constructed completely on our Databricks tech stack. It permits integration into a number of and various information sources and supplies a scalable infrastructure framework for information retrieval, prompting, and LLM administration. It’s constructed utilizing the compound AI agentic framework and helps the addition of a number of instruments (SQL queries, Python capabilities) which might be all ruled by means of our Unity Catalog governance layer.

tech stack

Agent / Device Framework

Human inputs are inherently ambiguous; LLMs have now given us the flexibility to make use of context to interpret the intent of a request and convert this into one thing extra deterministic. To service the request, it is likely to be essential to retrieve particular information, execute code, and apply a reasoning framework primarily based on beforehand realized transformation. All of this info have to be reassembled right into a coherent output that’s formatted accurately for whomever (or no matter) will devour it.  

That’s precisely what the sphere AI assistant does to reply to the queries from the sellers.  The sector AI assistant has 1 driver agent and a number of instruments and capabilities that carry out the deterministic processing.  

  • Information basis:  That is the set of information sources that the agent interacts with.  In our answer, this information basis consists of information in our Lakehouse, gross sales collateral, Google docs in addition to information that resides in our CRM (Salesforce). 
  • Deterministic processing: The set of capabilities and instruments required to provide appropriate, high-quality responses. The LLM can extract fields from a question and move these to a regular operate name to do deterministic processing. Inside the Databricks Platform, the Mosaic AI Instruments and Capabilities capabilities allow this and user-defined capabilities can carry out most actions inside Databricks. These could be sometimes Python capabilities or easy SQL queries or APIs that combine with exterior apps reminiscent of Glean, Perplexity, Aha and so on. and these could be invoked utilizing pure language.
  • LLM fashions: We leverage Azure OpenAI, GPT 4 because the foundational mannequin for the sphere AI assistant answer. That stated, the framework helps a multi-model method the place the precise capabilities of every mannequin is evaluated with respect to the way it offers with particular use instances. For e.g. now we have evaluated our answer with varied open supply fashions and we selected Azure Open AI – GPT 4 because the mannequin for our answer primarily based on the groundedness of the mannequin, its potential to generate factual and related content material, its potential to choose the precise user-defined operate / instrument for processing every immediate, and its potential to stick to the content material output formatting prompting supplied to the mannequin.  

That stated, our answer structure is designed to permit for flexibility in adopting new fashions as they develop into out there in our Mosaic AI agent framework. 

At Databricks, now we have leveraged the Mosaic AI Agent Framework which makes it straightforward to construct a genAI utility like the sphere AI assistant. Utilizing this framework, now we have outlined analysis standards and we leverage LLM-as-a-judge functionality to attain the appliance responses. The Mosaic AI Gateway supplies entry controls, charge limiting, payload logging, and guardrails (filtering for system inputs and outputs). The gateway provides the person fixed monitoring of operating techniques to observe for security, bias, and high quality. 

The parts that we leveraged for our area AI assistant are:

Answer Structure

solution architecture

Our Learnings

Information is messyLeveraged Lakehouse,  iterative enlargement of datasets, targeted on data-engineered pipelines and constructing clear, GOLD Single Supply of Reality datasets 

 

Measuring ROI is troublesomeBe ready to experiment with small focus teams within the pilot. Constructing analysis datasets for measuring mannequin effectiveness is tough and requires targeted effort and a method that helps speedy experimentation

 

Information and AI Governance is a MUSTInteract early with Enterprise Safety, Privateness, and Authorized groups. Construct a powerful governance mannequin on Unity Catalog for the information in addition to the brokers and instruments 

Conclusion

By this submit, we hope you realized about our Databricks on Databrick’s GenAI journey and the way we leverage know-how like this to assist our sellers be simpler.  Using GenAI for this use case has helped to showcase how AI brokers can considerably remodel and help each facet of the vendor journey, from prospecting and buyer insights retrieval, driving higher information hygiene by automating repetitive guide duties and actioning these information insights to driving alternatives and bettering gross sales velocity. 

Keep tuned for our upcoming posts, the place we’ll proceed to share our experiences on how AI is reshaping the vendor expertise at Databricks.

Related Articles

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Latest Articles