From Gross sales Dilemma to Knowledge-Pushed Motion
Even the very best business presents are solely as efficient as their supply. At Databricks, we offer free credit score presents to assist prospects get began or speed up adoption, however gross sales representatives face a deceptively easy query: which of my buyer accounts are eligible, and which ought to I attain out to first?
What looks as if an easy process will be opaque and shortly flip right into a time-consuming, multi-team effort, particularly when accounts are unexpectedly ineligible for presents. Gross sales groups usually must dig by way of documentation, seek the advice of Slack threads, and manually examine accounts with operations groups. This creates pointless back-and-forth, slows down momentum, and will get in the best way of offering prospects with high-value presents. Even when accounts are recognized to be eligible, it’s not all the time apparent which ought to be prioritized.
Constructing a Smarter System with Agent Bricks
To sort out the issue, our workforce turned to Agent Bricks — Databricks’ platform for constructing high-quality AI brokers on enterprise knowledge — and constructed a multi-agent system that delivers clear, actionable steering on to gross sales groups. In lower than two days, I created a instrument that lets gross sales reps:
- Rapidly determine which buyer accounts qualify for credit score presents
- Perceive the precise purpose an account isn’t eligible
- Rank eligible accounts to deal with the highest-impact prospects first
As an intern in Enterprise Technique and Operations this summer time, I had a brief turnaround time, so velocity and ease have been vital. Agent Bricks let me shortly construct a high-quality resolution and supply the enablement gross sales groups wanted.
Designing the Multi-Agent Answer
Utilizing Agent Bricks’ Multi-Agent Supervisor, I designed a system that chains collectively three purpose-built brokers below one supervisor. Like an air-traffic controller, the Supervisor decides which agent to delegate every a part of the query to after which stitches their responses into one clear reply.
One Supervisor, Three Specialised Brokers
My resolution makes use of three brokers: two AI/BI Genie brokers and a Information Assistant agent, managed by a supervisor to orchestrate duties and knowledge circulation:
1. Provide Particulars Agent utilizing Information Assistant
This agent is skilled on our unstructured inner supply documentation (PDFs, slide decks) to deeply perceive supply guidelines, eligibility necessities, and the supply outreach and supply course of. Since Information Assistant can take paperwork of their present type, I didn’t should do any further work to parse, chunk, or embed this data.
2. Provide Eligibility Agent utilizing AI/BI Genie
This agent analyzes structured buyer account knowledge, ruled in Unity Catalog, to find out which prospects qualify for particular presents and, simply as importantly, why others don’t. The agent can floor the particular eligibility requirement(s) that an account doesn’t meet and counsel follow-up steps if a gross sales rep desires to troubleshoot this additional. To assist the agent stroll by way of the eligibility course of, the info desk consists of columns related to every of the eligibility standards.
3. Account Prioritization Agent utilizing AI/BI Genie
This agent appears at structured GTM knowledge to rank eligible accounts utilizing utilization knowledge, progress indicators, and supply relevance. Gross sales groups get a transparent, prioritized record of who to contact first.
Without having to analysis supervisor agent structure or interact with technical groups, I used to be capable of construct a practical AI agent system instantly on our buyer knowledge and supply program paperwork.
From Handbook Requests to Self-Serve Insights
The multi-agent resolution removes guesswork and creates a seamless, explainable expertise. By combining structured buyer knowledge with unstructured supply program data, the system permits:
- Self-serve eligibility troubleshooting: As a substitute of routing by way of a number of groups and Slack threads, gross sales groups can now shortly perceive supply eligibility points and take knowledgeable motion instantly, due to built-in explanations
- Extra clever focusing on: Gross sales groups can deal with high-value accounts based mostly on actual progress indicators and supply relevance, not hunches, streamlining how they determine high-impact alternatives
- Quicker outreach: By rising supply understandability and lowering guide friction, the response SLA decreases from 48 hours to below 5 seconds, and gross sales groups can transfer extra shortly and confidently
Most significantly, the system scales as accounts are added and extra presents are created. Buyer account and GTM insights replace robotically when the reference knowledge in Unity Catalog modifications, and new supply applications will be supported by updating the paperwork within the information base – with no new code required.
Limitations
Whereas the present system is highly effective, there are a couple of limitations to notice:
- Agent Overlap: As a result of the brokers can’t instantly share context, sure items of data wanted to be duplicated throughout them, regardless that the supervisor “is aware of all.” For instance, the Account Prioritization agent’s knowledge desk features a column indicating which provide – if any – every account is eligible for (already recognized to the Eligibility agent). It additionally incorporates context in regards to the utilization eligibility bands for every supply sort (already recognized to the Provide Particulars agent). This duplication ensures the Prioritization agent can purpose about focusing on and rank accounts accurately.
- Person Workflow Integration: Most gross sales groups work primarily in Slack and Salesforce, not Databricks. Integrating this technique as a Slackbot or into Salesforce would put eligibility particulars and steering instantly into their on a regular basis workflows.
Conclusion
Industrial presents solely work if gross sales groups know who to focus on — and why. Earlier than Agent Bricks, this was a guide, multi-team problem that slowed down outreach and launched ambiguity into our applications. With Agent Bricks, we have been capable of construct, check, and refine a multi-agent AI system with nothing extra in hand than our knowledge and our aim.
Although our system has a couple of limitations in its present type and isn’t embedded within the instruments gross sales groups use every day, the features have already been significant; it’s made supply focusing on sooner, extra clear, and extra scalable. The actual magic lies within the prioritization of accounts: the system robotically aggregates buyer knowledge and supply data to intelligently floor the highest-impact alternatives first, and I didn’t even have to inform the agent precisely methods to do it. Now that’s knowledge intelligence.
Get began constructing with Agent Bricks and create your first resolution at present.
