Redbird supercharges analytics pipeline with AI brokers, handles 90% of workload

Simply as enterprises proceed to undertake giant language model-powered text-to-SQL as a method to ‘talk’ to their knowledge belongings, a new shift within the ecosystem has began rising: AI brokers. At this time, New York-based Redbird introduced a brand new chat platform that makes use of “specialist agents” to assist enterprises deal with most analytics worth chain duties, from knowledge assortment and engineering to knowledge science and producing precise insights (reporting).

This implies an enterprise consumer can provide a pure language immediate to get insights from knowledge in nearly real-time and execute analytical efforts that pave the best way for these insights. Based on Erin Tavgac, the co-founder and CEO of the corporate, this represents greater than 90% of an enterprise’s enterprise intelligence efforts.

“For the past several decades the promise of truly self-serve analytics has fallen short for organizations, with the reality instead being complex data pipelines, dashboards, and shadow analytics that require technical skills. We have invested significant R&D into fusing the power of LLMs with Redbird’s robust end-to-end analytical toolkit in the form of AI agents that enable users to finally achieve self-serve, conversational BI that runs on their organization’s data,” he mentioned in a press release.

Transferring into the age of AI brokers

Whereas the age of AI brokers is new, Redbird itself has been a long-standing participant within the analytics area. The corporate began in 2018 as Dice Analytics and supplied enterprises with a no-code, drag-and-drop toolkit that enabled their customers to create workflows geared toward automating and unifying all analytical duties resulting in dashboarding and insights. Earlier this yr, the corporate expanded this work with the launch of a conversational interface, permitting customers to ask enterprise questions in pure language and obtain insights and reporting outputs in real-time.

Now, as the following step, Redbird has added an ecosystem of specialised brokers that function on prime of this end-to-end toolkit to orchestrate in addition to execute multi-step analytical duties to reply business-related questions.  

As Tavgac defined, admins establishing the chat platform have to decide on a base LLM (like GPT, Llama and so on) and cargo up their group’s proprietary knowledge ontologies, enterprise logic and reporting blueprints (like enterprise definitions, PowerPoint report templates, and so on.) to customise it with related enterprise context. As soon as the info is inputted, the AI brokers utilizing the LLM start to make use of all of the context and generate metadata from the knowledge to do their work  — in response to consumer questions.

“User prompts are sent to Redbird routing agents, which identify the best specialist agents to execute the tasks for that prompt (like PowerPoint Reporting agent, Data Engineering agent, etc.) and figure out how to orchestrate the execution order of those agents. Each specialist agent then manages its own part of the overall task by identifying relevant datasets/ontologies and executing the needed task using the Redbird toolkit, which includes applications and functions to handle the mechanical steps of the pipeline,”  Tavgac famous.

Detailing the duties, he famous Redbird brokers can pull unstructured or structured knowledge from over 100 knowledge sources, together with Snowflake, Databricks and Hubspot. It will probably run superior processing on prime of the collected knowledge by performing knowledge wrangling, AI-driven tagging and knowledge science modeling. It will probably additionally generate sturdy reporting outputs (like shows, Excel studies and e mail/Slack updates) whereas taking vital actions based mostly on these studies (like executing an advert purchase/modifying a marketing campaign).

“Once the task is executed, the chat platform responds to the user with not just a text answer but also any deliverables needed, like a PowerPoint report the agents built or the data that they collected from a SaaS system,” he mentioned.

No-code workflow orchestration stays accessible

As enterprises double down on their knowledge efforts, going past text-to-SQL — adopted by Dremio, Snowflake and plenty of others – and streamlining the analytics pipeline end-to-end with AI brokers could possibly be a good way to avoid wasting time and assets. 

Nonetheless, as many should still have issues over the reliability of AI brokers, Redbird is just not removing its unique drag-and-drop interface for automating enterprise intelligence workflows. As a substitute, the corporate has made no-code the secondary choice for customers. The brokers will orchestrate the duties whereas additionally making a no-code model of the workflow, permitting customers to audit and examine every little thing intimately if required. 

“So far, existing AI solutions have primarily tackled the automation of a very small fraction of BI and analytics efforts (SQL querying). While Redbird values and solves for that use case (text-to-SQL), it is also applying the power of its AI agents to automate the other more difficult and more sizable parts of enterprise BI workflows… Our approach to solving this challenge has enabled us to onboard eight of the Fortune 50 brands and over 30 mid-to-large-sized enterprise customers in the last few months,” Tavgac added. This consists of manufacturers like Mondelez Worldwide, USA At this time, Bobcat Firm and Johnson & Johnson.

At present, he mentioned the corporate is providing its expertise on a SaaS mannequin with usage-based licensing charges and producing seven-figure income. Nonetheless, he didn’t share the precise specifics.

As the following step, Redbird will proceed its AI agent-driven work and take its new Chat platform to extra enterprises. It additionally plans so as to add extra superior brokers within the analytics worth chain to allow even deeper AI-powered enterprise intelligence protection for non-technical customers. 

“We additionally intention to increase past our major concentrate on analytics / BI use instances and right into a deeper ‘Large Action Model’ strategy that leverages AI brokers that may take extra nuanced motion based mostly on the analytical outcomes (i.e. buy provides, ship invoices).