Tasq v6 Beta Release

We’ve been quietly working on something big. On December 7th, we’ll release Tasq v6 (beta) — and it redefines what agentic truly means for time-series based operations.

The reason we went down agentic:

1. Integration is easier for clients

2. Accuracy of prompt results improves

3. Tasqs’ “Build your own model” as an agent is the path we want to dive further into and what has taken off as of late

The basis of this release is improving 3 core areas of the business. Current client satisfaction, enabling company growth & building more around our core differentiator. 

1. Integration:

Agentic means easier and quicker “no hands” integration. Integrated right into Teams, enables low barrier use & reduces onboarding friction. This means we are simplifying user workflows vs the current applications in use. We have made it so easy that users do not need any touchpoints before onboarding, everything is automated to give you insights on the first minute of onboarding.

Connect to db > Tasq Agent Spun up > @Tasq in Teams to give you AI instantly at your fingertips. 

This is the future of trials, and will enable quicker iteration for the client. Technology groups are now enabled. Before, technology groups within Oil and Gas were a weight on the business unit, offering a roundtable of new technology that might not solve the end users current painpoints. Now, trials can be 30 minutes with technology groups offering up the “finalized technology” to the end users, making that group more useful, and enabling higher iteration. 3-6 month trials are a thing of the past, Integration is no longer a barrier for iterating with new technology.

2. Accuracy of prompt results improves

For the past year our Tasq v5 AI Data Analyst has been a key feature that gets a lot of use. Type anything into it, and Tasq automatically generates code to retrieve the necessary information. We have noticed a lot of use cases from it, but we have also noticed a higher than desired false positive rate from it. Questions like “show me all wells with increasing line pressure and casing pressure by 2% a week” retrieve varying results. 

One-shot AI was tough to nail down. Time-series data isn’t static text, it’s live, contextual, and interconnected. Most AI is missing the mark with time series accuracy, mainly due to context, systems just can't reason across it. With evals, test loops, training data, the hope is the SQL generator nails it, but the reality is sometimes it did; sometimes it didn’t. This was down to a few reasons. 

• Latency limits & avoiding timeouts due to poorly optimized queries

• Db specific syntax leading to erroneous code

• Added context bloat to the training data

• Post code/results return, there was still follow up from the user to tweak the results

• Reliability in the same prompt varied even with proper training data

Over the past six months, we’ve been testing Tasq’s fully agentic system side-by-side with legacy code gen SQL-prompt versions. The results are a massive improvement. This coordination with Tasq’s “Signal Search” is the breakthrough. It’s why our accuracy jumped from 50% to 80% with an 8x wider cases! The chain of thought, context engineering, memory & agents all thinking together before answering. They validate, test, and refine together. You’re not getting a hasty SQL hallucination, you’re getting transformation without having to do anything more.

3. Build your own model as an agent is the path we want to dive further into and what has taken off as of late

Agentic means: Building the best in class capabilities for searching time series data. We have also expanded the capabilities of how this works with other Agents.

• Multiple agents that work together to bring the right results embedding the right context in each prompt

• Agents that invoke models, graphs, maps, and recommendations, not just code.

• Agents trained specifically on oil & gas models, physics-based models, statistical inference, signal search, pattern matching all working together.

Searching signals & patterns is transformational for users to build their own models. Agentic system built around this is very powerful. It enables better search, better workflows, better recommendations and everything to be more accurate. 

Easier ways to trigger build your model, analyze results from it, connect it to downstream applications is a focus of ours. We had a lot of success with Tasq 5.0 and the ability to build your own models. We are going deeper here. Connecting agents to build your own model enables users to have the most workflows out of the model results. An agentic experience with time series data and building models is unique. 

We have built agents to enable downstream actions and workflows with other agents that work to  integrate at any steps of a downstream process, whether it is an internal workflow tool, third party mapping “

Summary:

There is so much more to time series search than SQL. Time series search has not been solved at scale and is the unlock to most workflows in operations.. Platforms like Pi, snowflake and such do not have the capabilities, context, & ability to create models like Tasq does. On the other hand, platforms like Palentir are great data connectors & workflows, but lack the industry intelligence that Tasq offers. 

For time-series data whether it's to build a model, analyze events, pattern match, summarize performance, assign tasks, or automate workflows, Tasq v6 does it faster and with more intelligence than anyone else.

AI is moving fast. Quality and differentiation matter. More accurate, more value, & integrated into any downstream system, Tasq is the utilization layer that enables operations. We continue to put innovation first to be ahead of the cycle. We are excited to share more about our benchmarks as we release Tasq v6.

Reach out if you are interested in taking it for a test drive.

Wes