Athenic 2.0 - A faster, smarter Athenic. Analyze on autopilot.
by•
Athenic is an AI agent for analyzing data and automating work. Connect your data, chat in plain English, and ship dashboards, reports, and automations. Built for startups to Fortune 500.
Replies
Athenic AI
👋 Hey, Product Hunt, long time no see!
We first launched Athenic in 2023, and a lot has changed since.
Most "chat with your data" tools (Athenic 1.0 included) stop at an answer. Athenic 2.0 keeps going: it builds the dashboard, writes the report, and re-runs analyses on schedule — ask once, not every Monday.
Here's what's new:
Automations — recurring analyses delivered to your inbox
Business apps — connect your CRM, ERP, paid media channels & more, not just SQL databases
Agentic Web research — Athenic monitors your competitors and surfaces market trends on its own
Improved Charting — build full dashboards though chat, with more chart types and customizations
New usage-based pricing too, pay only for what you use. 2,000 free credits to start, no credit card required.
Happy to answer any questions and always grateful for feedback. What's the first thing you'd put on autopilot? 👇
— Jared
@jared_zhao As a data anylyst ,upgrading from just SQL databases to ERP and CRM data is a huge hurdle cleared. Data centralization is always the hardest part of these tools. How does Athenic handle data modeling/cleaning across those different business apps? love the idea
Athenic AI
@priya_kushwaha1 Thanks Priya! We noticed that many companies don't have data pipelines & data warehouses yet, which is why we decided to offer both as part of Athenic, in order to allow direct connections to business apps.
To answer your question about data modeling / cleaning - we have a "Data Engineering Agent" which works by taking in 1) your instructions and 2) examples of correct number (e.g., what was the revenue last year, how many prospects last month), and it works backwards to create the correct data model. Updating the model is easy as well - you can just tell the agent to add or update definitions.
@jared_zhao looks solid, good luck for the launch
the agentic data analyst framing implies the agent takes initiative rather than just responding. curious what the actual agent behavior looks like in practice. does it proactively flag anomalies in connected data, suggest analyses you haven't asked for, or is the agent label more about multi-step reasoning within a query than about autonomous action between sessions. the distinction matters a lot for how people would integrate this into their workflows
Athenic AI
@ansari_adin Hi, yes, the distinction is important and Athenic is capable of both. During your sessions Athenic will do multi step reasoning and suggest alternate analysis paths. It will also suggest automations or you can create them yourself. So you can do things like anomaly detection where it only emails you if it finds something interesting or if it crosses a threshold. Or check the web for events that may have impacted your business and give a summary at the top of the analysis. Automated workflows are the heart of 2.0
@eggro the web events check affecting your business analysis is the most genuinely agentic thing in that description and probably the most differentiated. pulling external context to explain internal data movements without being asked is a different capability than responding to queries. if that's working reliably it's worth being the centerpiece of how you describe 2.0 rather than something mentioned in a reply
Athenic AI
@ansari_adin Hi Ansari - agreed, in fact, the agentic analysis is what we use Athenic for the most internally. We hooked up our Ads data and asked Athenic to find opportunities, and then do web research on best practices / things we should change. Then it emails us the findings every Monday.
Love that it goes from question to automation, not just a one-off chart. How does Athenic decide when something's worth turning into a recurring report vs. a single answer?
Athenic AI
@shubham4real Hi Shubham - actually it's up to you to create an automation, vs having analysis as a one-off. If you find that you're doing analysis repeatedly, that'd be a great thing to automate.
As for how Athenic determines when it should email you - that's something you can configure as well. For instance, you can ask Athenic to only email you if there's something materially different from the last time it did analysis last week (just as an example).
Which integrations do you support? I couldn’t find that information on the website.
Athenic AI
@natalia_iankovych Hundreds of integrations - we're working on adding that to the home page, but for now, the best way to see the integrations is just to login to see.
@eggro @jared_zhao The “analyze on autopilot” angle is strong if it helps teams move from dashboards to decisions. A lot of analytics tools show what happened, but the real value is surfacing what changed, why it matters, and what someone should look at next.
Athenic AI
@alpertayfurr Hi Alper! Agreed, the ability to "set and forget" an agent that runs in the background to find insights and opportunities is really useful. I gave an example above about how we're doing that for our Ads data + web search on what we could improve in our Ads.
The part I find most interesting is trusting an agent to pick the join paths across tables on its own — that's usually where text-to-SQL tools quietly get the number wrong but still return something confident-looking. How are you handling the cases where the schema is ambiguous: does Athenic show its reasoning / the SQL it ran so an analyst can sanity-check, or is it more of a trust-the-answer flow?
Athenic AI
@mikebrandswarm The setup is reasoned through and stored as a semantic model. The base SQL datasets and semantic models can be viewed by a team admin and verified or edited. Non admin users can also flag feedback for the admin. But the system is quite good at setting up autonomously. You're definitely spot on about that being a major failure point of text to SQL.