A launch is a multiplication problem for a lean analytics team: more stakeholders, more questions, and a same-day clock replacing a comfortable one. Agios saw it coming a year out. Rather than add headcount, the commercial analytics team put a governed virtual analyst on the warehouse it already trusted — live in weeks, and now running pre-call planning, market mapping, and root-cause analysis for the whole commercial organization.
Less build and maintenance effort, with static Excel and PowerPoint reporting replaced by live apps.
For analysis that used to sit behind vendor turnaround.
Answered live in the session instead of over rounds of back-and-forth.
The same handful of analysts served market access, field, and leadership through the launch.
Agios runs commercial analytics with a handful of people serving market access, field, and leadership teams. A launch was about to multiply the requests against fixed headcount. Unlike teams that react once the pressure ramps up, Agios saw it coming a year out and started preparing before the queue backed up.
Agios already uses ChatGPT, Claude, and Copilot daily for email, slides, and general analysis, where variance in the answer is fine. Commercial data is a different job: someone acts on the number, so the same question has to return the same right answer for every user. That takes metric definitions, business rules, and access controls baked in, and it is why Agios evaluated vertical AI platforms on semantic-layer strength, reasoning depth, speed, and consistency under repeated questioning. Tellius ranked highest on those tests.
Nothing was ripped out. The existing warehouse stayed the single source of truth, and Tellius went on top as the semantic, reasoning, and agentic worker layer. That is what makes the speed safe: every answer runs on the same definitions the business already trusts, with the SQL exposed underneath.
Metric definitions and business rules, validated metric by metric against trusted reports. The same answer for every user, with the SQL exposed.
The most-asked questions run on a cadence, delivering scorecards and briefs to email, Slack, or Teams.
Dashboard-like apps built and changed in natural language, with deeper exploration sitting underneath the default answer.
Row-level access, defined workflows, and a validation agent that checks every output against source data.
The objection Deepanshu hears most is that this has to be a multi-year project. It wasn't — and the reason is unglamorous. Agios had already done the data work. "AI has skills. What it lacks is context, and that's where you come in."
The warehouse was already analytics-ready. Tellius connected to the data lake directly. Deepanshu’s rule of thumb: if a person can manage the data, AI will be able to manage it too.
Business context, KPI definitions, and guardrails set up in a few weeks, including row-level access so a rep sees only their own territory from the first login.
The step most teams skip. Tested against the most-asked stakeholder questions until the answers came back right every time.
Existing dashboards run in parallel first so the business can check new answers against old, then a pilot group, then everyone.
Course-corrected live in the session, instead of over days of vendor back-and-forth.
People who want to interrogate the data directly — including an RVP of Sales who asks his own questions and builds his own custom reports.
For the questions many people ask, the team encodes the steps to follow and the structure of the output, so a familiar question is handled identically each run.
Agentic apps that behave like dashboards on the surface — default answers up front, deeper exploration underneath. Users don't care what's beneath. The analytics team cares a great deal.
Do not assume the AI will automatically know your organization. You have to train it like a new employee. Do that groundwork diligently, because it is going to serve you for a long time to come.
Highlights from the PMSA session on how an AI-native commercial team prepared for launch scale — what they evaluated, what they built, and what they'd tell a team starting now.
Agios started about a year ahead of its launch. "If you start when the pressure hits, panic kicks in and you are not diligent enough."
Commercial numbers need the same right answer every run. General-purpose AI covers the rest. Don't cross the streams.
Analytics-ready data and the semantic layer were most of the effort, and they are what make the speed safe.
AI improves every month. Building dashboards from a prompt wasn't on the radar at kickoff; the idea arrived months into production, on a foundation ready for it.
Tellius gives commercial teams an AI worker that shows up with the work done. It connects structured and unstructured data, applies your business rules through a governed semantic and reasoning layer, and delivers finished work where your team already works.
Live in weeks on the stack you already own.