Customers/Agios Pharmaceuticals
×

Agios ran the biggest launch in company history on the team it already had.

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.

2/3
Dashboard Build & Maintenance

Less build and maintenance effort, with static Excel and PowerPoint reporting replaced by live apps.

Months → Days
Work That Used To Queue

For analysis that used to sit behind vendor turnaround.

Days → Hours
Ad Hoc Questions

Answered live in the session instead of over rounds of back-and-forth.

Similar
Headcount, Pre- And Post-Launch

The same handful of analysts served market access, field, and leadership through the launch.

The Problem

Pre-launch commercial analytics and the impending wave

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.

Pre-Launch
Current State
  • Ad hoc questions routed through offshore vendors.Overnight to weeks per answer, plus rounds of back-and-forth.
  • Dashboards built through a multi-vendor chain.Weeks per build, with enhancements landing every few months.
  • Turnaround expectations were relaxed.The queue was survivable.
Post-Launch
Impending Problem
  • Increased number of questions and expected support.Field, marketing, market access, and leadership all at the door at once.
  • Same-day turnarounds needed."Which accounts moved this week?" expects a same-day answer; "why did the region dip?" is due before the next call.
  • Every answer carries day-to-day business impact.On the same fixed headcount.

Where horizontal AI fell short

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.

The Solution

A governed, virtual commercial pharma analyst,
built on Tellius

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.

Tellius — AI worker layer
workflows · apps · answers
Semantic + reasoning
definitions · rules · guardrails
Your data
warehouse · data lake
Semantic + reasoning layer

Metric definitions and business rules, validated metric by metric against trusted reports. The same answer for every user, with the SQL exposed.

Agentic workflows on a schedule

The most-asked questions run on a cadence, delivering scorecards and briefs to email, Slack, or Teams.

Agentic apps for everyone else

Dashboard-like apps built and changed in natural language, with deeper exploration sitting underneath the default answer.

Guardrails from day one

Row-level access, defined workflows, and a validation agent that checks every output against source data.

Implementation

Weeks, not quarters

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."

01

AI-ready data

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.

02

Context + rules

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.

03

Validate + pilot

The step most teams skip. Tested against the most-asked stakeholder questions until the answers came back right every time.

04

Roll out wide

Existing dashboards run in parallel first so the business can check new answers against old, then a pilot group, then everyone.

What The Virtual Analyst Grew Into

Analyses that were multi-week projects now run in minutes.

Course-corrected live in the session, instead of over days of vendor back-and-forth.

1
Pre-Call Planning: Physician 360A full view of a physician before the conversation — from patient mix down to diagnosis history, joined across CRM activity, claims, and profiling data.
2
Market Mapping + PrevalenceSizing prevalence in new markets to inform where the commercial effort goes next.
3
Customer + Patient SegmentationSegmentation work that runs alongside market mapping rather than queuing behind it as a separate project.
4
Root-Cause "Why" AnalysisWhy a trend broke, why a geography is underperforming — with the full diagnostic picture. Multi-week projects now run in minutes, while the team is still exploring.
5
Agentic Apps + DashboardsLive apps that replaced static Excel and PowerPoint — which matters most post-launch, when a static report is stale before it circulates.
The Operating Model · One Foundation, Different Front Doors
GOVERNED · ROW-LEVEL ACCESS
1
POWER USERS
Ask anything

People who want to interrogate the data directly — including an RVP of Sales who asks his own questions and builds his own custom reports.

2
AGENTIC WORKFLOWS
Encoded once, run the same way every time

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.

3
EVERYONE ELSE
Answers served, not searched

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.

Deepanshu Arora
Associate Director, Commercial Advanced Analytics · Agios Pharmaceuticals
Watch · PMSA Webinar Highlights

Deepanshu Arora on building it before the pressure hit

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.

Advice

What Deepanshu would tell a team starting now

01

Start before the pressure builds

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."

02

Separate governed from general

Commercial numbers need the same right answer every run. General-purpose AI covers the rest. Don't cross the streams.

03

Don't skip the data groundwork

Analytics-ready data and the semantic layer were most of the effort, and they are what make the speed safe.

04

Stay close to the technology

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.

What Is Tellius

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.

Used by 8 of the top 10 pharmaceutical companies
A five-time Gartner Magic Quadrant Visionary