Skip to main content
Ontelis home
See a demo
Ontelis home

One of the top five US biopharma companies

Brand teams get HCP answers in under 30 seconds

An HCP population question used to wait three to five business days for an analytics ticket. Brand teams now ask it in Salesforce.

  • Under 30 seconds

    for an HCP population question, down from three to five business days via an analytics ticket. As of October 2026.

  • 1 day

    from a final campaign brief to a Draft journey verified by readback, down from about three weeks. As of October 2026.

  • 13

    Marketing Cloud artifacts built from a single brief and independently read back, including nine emails and a Journey Builder Draft

  • 0

    HCP records copied out of the warehouse, and zero messages sent without a person approving the exact plan

“We had more data about our physicians than ever, and every question about it still started with a ticket. By the time the answer came back, the plan had moved on.”

Director, Omnichannel Engagement, one of the top five US biopharma companies

Brand and omnichannel teams now put their HCP (healthcare professional) questions to an agent in Salesforce. Marketing operations hand a brief to a second agent, which plans the journey, waits for a person’s approval and builds a Draft in Marketing Cloud.

Before

Questions waited days, briefs waited weeks

An omnichannel lead could not plan a brand’s next email, field or digital program without waiting twice: once for an answer about the audience, once for a journey to review. One lead sits on each brand at a US pharma company with a multi-brand specialty care portfolio, accountable for how physicians hear from that brand.

  • An HCP audience questionThree to five business days, restarted by every follow-up
  • A written campaign briefAbout three weeks to a journey worth reviewing

Dashboards helped only when someone had built one for that exact question. Anything else meant a ticket: a central team of analysts picked it up and wrote SQL for the enterprise warehouse that holds the HCP data. (Analytics & Insights covers this work.)

For a campaign, marketing operations took each written brief and built it by hand in Marketing Cloud: the emails and templates, the entry events, the Data Extensions and the journey paths. Briefs left things out, and approved assets that already existed but could not be found were made again from scratch.

Why a generic AI assistant was never going to pass

  • Definitions

    The numbers had to be right, not just fluent.

    One HCP can be associated with several brands and appear in several preference observations. Count rows instead of distinct HCPs, or divide by the wrong population, and a confident answer is simply wrong. An earlier chatbot pilot had failed on exactly this.

  • Data residency

    The data could not move.

    The approved HCP dataset lives in Amazon Redshift under the company’s data governance. Any approach that copied it into a new application database was a non-starter for IT and privacy before the first demo.

  • Medical, Legal, Regulatory

    Nothing reaches a physician without MLR.

    Promotional content goes through MLR review. An agent able to activate or send a journey on its own would never be approved, however good its output looked. Governance had to be built in, not bolted on.

Reviewers from the customer’s IT, privacy and marketing compliance teams set the controls with Ontelis in weeks 1 and 2. Nothing was coded specially for this customer: the controls are standard Ontelis platform policies, and they bind both agents on every action.

The solution

Two agents. One governed context.

Ontelis forward-deployed engineers worked alongside the brand, omnichannel and marketing operations teams to build two agents on the Ontelis platform. Both draw on the same context: the connected systems, the business definitions the team signed off, and the policies that decide what any agent may read, write and show. The HCP Insight Agent answers inside Salesforce, where brand teams already work. The Campaign Agent builds in Marketing Cloud, where marketing operations already work.

Where people work

Salesforce, via Agentforce
Brand managers and omnichannel leads
Ontelis campaign workspace
Marketing operations and campaign reviewers

Agents

HCP Insight AgentRead only
Reads. Governed queries over the approved HCP view.
Campaign AgentDraft only
Writes. Approved plans become verified Drafts.

Ontelis platform

Govern
Read-only query policy, plan-bound approvals, Draft-only writes, full audit trail
IntuitionDB
HCP counting rules, denominators, brand cohorts, score meanings, journey conventions
Context Graph
HCP view schema, Marketing Cloud asset inventory, folders and send classifications
Connect
Redshift through Data Cloud zero copy. Marketing Cloud REST and SOAP APIs.

Systems of record

Amazon Redshift, through Salesforce Data Cloud
Approved HCP view, exposed as a Data Lake Object. Queried in place, never copied.
Salesforce Marketing Cloud
Content Builder, Data Extensions, Journey Builder, entry events

How it works

HCP answers on the team’s own definitions

Ontelis is AI infrastructure for pharma commercial operations that maps every system, records how the team decides, names who approves each step and logs every action for replay. Its forward-deployed engineers built two agents with the brand, omnichannel and marketing operations teams. The first, the HCP Insight Agent, takes the brand teams’ questions in Salesforce, through Agentforce. It reads only.

What brand teams can ask

  • Population and segmentation

    Distinct HCP counts and percentage breakdowns by brand, segment, specialty and geography, each on the agreed denominator.

  • Cross-brand overlap

    HCPs on both brands, either brand, or one and not the other, with preference observations restricted to the brands in question.

  • Channel, content and timing

    Channel preferences and performance categories, digital affinity, content preferences, preferred days and sessions. Top five specialties shown, the rest grouped as Others.

  • Lookup and bounded lists

    Find an HCP by name or NPI. Lists return the full matching count plus a preview of up to ten records, never a bulk export.

  • Scores, explained

    Score averages alongside what each score represents, with a plain statement where the underlying methodology is not available.

  • Real follow-ups

    Population, filters and metrics carry forward, so “and of those, who prefers email?” means what the user meant.

  1. Omnichannel lead

    Asks a population question.

  2. HCP Insight Agent

    Definitions first. IntuitionDB holds the counting rules, denominators and brand cohorts the brand analytics team ruled on, each labelled as a ruling.

  3. HCP Insight Agent

    One view. The agent writes its query for one place only, the approved HCP view, and takes that view’s schema from the Context Graph.

  4. HCP Insight Agent

    Checked first. Govern lets through a single read-only SELECT or WITH statement on the approved view, fields and functions, and stops anything else.

  5. HCP Insight Agent

    Inside the warehouse. Connect runs the query inside the warehouse, Amazon Redshift through Data Cloud zero copy; the rows stay there.

  6. HCP Insight Agent

    One repair. If the error is of a kind that may be repaired, the agent gets one corrected attempt, and that attempt goes through every check again.

  7. HCP Insight Agent

    An answer or a limit. A separate step writes the reply using nothing but what the query returned. When a question is out of scope or the query fails, the reply names the limit and does not make up a value.

  8. Omnichannel lead

    Follows up. The follow-up keeps the population, filters and measures.

The rows a query reads are never copied into Ontelis. A list request returns how many HCPs match and shows no more than ten of them; it cannot be used to export the rest. Where a score has no documented method, the answer points that out.

One brief, an approved plan, a Draft read back

The second agent, the Campaign Agent, works for marketing operations. Given a brief, it can come back with questions twice at most; whatever is still unanswered goes into the plan, written down as an assumption. It searches existing assets, read only, so approved ones are reused.

Then it proposes a plan: the journey diagram, the content, the entry rules, and each artifact it will create or reuse. The plan waits on a Workspace decision card, the card a person decides on, bound to that version of the plan; Govern’s word for this is Propose and wait. The approval stores fingerprints of the plan’s content and of everything it depends on; if either changes, the plan needs a new approval.

Agents write the same way every time: plan, check, approval, a write with an idempotency key so a retry cannot write twice, then readback. Here, every Draft is fetched back from Marketing Cloud after it is written, since Marketing Cloud accepting a request does not show the build came out right. One build produced 13 Marketing Cloud artifacts from a single brief, each read back, among them nine emails and a Journey Builder Draft.

Plan v3 · Brand A HCP onboardingJourney plan for review
Approved · fp 7c1e…a94f
Entry · API event · Test modeHCPs added to program Data Extension · no re-entry
Email 1Welcome to the Brand A HCP program
Wait 2 days
Engagement splitClicked Email 1?
No
Email 2Reminder: what’s new for your patients
Wait 3 daysExit
Yes
Attribute splitSpecialty
Med oncEmail 3 ·
Clinical data
Not opened:
Email 4
HematologyEmail 5 ·
Dosing
Not opened:
Email 6
OtherEmail 7 ·
Disease ed.
Not opened:
Email 8
Email 9Patient support resources
Exit

Assumptions carried into plan: “Other specialties” covers all HCPs outside medical oncology and hematology. Email 1 layout reused from the existing Brand A template.

Where the agent stops

The Campaign Agent writes only Draft journeys, Data Extensions with no rows, and entry events in Test mode. Govern holds it to draft writes, the class where nothing is sent; a write class is how undoable a write is, and it sets the default autonomy level. Loading audiences, switching journeys on and sending belong to people, each after MLR review, never to the agent.

Agents never sign, attest, approve content, assess an adverse event or release a payment above their limit.

Changes to prompts, flows and policies are versioned, with rollback, and the audit trail records questions, plans, approvals and builds. Context, policy decisions and check results reproduce exactly at pinned versions; model output is stored, not regenerated. The agents use provider adapters for several model vendors, and the customer’s model policy decides which runs.

Customers bring their own model contracts and endpoints, or run open-weight models inside their own environment.

Marketing & Content walks one sample campaign from brief to go-live.

“What won over our compliance team wasn’t the speed. It was that the agent shows its work, stops at Draft, and tells you when it doesn’t know.”

Head of Marketing Operations, one of the top five US biopharma companies

First agent live in week 9

Ontelis forward-deployed engineers were embedded with the customer’s brand, omnichannel and marketing operations teams, working with the customer’s commercialization services partner. No phase closed without evidence.

  1. Controls and rulings

    Weeks 1–2

    IT, privacy and marketing compliance reviewers set the controls; the HCP view was linked through Data Cloud; brand analytics ruled on counting rules, denominators and cohorts, and the rulings went into IntuitionDB. Evidence: reference questions fixed in advance.

  2. HCP Insight Agent, tested

    Weeks 3–7

    Checked against the reference queries and tried by omnichannel leads in UAT, with fixes for cohort preservation, formatting and score explanations. Evidence: each fix a versioned release that can be rolled back.

  3. Accepted

    Weeks 8–9. First agent live in week 9

    Evidence: 14 of 14 live conversation turns passed in the final regression, and all 27 channel-by-day count rows matched the reference exactly.

  4. Campaign Agent, built

    Weeks 8–15

    Built in a Marketing Cloud business unit set aside for it, and tested on new and reused content, splits, waits and DOCX briefs. Evidence: every build read back.

How the two agents were delivered, by week after kickoff.

These are this customer’s weeks. Ontelis promises no duration.

FDE is the Ontelis service in which forward-deployed engineers audit a pharma company’s estate, build the first process with its team and take it to production. Ontelis staff and forward-deployed engineers propose but never approve anything in customer production, and they have no standing access.

Governance

The controls that got IT, privacy and compliance to yes.

None of these were custom code written for one project. They are Ontelis platform policies, configured with the customer’s IT, privacy and marketing compliance reviewers in the first two weeks, and applied to every action either agent takes.

Ontelis controls in this deployment
ControlWhat it doesWhy it matters in pharma
Read-only query policyEvery generated query is checked before it runs: one SELECT or WITH statement, the approved view, approved fields and functionsAn agent cannot change data or wander outside what it was approved to read
Zero-copy accessQueries run where the HCP data lives, through Salesforce Data CloudNo new copy of HCP data to secure, govern or explain to privacy
Bounded outputsLists return the full count plus at most ten recordsAnswers inform decisions without becoming an export channel
Plan-bound approvalApproval attaches to the exact plan and its content and dependency fingerprintsWhat was reviewed is exactly what gets built
Draft-only writesWrites stop at Draft journeys, empty Data Extensions and Test-mode entry eventsActivation and sending remain human decisions, after MLR
Deterministic artifact keysAn identical retry reconciles with what already exists instead of duplicating itA failed run does not litter Content Builder with near-identical assets
Independent readbackContent, fields, sendability, event linkage, journey paths and Draft state are read back after every buildPartial or uncertain builds are reported as exactly that
Model-agnosticProvider adapters for Google Gemini, Anthropic and OpenAI, with deterministic code doing assembly and validationThe customer’s model policy decides, not the platform
Versioned releasesEvery prompt, flow and policy change is versioned, with retained rollback versions and a full audit of questions, plans, approvals and buildsReplayable evidence for compliance and IT, and a safe way back

Results

Analysts went back to analysis

Before and with Ontelis
BeforeWith Ontelis
HCP population question3 to 5 business days, via analytics ticketUnder 30 seconds, self-serve in Salesforce
Follow-up questionNew ticket, new waitSame conversation, context carried forward
Business definitionsVaried by analyst and dashboardOne agreed set in IntuitionDB, applied every time
Brief to reviewable journeyAbout 3 weeks1 day, including clarification and review
Existing assetsRebuilt when nobody could find themFound and reused before anything new is built
Evidence for reviewScreenshots and spreadsheetsPDF plan, journey diagram and readback report for every build

Three groups work differently now. Analysts spend their time on analysis, not on clearing tickets. Marketing operations review plans rather than retyping briefs. And the brand teams deciding whom to reach count HCPs exactly as the people building the sends do.

Results as of October 2026. How to read these figures. Under 30 seconds is a customer figure from the production deployment. 1 day is a customer figure from a Marketing Cloud business unit set aside for the agent, counted from a final brief. 14 of 14 and 27 of 27 are an acceptance test on a frozen reference set. No further method was stated.

These are this customer’s figures under the method above, not a promise for another.

Planned next, and the rest of Ontelis

Because both agents run on one context, every new capability starts with the definitions and policies already in place.

  • Into the field

    Planned: the HCP Insight Agent opens to field teams for call planning, each person limited to their own territory.

  • Governed activation

    Planned: audiences loaded and journeys switched on, but only after consent and suppression checks and behind the same plan approval.

    Consent and content status are read live at send time.

  • MLR-aware content

    Planned: approved claims and safety information placed exactly as the claims library holds them, with no rewording.

  • More channels

    Planned: SMS, push and banner steps. Plans can name them today; none is built until a person approves it.

    No promotional AI calls or texts to HCPs.

For IT and privacy reviewers:

Security and data

Models
Ontelis builds no foundation model. No model is trained on customer data, except an opt-in adapter that never leaves the customer’s data plane.
Vendor documents
Ontelis provides: a SOC 2 Type II report, an ISO 27001 certificate, a HIPAA business associate agreement wherever Ontelis processes PHI, a data processing agreement with transfer clauses, and a sub-processor list.
Your controls
Ontelis’s posture as a vendor is kept separate from Govern, which holds your own controls.

The customer asked us not to name it, and we also withhold its partner, its brands and the people quoted, who speak here by role. The figures date from October 2026 and come from the production deployment and from a Marketing Cloud business unit reserved for the agent.

Customer story

Email campaigns cut from 131 effort-days to 46Roughly 131 effort-days per campaign to a median of 46, across nine teams. Led by the customer’s commercialization partner, with Ontelis engineers building.

Where life sciences puts AI to work.

See a demo