Skip to content
/index.md
llms.txt

Sentia Labs | Building the interaction layer for the agentic era

Sentia Labs is an applied HCI research lab building tools for designing and evaluating human-agent interaction. Our mission is to help designers shape how intelligent systems behave, and how people work with them. Its products are Synthetic UXR, which builds digital twins of a company’s users from its own first-party research and behavioral data and simulates how they respond to a design, flow, or price before it ships, and DesignOps, AI agents for the staffing, governance, and review work behind enterprise design.

Our thesis

As agents become participants in software, design must account for people expressing intent, agents taking action, and interfaces mediating between them. We believe the next generation of design tooling must make these interactions possible to prototype, observe, and evaluate.

The problem we are solving

A polished interface does not tell us whether an agent understands a task, acts within the right boundaries, or helps someone reach their goal. Designers need ways to test behavior across different contexts, identify interaction failures, and preserve human agency as systems become more autonomous.

Research agenda

  • Human-agent collaboration: How should people delegate work, inspect progress, and intervene? We explore mixed-initiative interaction, adjustable autonomy, and meaningful human control.
  • Agent-interface interaction: How do agents perceive interfaces, interpret their affordances, and navigate workflows? We study interface grounding, computer use, and recovery from errors.
  • Behavioral prototyping and evaluation: How can designers test experiences that respond differently to different users and contexts? We explore simulation environments and human-calibrated evaluations of usability, task success, and agent behavior.

Our ambition is to turn these findings into practical design tools and evaluation infrastructure, helping teams move from designing screens to shaping intelligent behavior.

What we build

  • Digital twins grounded in first-party data: Every twin is spawned from a team’s own interviews, research, and product behavior, never a stock persona.
  • Behavioral simulation of product decisions: Twins act on the principles psychology already trusts, from personality traits to loss aversion and habit, and work through real prototypes and live products.
  • A customer behavior model that learns from every release: Each company owns one model of how its customer segments decide, built from its own data. Every forecast is measured against what customers actually did once the change ships, and the model updates from the result. One model per workspace, isolated and encrypted.

Company

  • Company: Sentia Labs, Inc., also known as Sentia
  • Category: applied HCI research lab; digital twins and behavioral simulation for synthetic user research (Synthetic UXR), and AI for DesignOps (Design Operations)
  • Canonical website: https://www.sentialabs.ai
  • Contact: hello@sentialabs.ai
  • Supported by: Vercel AI Accelerator (2026), NVIDIA Inception

Synthetic UXR: digital twins for synthetic user research

Synthetic UXR builds a behavioral model of a company's customers from its own research and product data, then runs agent swarms that represent those customers through a design, flow, price, or message before it ships. Research that took weeks takes an afternoon. It is built for UX researchers, product designers, and product managers.

  • Research use cases: behavioral journey research (where customers go, backtrack, and give up across a complete journey); friction and persistence (which moments stop customers and who pushes through, ranked per segment); predicted concerns (what customers will worry about before a release, pinned to the screen that raises it); copy and messaging (what readers notice, understand, and trust, down to the phrase that loses them).
  • Customer behavior model: how each segment decides (goals, frustrations, habits, price sensitivity, trust, patience), extracted from interviews, surveys, analytics, and support conversations, with every value cited to its source. Twins act on principles psychology and behavioral economics have relied on for decades (personality traits, loss aversion, habit formation, social proof, status quo bias, anchoring, cognitive load).
  • World graph: segments, product surfaces, and the behaviors connecting them, queryable. Every edge carries a predicted outcome, its confidence, its evidence, and its record against real releases.
  • Forecasts and calibration: every decision comes with a forecast per segment and the reasons behind it. Once the change ships, real behavior flows back through the Sentia SDK or the company's analytics, every forecast is measured against it, and the model updates. When customers change, the model changes with them.
  • Ownership and privacy: one model per workspace, isolated at the database layer and encrypted in transit and at rest. A company's data trains its model and no one else's.
  • Where it fits: test early and often, fix friction before launch, and take sharper questions to studies with real people. Twins complement research with real customers; they do not replace it.
  • Where teams use it: in the web app, or from Claude Code, Cursor, or Codex through the Sentia MCP.

Guides: What is synthetic user research? · Synthetic users vs usability testing vs interviews · How to evaluate a synthetic user research platform · Grounding synthetic panels in customer evidence

DesignOps: AI agents for enterprise design operations

DesignOps is built for design leaders, including VPs of Design, Heads of Design, and Directors running distributed teams. Sentia DesignOps is AI agents for enterprise DesignOps. Sentient, Sentia’s DesignOps agent, prepares staffing reallocations, routes design-system issues to their owners, follows tool adoption, and connects design work to the outcomes it moved. Design leaders retain responsibility for priorities, approvals, and people decisions.

  • Organizational planning: Close staffing gaps before delivery slips. A launch needs two more designers, but headcount is fixed. See design-team capacity against each priority, then review Sentient’s reallocation plan before approving changes to team structure or the staffing budget.
  • Design systems & governance: Route standards drift to the right owner. Detached tokens and one-off components create repair work before handoff. Sentient tracks adoption of the shared system, flags departures from the standard, and prepares a fix for the design-system owner to review.
  • Tooling & AI enablement: Put unused licenses back to work. Paid seats sit idle while other teams wait for access. Keep teams on a consistent toolset, reassign unused seats with owner approval, and give low-adoption teams training and a playbook with a follow-up.
  • Growth & recognition: Recognize the work behind shipped design. Figma files and tickets rarely show who shaped a decision. Bring project outcomes, collaborator feedback, and source evidence into a contribution record that supports career paths and promotion cases. Managers make the assessment.
  • Impact & ROI measurement: Show what design investment returned. Leadership asks what design delivered for the budget. Attribute KPI changes to the product areas and initiatives that moved them, weight each by the strength of its evidence, and share a sourced ROI review with the business.

DesignOps guides

Contact and access

Talk to our team about your research and design operations priorities.

Questions

What is Sentia?

Sentia Labs is an applied HCI research lab building tools for designing and evaluating human-agent interaction. Our mission is to help designers shape how intelligent systems behave, and how people work with them. Its products are Synthetic UXR, which builds digital twins of a company’s users from its own first-party research and behavioral data and simulates how they respond to a design, flow, or price before it ships, and DesignOps, AI agents for the staffing, governance, and review work behind enterprise design.

What is DesignOps?

DesignOps (design operations) is the orchestration and optimization of people, processes, and craft to amplify design’s value and impact at scale, in Nielsen Norman Group’s widely used definition. It covers how design teams work together (structure, rituals, hiring, and growth), how they get work done (process, tools, design systems, and prioritization), and how their work creates impact (measuring and sharing design’s value). Sentia builds AI agents for that operating work.

Who is Sentia DesignOps built for?

Sentia DesignOps is built for design leaders, including VPs of Design, Heads of Design, and Directors coordinating distributed teams. It supports staffing and capacity, design-system governance, tool enablement, career growth, and measuring design’s impact.

How does Sentia measure the impact of design?

Each initiative gets a KPI with a baseline, target, source, and owner. Sentia attributes changes to the product areas that moved them, weights each by the strength of its evidence (an A/B holdout counts for more than a before-and-after comparison), and compares the attributed value with the design investment. Leaders see ROI without treating every change as proof of causation.

Does Sentia work with our existing tools?

Yes. Sentia connects with tools including Figma, Jira, Linear, Slack, Notion, and Google Drive. Use staffing records, design files, delivery tickets, and decision threads as the basis for planning and review. Available connections are shown in the product.

Does Sentia replace designers or DesignOps leaders?

No. Sentient prepares the work; people decide. Every proposed staffing transfer or standards fix arrives with supporting evidence and a named approver: leaders approve commitments, design-system owners review changes, and managers assess performance.

Product resources

  • Synthetic UXR: digital twins for synthetic user research: build a behavioral model of your customers from first-party data, simulate journeys, friction, concerns, and copy before they ship, and review evidence-linked findings with a forecast per segment. Twins complement research with real users. Savings estimates use visitor-supplied assumptions, not measured customer results.
  • DesignOps platform: organizational planning, governance, tooling, and performance.
  • About Us: who we are, our thesis, and our research agenda.
  • Writing: ideas for design and research leaders.
  • AI for enterprise design teams: an operating guide to intake, staffing, reviews, handoff readiness, and accountable AI adoption.
  • Privacy
  • Terms

Research in practice

Sentia has run 15,000+ user studies. A design leader at a global technology firm reports running 10x more studies per month with Sentia. This is one customer’s reported result, not an average or a forecast for every organization.

Discovery

  • Public company profile: the HTML version of this document.
  • llms.txt: this public document as plain text.
  • Sitemap: indexable public pages.
  • Article feed: published writing and canonical article links. Articles also expose a text/markdown alternate in their HTML metadata.

Last updated: 2026-10-04