Persona design for agentic and physical AI

We design the humanity in AI.

Personality, voice, and judgment—from agents to humanoids, in 41 languages. We've done this for commercial AI at global device makers since 2016.

Start a project
Meet ddai

What we do

What ddai does

One character in every language

A health-coaching robot talks with a user who wants to skip today's workout. Switch languages. The words change; the character holds.

Person

I just want to rest today. Skipping the workout.

Robot

Understood. You walked a lot yesterday, so rest is fine. May I suggest ten minutes of stretching this evening?

Person

Not that either.

Robot

All right, no more suggestions today. I'll check in on how you feel tomorrow morning.

Character spec
  1. 01

    Calm, never rushed

  2. 02

    Encourages without pushing

  3. 03

    Declines with a reason and an alternative

  • 2016Year we began designing AI personas
  • 41Languages in commercial service
  • 120+Countries where the AI we support is used
  • 4Entities in Korea, the US, Germany, and China

Crossroads

Where the humanities meet technology, academia meets industry, and research meets product—ddai

  • MITRobots

    Letting a robot look while it talks, through tool calls

    Dong Won Lee, Cynthia Breazeal, Hae Won Park et al. · arXiv 2026

    The authors propose a minimal system in which a real-time multimodal LLM calls tools to look at people and objects and scan the scene mid-conversation. On a Jibo robot across six scenarios, tool-decision accuracy was 0.72 for OpenAI and 0.77 for Gemini.

    ddai insight

    Looking less isn't a safe default for a talking robot. A model can be right most of the time it looks and still miss many moments that called for a look.

    A Modern System Recipe for Situated Embodied Human–Robot Conversation with Real-Time Multimodal LLMs and Tool-Calling

    Read the paper
    Humanoid
  • HarvardAgents

    Agents repeat their past experiences, mistakes included

    Harvard · Michigan State · University of Minnesota · Zidi Xiong, Yuping Lin, Wenya Xie et al. · ACL 2026

    The study tests how adding and deleting memories shapes four LLM agents over time. Agents follow similar past experiences, so stored errors spread; keeping only runs that matched the ground truth raised EHRAgent accuracy from 13.05 (storing everything) to 38.50.

    ddai insight

    For an agent, memory works less like a record and more like an example to imitate. Choosing what to keep is choosing how it will judge next.

    How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior

    Read the paper
    PersonaOS
  • AppleRelationships

    Human-like talk reads differently when an AI says it

    Sunnie S. Y. Kim, Margit Bowler, Leon A Gatys · arXiv 2026

    In 21,000 conversations with four LLMs, human-like behaviors were common but varied by model and user. Human raters judged relationship-building less appropriate from an LLM than from a person, and boundary-keeping more appropriate.

    ddai insight

    Whether a remark fits depends on who says it. Relationship talk that works between people fits an AI less, while drawing boundaries fits an AI better than a person.

    Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts

    Read the paper
    PersonaOSHumanities
See all research

Work

The expertise inside the work

  • 01

    AI assistant persona, scaled to 41 languages

    Expertise
    Persona design, response style, and per-language rewriting
    Method
    Spec first; native writers rewrite to the same spec; one rubric scores every language
    Deliverables
    Persona spec, multilingual responses, and evaluation criteria
    PersonaOSLocalization
  • 02

    Dialogue for a wearable robot

    Expertise
    Robot voice and situational utterance design
    Method
    For each use scene, design when the robot speaks first and when it answers
    Deliverables
    Dialogue scenarios and utterance data
    Humanoid
  • 03

    Judgment criteria for AI agents

    Expertise
    PersonaOS-style judgment design
    Method
    Record a person's criteria layer by layer, then write rules for where they conflict
    Deliverables
    Judgment criteria document and evaluation set
    PersonaOS
See all work
Certified for innovation, security, and quality
  • Inno-BizCertified technology-innovation SME in Korea
  • Venture companyCertified venture company in Korea
  • ISO 9001Quality management system
  • ISO 27001Information security management system
  • Corporate R&D centerAccredited in-house research and development unit

Patents held

  • Contact us

    Building a robot or an agent? ddai designs its character and judgment.
    From the persona spec to evaluation data in 41 languages, one team sees it through.

    Start a project
  • ddai

    Before AI can stand beside people, it needs a character and a way to judge. ddai designs both.

    Meet ddai