Project under NDA
Enter password to continue
Incorrect password
←Tanisha Pratap Singh
Dynamic Syms builder and live Sym preview, shown on a MacBook

Symtrain · UX Design · 2025

Dynamic Syms

An AI customer that can improvise, and a builder that keeps the training on purpose. Designed from creation to live practice.

Symtrain is a simulation based training platform for customer facing teams. Instead of shadowing live calls or sitting through slides, reps practise the real moments of the job, a billing dispute, an objection, an escalation, inside realistic simulations, get scored against a rubric, and get coached on what to fix. The full loop, create, practise, assess and improve, lives in one product shared by the trainers who build the exercises, the trainees who take them, and the managers who get a team ready for the floor.

For years those simulations were scripted by hand, so a trainee rehearsed a fixed branch tree and froze the moment a real customer went off script. Dynamic Syms replace the script with an AI customer that improvises, responding to whatever the trainee actually says, in real time, with a chosen personality and goal. My work was to make that shift usable and trustworthy: a simulation a trainer can build without writing prompts, a score a rep can believe, and a live call that holds together, across the creator, trainee and manager experiences.

What Symtrain is, and where Dynamic Syms fits.

Symtrain runs a full training loop for contact centres and customer facing teams: create a simulation, practice it, assess the attempt, analyse the results, coach the gap, repeat. The unit of practice is a Sym, a controlled recreation of a real work scenario. A Sym can be audio, chat, or a visual walkthrough of real software, and it lives inside modules and training plans with its own scorecard.

A manager assigns Syms, a trainee takes them in practice or test mode, and the platform scores every attempt against a weighted rubric. The point is not a quiz. It is reps on the hardest moments of the job before those moments happen with a real customer on the line.

Historically every Sym was a scripted branch tree. A trainer hand authored each line the customer could say and each path the conversation could take. Trainees learned to navigate that tree. They memorised the happy path and froze the moment a real customer said something off script.

Dynamic Syms replace the tree with an AI customer that responds to whatever the trainee actually says, in real time, with a chosen personality and goal. Same scoring, same reporting, a conversation that never runs on rails. The question this project had to answer was how a trainer creates one of those without writing a single prompt.

Unscripted AI is easy to demo and hard to make trustworthy.

A model that talks back is one API call. A training tool a company will stake its onboarding on is a different thing entirely. Four tensions shaped every decision.

The prompt engineering wall

The people who know the scenarios are trainers and subject matter experts, not engineers. Hand them a blank prompt box and the feature dies on arrival. Creation had to feel like filling in a brief, not programming a model.

Control over an improviser

An AI customer that can say anything will. It has to stay inside the scenario, respect policy and facts, hold a consistent personality, and not wander off or end the call early. Freedom needed guardrails the creator could set.

A score people believe

If the conversation is different every time, the scoring has to feel fair every time. Trainees and managers needed to see exactly why an attempt passed or failed, criterion by criterion, with the transcript as evidence.

Real time, not eventually

Practice only works if the customer answers like a customer. Latency, audio lag and abrupt endings break the illusion instantly, so the experience had to be designed around speed and graceful recovery, not just the happy path.

Structure the freedom. Never show a blank box.

The core move across the whole feature was the same: take something open ended and give it a shape a non technical person can reason about. Goals become templates. Prompts become labelled fields. Scoring becomes a rubric. Personality becomes a few named dials.

That principle flows through three experiences, the creator who builds the Sym, the trainee who lives inside it, and the manager who assigns it and reads the results. The rest of this study walks each one, then shows how they close into a single coaching loop.

The process radiated outward from the problem.

Research expanded into design, and design into validation. Each ring is a phase, each marker a hand off from one to the next.

DS Research & Discovery Design & Iteration Validation & Delivery SYNTHESIS USABILITY TESTING

Three roles, one shared object model.

Everything in Symtrain is built from a small set of objects. Dynamic Syms slot into that model as a new kind of Sym, so creators, trainees and managers each get a view tuned to their job without fragmenting the system underneath.

Syms simulations Modules grouped Syms Training Plans guided journeys Scorecards weighted rubrics Playbacks scored attempts Dashboards performance
Symtrain Dynamic Syms  ·  one simulation object, three role-specific views
Creator
Builds and configures a Sym without touching a prompt.
Sym Library Create Sym · Guided or Dynamic Goal & AI Generation Scenario & Persona Scorecard Preview & Publish
Trainee
Practises the assigned scenario and reviews the result.
My Exercises Practice or Test Live Conversation Scored Playback Attempt History
Manager
Assigns the work and watches the team reach the floor.
Assignments Scorecard Templates Team Playbacks Performance Dashboard
Sym type
Guided
Dynamic
Audio
Scripted
Unscripted
Chat
Scripted
Unscripted
Visual + Audio
Scripted
Unscripted
Visual + Chat
Scripted
Unscripted

Built inside Symtrain's own design system.

Dynamic Syms was new, but it could not feel new. It was built on Symtrain's existing foundation, Satoshi for type and a disciplined colour system, so a generative feature still read as native to the product.

Satoshi — primary typeface
Light (300)
Regular (400)
Medium (500)
Bold (700)
Aa
Colour — core ramps
Brand · Lime
Green
Blue
Red
Yellow
Grey

A trainer builds an AI customer by describing a scenario, not a model.

Creation starts from the Sym library and ends with a working, scored, unscripted simulation. At no point does the creator write a prompt. They pick a goal, let AI draft the scenario, then shape it through structured fields they already understand.

app.symtrain.com / syms
The Sym library listing every simulation with type, version and status
The library. Every Sym, its type, version and status, with one entry point to build a new one.
app.symtrain.com / syms / new
Choosing a goal template such as Objection Handling or Sales Pitch
Start from a goal, not a blank page. Objection handling, discovery, sales pitch, support, or a custom brief.
app.symtrain.com / syms / generate
AI generating the customer persona and scenario from the chosen goal
AI drafts the scenario and a customer persona from the goal, so the creator edits instead of authors.
app.symtrain.com / syms / scenario
Structured scenario fields for call opening, first message and prompt, with a live preview panel
The prompt, turned into a brief. Call opening, first action, discovery, objections and closing each get their own labelled field. A live preview sits alongside the whole time.
app.symtrain.com / syms / scenario
Objection and escalation prompt fields with add controls
Objections and escalations are listed, not coded. The creator adds the moments they want the customer to test.
app.symtrain.com / syms / persona
Customer persona setup with name, voice, behaviour and a de escalation intensity slider
Personality as dials. Name, voice, behaviour and how quickly the customer calms down. The same scenario, many temperaments.
app.symtrain.com / syms / scorecard
Assigning a weighted scorecard with criteria across metrics
Attach the rubric. Criteria and weights the attempt will be judged against, grouped by metric.
app.symtrain.com / syms / settings
Advanced settings including overall passing score and whether the AI can end the call
Guardrails. Passing score, whether the AI may end the call, and the environment it plays in.
app.symtrain.com / syms / preview
The finished builder with the scenario on the left and a live Sym preview conversation on the right
Preview before publish. The creator runs the exact conversation a trainee will, from inside the builder, and tunes it live.

For the trainee it should feel like a real call that forgives.

The trainee always knows where they are, which mode they are in, and whether it counts. They choose practice to learn safely or test to be assessed, hold a live conversation with the AI customer, and get a score they can actually read.

app.symtrain.com / my-exercises
My Exercises list with progress stats and assigned simulations
My Exercises. Assigned Syms, progress, and clear status so nobody wonders what is left to do.
app.symtrain.com / sym / start
Choosing practice or test mode before starting, with a before you begin panel
Practice or test. One clear fork, with a calm primer on how the conversation will behave and that it adapts.
app.symtrain.com / sym / live
Live conversation with the AI customer and real time coaching nudges
The live call. The trainee speaks or types, the AI customer responds in character, and quiet nudges coach the moment without breaking it.
app.symtrain.com / sym / playback
Scored playback showing Sym Score 79 of 100, knowledge and soft skills tabs, per criterion scores and the full transcript
The score, made legible. An overall Sym Score, knowledge and soft skills split out, every criterion weighted and explained, and the transcript as the evidence behind it.

Fair scoring of an unscripted call is a design problem, not just a model one.

Scorecards are reusable templates a manager builds once and reuses across Syms. Each criterion carries a weight, an evaluation instruction the AI judges against, and a severity, so the rubric is explicit long before anyone is scored by it.

scorecards
Scorecard templates library
Reusable templates, owned by the org.
scorecards / new
Starting a scorecard from blank or a Symtrain template
Start blank, or from a proven template.
scorecards / edit
Editing criteria with weights, evaluation prompt and severity
Weight, instruction and severity per criterion.

When the words are not enough, practise on the real screens.

Some jobs are not only a conversation. A rep is also navigating software while they talk. Visual Syms layer the real product screens, with tagged hotspots, onto the same dynamic conversation, so the trainee handles the call and the tool at once.

app.symtrain.com / syms / new
Creating a dynamic Sym and choosing a visual plus audio type
Visual and audio, or visual and chat. The conversation engine stays the same, the stage gains real screens.
app.symtrain.com / syms / screens
All Screens view where uploaded screens are auto tagged to conversation phases with hotspots
Upload the screens and AI tags each to a conversation phase. The creator reviews the tagging instead of wiring it by hand.

Assign the work, then watch a team get ready for the floor.

The manager side turns individual attempts into a program. Assign Syms to people or whole teams, then read performance in one place, who is floor ready, who is at risk, and which skills the training is actually moving.

app.symtrain.com / assignments
Assigning Syms to agents and teams
Assign Syms and modules to individuals or teams in a few clicks.
app.symtrain.com / assignments
Selecting trainees to assign a Sym to
Pick trainees and teams, with roles visible at a glance.
app.symtrain.com / dashboard / team-performance
Team Performance dashboard with completion, pass rate, average score, floor ready trainees and per team breakdowns
The dashboard that closes the loop. Completion, pass rate, average score and floor readiness roll up across teams, surfacing the top and bottom performers and a direct path to assign the right practice next.

The hard part was never the AI. It was making a team trust it.

What the design changed.

Dynamic Syms moved Symtrain from authoring branch trees to describing scenarios. The work spanned research, interaction design, UI and testing, and shipped as the flows shown here. A few signals from moderated testing and early rollout.

0 prompts
A creator ships a fully unscripted AI simulation without writing one, through templates and structured fields.
~70%
Less time to build a simulation versus hand authoring a scripted branch tree, observed in creation testing.
3 roles
Creator, trainee and manager designed as one connected system on a shared object model.

Research led

The direction came out of usability testing and UAT, where the recurring failures were a prompt engineering barrier for creators, broken trust when scoring felt opaque, and immersion breaking on latency and abrupt endings. Each became a design constraint rather than a bug ticket.

Honest framing

Figures here are directional signals from moderated sessions and a pilot cohort, not audited product metrics. The intent is to show what the design was built to achieve and the early evidence that it did, not to overclaim.

Dynamic Syms · Symtrain

Practice that finally behaves like the real thing.

← Back to all work