I led product design, UX/UI and frontend engineering through Sapiom’s $35M Series A launch. The platform brings agent customization, runtimes, tool integrations and workflow automation together.
AI agents
Workflow builder
Developer experience
Design systems
Project overview
Overview
Build and inspect AI workflows
Create agents, edit workflows and inspect runs in one workspace.
Role
Founding Design Engineer
Product design, UX/UI and frontend engineering. Rebuilt the UI, design system, website and demos; led launch creative direction. Partnered with founders and engineers on strategy, AI-native prototypes and MVP features.
Team: Founder CEO, Engineering and AI Researcher
Problem
Chat and workflow fell out of sync
The early builder could accept a chat response without updating the workflow. Long replies buried decisions, making it hard to tell what an agent would do.3
Solution
Build, revise and inspect one workflow
Keep the conversation, editable plan and run evidence together. Show each change in context, with controls to revise the plan or stop a run.
Chat, workflow and run details together
Chat and canvas share selection; Steps keeps your place as you inspect a run.
From the workspace to a nested agent
Collapse the panels to focus on the canvas. Inspect the scheduler, open its workflow, then return to the receptionist.
From sign-up to a testable agent
Two questions turn a goal into a testable template, with a live preview of its steps.
Screen 1 of 5
Create a workspace
Show the product working beside the sign-up form.
From a template to a running agent
People can compare steps, tools, cost and approvals before opening a template in Studio.
Screen 1 of 4
Browse
Compare templates by their steps, cost and whether a person signs off.
From building an agent to operating it
The web console gives teams a shared entry point for Agent studio, Router and Runtime. Agent activity, usage and connected accounts stay accessible as work moves from an individual workflow to a fleet.
Screen 1 of 3
Start in one workspace
Choose a product, continue an agent or start from a template.
Agent studio on mobile
Chat, workflow and run activity each have room to work on a phone.
Screen 1 of 9
Start from the promise
Lead with what the agent will do and show a real plan before asking for an account.
Shared components and code
I built shared React components in TypeScript and Tailwind and documented their states in Storybook, covering workflow steps, folder navigation, streaming replies, human approvals and run controls.
Visual & token foundations
Surface colors, typography and shared workspace primitives across Agent Studio.
Components in context
A local specimen. Inspect its appearance without running an action.
Design decisionParse the request into an inspectable step plan first. Ask a question only when the answer changes a card, and keep confirmed choices editable before the build.
Design decisionBind the conversation and canvas to one shared ledger so every answer updates the graph in the same turn and delegates cleanly to child agents.
Design decisionExpose per-step inputs, outputs, latency and metered tool costs directly on the workflow rather than burying them in a separate log stream.
Design decisionSeparate local stubbed test runs from live cloud execution, and pause at a human approval gate before any external write or paid capability call.
Patterns synthesized from product research and internal walkthroughs.3, 10, 11, 12, 13
Plan review before anything runs
The request becomes a step plan that can be checked and changed before the build. Every clause stays traceable to the step it created.
Request
When a loan application arrives01, read the documents02 and check credit03, then score it against our rules04. Send borderline cases to a reviewer05 and ask for anything missing06.
Plan6 steps from 6 clauses
01Receive applicationwebhook.intake$0.00
02Read documentsstorage.extract$0.00
103Verify creditexperian.credit$0.02
04Assess applicationclaude-sonnet$0.01
05Human reviewreview.gateNeeds answer
06Request documentssms.followupIf needed
2
Changes step 05
Which credit score should send an application to review?
Below 620Below 660Set my own
6 steps · est. $0.03 per runEdit planBuild workflow3
1
One clause, one step
Each part of the request maps to a visible step, so nothing disappears into the build.
2
Ask only when it changes a step
The review threshold decides routing in step 05, so it is the one question worth asking.
3
Cost before commitment
Step count and estimated cost per run sit beside the build action, and every choice stays editable.
Approval before a run leaves the sandbox
A live run stops at a gate that states what it will touch and spend, in plain language, next to the test it passed.
Approve live run
leasing · this run calls live services on your accounts
1
Local testPassed
Tools
stubbed
Cost
$0.00
LiveAwaiting you
Tools
your accounts
Est. cost
$0.03
Local test passed6 of 6 steps completed in run app_0142
Credit access is read onlyexperian.credit can pull a soft report, nothing else
Spend cap set$5.00 per day, this run is estimated at $0.03
2Sends a message outside the sandboxsms.followup texts the applicant when documents are missing
Your approval is recorded with the runCancelApprove and run live3
1
Test and live never look alike
Stubbed tools at no cost on one side, your accounts and an estimate on the other.
2
Name what leaves the sandbox
External writes are listed with the tool that performs them, so the risk is specific.
3
Approve something concrete
Scope, spend and test results are checked first, and the decision is recorded with the run.
Product implicationMake it straightforward to inspect a failed or degraded step, revise the plan and re-run locally.
Visibility is more common than evaluation
Some observability
89%
Offline evaluations
52.4%
Online evaluations
37.3%
LangChain’s survey of 1,340 respondents; Anthropic’s evaluation guidance and Gartner’s 2025 forecast (projecting over 40% of agentic projects canceled by 2027 due to cost and risk controls) reinforce exposing what ran, what changed and what each step cost.4, 8, 9
Preparing the launch demo
I built repeatable Agent studio and Router demos for recording and hands-on exploration. The sequence followed one task from agent creation to execution and usage costs. An early 52-second concept film tested the story before final production.
An illustrated summary of the early 52-second film.
00:03The cost problem
00:15Remove the barriers
Email verified prospects…
00:28Describe the outcome
Verified prospect outreachGeneratingSearch the domainFind the right contactsVerify every addressEnrich with company dataSend and record
00:31Build the workflow
Verified prospect outreachTimeCostSearch the domainFind the right contactsVerify every addressEnrich with company dataSend and record
00:36Inspect execution
Ship agents,not infrastructure.Start Building
00:49Ship agents
One node, every state it can reach
Border, badge and time change together, so a run reads correctly in greyscale and at a glance.
01Queued
Verify creditexperian.creditQueuedWaits for step 01
02Running
Verify creditexperian.creditRunning0.8sCalling the bureau
03Waiting on a person
Verify creditexperian.creditWaiting on you4mApprove paid call
04Failed
Verify creditexperian.creditFailed10sTimed out, attempt 1 of 3
05Complete
Verify creditexperian.creditComplete1.2sScore returned
Following one run on a phone
On mobile each plane gets the full screen. Tabs switch the view, never the context: the selected step travels with you.
1
leasingWaiting on you
Build an applicant screening workflow.
Ready for your reviewAssess application: low riskOpen stepApprove
ChatStepsCanvas
2
leasingWaiting on you
Receive application
Read documents
Verify credit
Assess application1.8s
Human reviewHold
Request documents
ChatStepsCanvas
3
leasingWaiting on you
Verify creditAssess applicationHuman review
Assess applicationComplete1.8s$0.01
ChatStepsCanvas
1
Chat
Approve from the message. Open step jumps to the same step in the other views.
2
Steps
Scan status and cost. The waiting step carries the same Hold badge as desktop.
3
Canvas
Structure on demand. A half-height sheet keeps the graph visible above it.
Later demo storyboards
September 13, 2026 studies for the agent map, step inspection and run evidence.
Plan the agent map
Inspect a step
Read the run evidence
Three products, one platform story
Each product page leads with one promise, then shows the product working: a routed request, an agent taking shape in Studio, and a run that waits for approval before it resumes.
The homepage pairs one promise with the real workspace.
Router
One endpoint, with a model chosen for each request.
Company-reported launch results. Views are not unique people; 67 placements include 55 syndications. These are company milestones, not measured effects of the interface.
3Project records
Project walkthroughs, team reviews and merged design engineering contributions. Interactive examples use sample workflow data. Read the text case.