Sign up to save your podcasts
Or
Share Just Now Possible
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Just Now Possible
Just Now Possible episodes
- Building Banani: How a Canvas-First AI Designer Is Raising the Floor on Product Design
Guests
- Vlad Solomakha, CEO & Co-founder, Banani
- Vova Parkhomchuk, CTO & Co-founder, Banani
- Vlad Ostapovats, Founding Growth, Banani
In this episode
- Why Banani started as a Figma plugin and what they learned from early organic distribution
- The canvas-first approach: why Banani is built around a design canvas rather than a chat interface
- How their agent architecture splits prompts into surgical edits instead of regenerating full screens
- The "gulf of specification" problem and what Banani is building to help agents and designers speak the same visual language
- Managing context across canvases with hundreds of screens — per-screen history with shared project context
- Why Banani doesn't compile running applications — just HTML/CSS mockups — and how that shapes everything
- How they evaluate design quality without traditional evals: spinning up 10 screens from one prompt to compare models
- Their approach to building at the edge of what's possible: identifying which model limitations to work around vs. wait out
- The role of context engineering and specialized agent tools in producing tasteful, high-quality design
Resources & Links
- Banani
- TL Draw
Chapters00:00 Meet the Founders
01:12 What Bonani Builds02:18 Why an AI Designer03:40 Raising the Design Floor06:23 Why AI Was Finally Ready10:48 First Prototype Figma Plugin14:10 Early Growth and Distribution15:25 Standing Out in a Crowded Market20:13 Product Tour Canvas First AI23:40 Autopilot vs Manual Control27:07 Tech Behind High Quality Design32:08 Craft Beyond 80 Percent33:40 Gulf of Specification36:44 Proactive Agent Interviews38:40 Canvas First UX Choices42:54 Agent Architecture Under Hood48:48 State History Context Tricks52:32 Tooling Context Engineering56:04 Navigating Busy Canvases01:00:13 Betting on Model Progress01:03:47 Shipping Around Imperfections01:07:20 Try Banani and Next Steps01:07:52 Building the Banani MCP01:09:19 Final Thanks and Wrap1 hr 11 min - Building Agent Studio: How Medable Is Using Agentic AI to Accelerate Clinical Trials
Guests
- Luke Bates, Product Leader (Agent Studio), Medable
- Jen Brown, Product Manager, Medable
- Matt Schoolfield, Product Designer, Medable
- Fiachra Matthews, Principal Architect, Medable
What we cover in this episode:
- What Medable does: enabling global clinical trials across 100+ languages and accelerating drug-to-market timelines
- The two agents built on Agent Studio—ETMF (document classification) and CRA (clinical data monitoring)—and the problems they solve
- Why Medable chose a platform approach to agents instead of one-off builds
- How Agent Studio works: models, skills, knowledge bases, MCP connectors, versioning, and trigger types
- Three deployment models: Medable-built products, services-led custom builds, and self-serve platform access
- RAG approaches at scale: embeddings vs. markdown hierarchies vs. just-in-time MCP retrieval
- How they built a unified ontology layer to map terminology across 13 different clinical data systems
- Why they built custom MCPs with an authentication and credentialing wrapper
- Context window management with sub-agents and automatic tool filtering
- Evaluation design in a GXP-regulated environment: golden datasets, production monitoring, and the challenge of human feedback as ground truth
- How they document agent intent → specification → test evidence to satisfy regulatory bodies
- The "full self-driving" vision for clinical trials and what it would take to get there
Resources & Links
- Medable - Clinical trial platform powering Agent Studio
Chapters
00:00 Meet The Medable Team01:14 Medable Mission And Scope03:27 Agent Studio Platform Overview06:29 ETMF Document Automation08:47 CRA Agent For Monitoring10:40 Clinical Trial Workflow Primer14:34 Why Build A Platform17:51 Learning AI As A Team21:47 Early Days Of Agent Studio23:15 How Agents Are Built25:15 Customer Adoption And UX30:00 Skills And MCP Standards31:15 Scaling Context Retrieval33:07 RAG Patterns And Tradeoffs34:48 Ontology Data Layer Explained38:01 Customer Friendly Agent Setup42:19 MCP Security And Connectors44:36 Tool Bloat And Subagents50:44 Evals For Reliable Agents54:40 Human Feedback Isn’t Truth57:43 GXP Compliance For Agents01:03:34 Full Self Driving Trials1 hr 7 min - Building GitHub for Product Management: How Momental Uses AI to Find Merge Conflicts in Strategy
Guests
- Matthias Kleverud - Co-Founder, Momental
- Charlotte Kleverud - Co-Founder, Momental
What we cover in this episode:
- What "GitHub for product management" means: finding merge conflicts in strategy, not code
- The product chain: signals → learnings → decisions → principles, and how AI maps it
- Three trees that model an organization: the product tree (OKRs to epics), the wisdom tree (decisions and their reasoning), and the people/time tree
- How a document processing agent uses OODA-loop thinking to extract and connect context across documents
- Why traditional chunking and RAG breaks down at scale and what Momental does instead
- The origin story: building a team of AI agents in 2024, only to discover agents hit the same alignment problems as humans
- Starting in 2022 with DaVinci 002 and learning that the market wasn't ready for AI-assisted product thinking
- How conflicts are detected, auto-resolved, or escalated to humans with merge options
- Why metadata—who said it, when, and in what context—is critical to preventing hallucinations
- The self-improving agent: collecting user feedback weekly and rewriting its own prompts
- Moving from chat-first to UI-first to proactive agents as an AI product design pattern
- Design partner strategy and what's next for Momental's public launch
Resources & Links
- Momental - GitHub for product management
- Spotify - Where both founders started their PM careers
- Claude Code - AI coding tool discussed in the conversation
- Perk episode on Just Now Possible - Referenced episode about eliminating shadow work
Chapters
00:00 Meet The Founders01:14 GitHub For PMs Explained03:19 Strategy Merge Conflicts06:49 Product Chain Model09:49 Capturing Context Fast12:17 Context Graph And RAG Limits16:52 Origin Story Since 202220:01 From Agent Team To Foundation25:26 Three Trees Of Context28:42 Two Agents Secret Sauce31:37 How Document Processing Works34:55 Agents Ask Better Questions35:41 Human In The Loop Context36:38 Data Models And Graphs39:21 Beyond Documents And Vectors42:25 Specialized Tools Win44:50 Quarterly Planning At Scale49:38 Discovery Versus Vibe Coding51:00 Tree Building And Conflicts53:49 UI Over Chat Interfaces56:01 Proactive Agents In Practice58:00 Quality Evals And Feedback01:00:22 Launch Plans And Mission01:03:19 Eliminating Shadow Work01:03:56 Closing Thanks1 hr 5 min - Building AI Sales Reps: How ShowMe Orchestrates Voice, Video, and Multi-Agent Workflows to Close Deals
Guests
- Yuri Vela Tulopov -- Co-Founder and CEO, ShowMe
- Quique Gomez -- Co-Founder and Lead Product Engineering, ShowMe
What we cover in this episode:
- How ShowMe builds AI digital workers that function as inbound sales reps
- The origin story: spotting the conversion gap at a previous company and realizing AI could fill it
- Why the first MVP was a voice agent with product videos and a simple RAG knowledge base
- Adding a realistic avatar via HeyGen and how it changed user engagement through better affordances
- Decomposing a single sales conversation into multiple specialized sub-agents (greetings, qualifying, pitching)
- The three agent types: conversation agents, evaluator agents, and creator agents
- How deterministic workflows manage the lead-to-close journey across days
- Building toward a smart orchestrator agent that breaks out of rigid workflow paths
- Ingesting sales transcripts and training materials to teach agents company-specific sales skills
- Customer-driven evaluation loops that start at 100% review and taper to ~5% over time
- Creating automated tests from customer feedback to prevent prompt regression
- Confidence scoring and frustration detection for real-time human handoff decisions
- Treating the agent as a coworker: onboarding via Slack, weekly reporting, CRM integration
- Future plans: self-serve PLG motion, smart orchestration, and expanding to customer success
Resources & Links
- ShowMe - AI digital sales reps for inbound teams
- HeyGen - AI avatar platform used for ShowMe's video calls
Chapters00:00 Meet the Founders: Juri & Kike Introduce Show Me
00:45 What Show Me Builds: AI Sales Reps as Digital Coworkers02:17 Why Inbound-First Sales Agents (and Not Outbound Spam)03:51 Origin Story: The Website Conversion Problem That Sparked the Idea08:11 MVP Launch: Voice + Video Product Demos in Two Weeks10:45 Bootstrapping the Knowledge Base: Videos, Docs, Scraping & RAG11:54 Beyond Demos: Multi-Stage Buyer Journeys, Follow-Ups & Orchestration14:34 Building Trust: Avatars, Video-Call UX, and AI “Affordances”20:18 Whiteboard Architecture: Agents, Workflows, and the Orchestrator Layer29:43 Where Agents Run: Creators, Evaluators, and Breaking Deterministic Flows32:18 Sales Is High-Stakes: Personalization vs. Hallucinations & Revenue Risk33:35 Conversation Agent Evolution: From Q&A Bot to Guided Sales Discovery34:10 Why One Agent Becomes Many: Decomposing Stages for Latency & Memory36:36 Orchestrator + Tooling: Routing Between Greeting, Qualify, Pitch, Next Steps38:46 Teaching Sales Skills: Generic Prompting vs Company-Specific Playbooks42:52 Ingesting Real Calls & Onboarding Like a Teammate (Transcripts, Training Docs)45:05 Real-Time Voice + Avatar Demos: Latency Tricks and Video Clip Libraries47:33 Creator vs Evaluator Agents: Data Cleaning, Custom Fields, Sentiment & Confidence49:15 Human Handoff Guardrails: When Confidence Drops or Users Get Frustrated50:15 Proving Quality in Production: POCs, A/B Rollouts, Dashboards, and CRM Logging53:21 Evals at Scale: Customer Feedback Loops, Regression Tests, and the 5% Review Set58:19 What’s Next: Smarter Orchestration, Self-Serve Setup, and More Digital Workers01:02:07 Closing Thoughts: Customer Insight as the Moat in a Fast-Moving AI World1 hr 4 min - Building Earmark: How a Two-Person Team Turned Meetings into Finished Work
Guests
- Mark Barbir – CEO, Earmark
- Sanden Gocka – Co-Founder, Earmark
What we cover in this episode:
- How Earmark differs from generic AI notetakers by producing finished work, not just summaries
- The pivot from Apple Vision Pro presentation coaching to a web-based meeting assistant
- Running multiple agents in parallel during live meetings
- Template-based agents: Engineering Translator, Make Me Look Smart, Acronym Explainer
- Personas that simulate absent team members (security architect, legal, accessibility)
- Why ephemeral mode (no data storage) became a selling point for enterprise
- Reducing AI costs from $70/meeting to under $1 through prompt caching
- Why GPT 4.1 still beats newer models for prose quality in their use case
- The limits of vector search for analysis questions across meetings
- Building agentic search with multiple retrieval tools (RAG, BM25, metadata queries, bespoke summaries)
- Designing for product managers as the extreme user to solve for everyone
- Their vision for an AI chief of staff that goes beyond automating deliverables
Resources & Links
- Earmark — Productivity suite where the work completes itself
- ProductPlan — Roadmapping tool where both founders previously worked
- Granola — AI notetaker mentioned for comparison
- Assembly AI — Speech-to-text service used by Earmark
- OpenAI API — LLM provider with prompt caching support
- Cursor — AI code editor with build integration in Earmark
- V0 by Vercel — AI prototyping tool with build integration in Earmark
Chapters00:00 Introduction to Earmark Founders
00:28 Background and Experience01:05 What Does Earmark Do?01:23 AI and Productivity03:09 Comparing Earmark to Competitors03:41 Earmark's Unique Features05:53 Templates and Personas10:06 Technical Details and Development17:12 Early Product Versions and Challenges28:44 Understanding Prompt Caching29:49 Managing Multiple Tools and Costs30:59 Optimizing Transcript Summarization35:11 Challenges with Context and Reasoning Models38:10 Innovative Search and Retrieval Techniques44:06 Creating Actionable Artifacts from Meetings48:30 Ensuring Quality and Managing Hallucinations58:20 Future Vision for AI Chief of Staff1 hr 1 min - When Trust Is Everything: Building AI for Physicians at Healio
Guests
- Jennifer Deal – SVP of Product Development, Healio
- Casey Utley – Senior UX Designer, Healio
- Matthew Skepner – VP of Technology, Healio
What we cover in this episode:
- Why physicians need AI at the point of care—and how they actually use it (hint: it's preparation, not bedside)
- The surprising discovery that physicians wanted help with patient communication and empathy, not just clinical answers
- Building a working prototype in a weekend with Cursor after starting with Figma mockups
- How Healio's RAG system combines lexical search, vector search, and semantic search across multiple trusted sources
- Why "just use PubMed" isn't simple—five different ways to access the same data, each with trade-offs
- Designing citations that physicians trust: subscripts, hover states, and progressive disclosure
- Serving contextual ads while the LLM processes queries—a practical monetization approach
- HIPAA compliance and input guardrails for masking personal health information
- Eight LLM judges for evals: safety, medical accuracy, faithfulness, relevancy, completeness, reasoning, clarity, and overall quality
- Why physician feedback trumps LLM-as-judge feedback in high-stakes medical contexts
- The role of the Healio Innovation Partners in ongoing discovery and validation
Resources & Links
- Healio — Medical news, education, and clinical guidance for healthcare professionals
- PubMed — Database of biomedical literature
- Cursor — AI-powered code editor used to build the prototype
Chapters
00:00 Introduction to Healio Team01:00 Overview of Healio's Services01:57 Introducing Healio AI03:39 Addressing Physician Needs with AI05:45 Building Trust in AI Solutions13:56 Prototyping and Testing Healio AI18:02 Refining the AI Product21:48 Technical Architecture and Advertising Integration25:16 Balancing Speed and Accuracy in AI Responses26:30 Ensuring Credible and Trustworthy Content27:41 Challenges in Data Integration and Web Crawling29:00 Optimizing Search Strategies for Different Data Types31:09 User Interface and Trust Building34:31 Human Feedback and Continuous Improvement35:41 Guardrails and Evaluations for Reliable AI39:11 Experimenting with LLM as Judges45:13 Future Directions and User-Centric Design50 min - Building Tendos AI: How an Agent Swarm Turns Construction Emails into Quotes
Guests
- Daniel Kappler — CPO (Product & Design), Tendos AI
- Matthias Hilscher — CTO (Engineering), Tendos AI
Key Takeaways
- Start narrow to prove value: Tendos AI began with just radiators for one design partner before expanding to all building products
- Own the interface: building a web application (vs. integrating into legacy systems) gave them control over UX and the ability to iterate toward full automation
- Evaluate each agent, not just the chain: per-agent evals make debugging tractable and show exactly where performance changed
- Use review agents: a separate agent that checks work (like code review) catches errors before they reach humans
- Let customers pull you: customers asked Tendos to replace their CPQ software—strong signals of product-market fit
Topics Covered
- The tendering chain in construction and why it's ripe for automation
- How domain expertise (CEO's construction background) helped identify and validate the opportunity
- Entity extraction from PDFs ranging from 1 page to 1,800+ pages
- Planning patterns in agentic systems—creating and updating plans based on findings
- How agents evaluate product fit against customer requirements
- Building custom tracing and observability tools for complex agent chains
- The path toward self-learning systems through human feedback loops
Links & Resources
- Tendos AI
Chapters00:00 Introduction to Tendo and Key Roles
01:01 Understanding the Tendering Chain02:26 Real-World Construction Analogy03:34 Challenges in the Construction Industry04:48 AI's Role in Tendo's Product12:59 Early Prototypes and AI Integration18:31 Expanding Product Capabilities28:56 Customer Collaboration and Workflow Automation33:15 Strategic Partnerships and Technical Groundwork34:20 Focusing on Specific Customer Segments36:03 Product Evolution and Current Capabilities38:17 Technical Workflow and Automation40:12 Evaluating and Matching Product Requests47:00 Dynamic Agent Architecture55:29 Quality Measures and Evaluation01:02:59 Future Directions and Customer-Centric Development1 hr 6 min - Building a Career Co-pilot for Disadvantaged Students: How Zero Gravity Bridges Knowing and Doing
Guests
- Elliot Little, Product Manager, Zero Gravity
- Dan St. Paul, Software Engineer, Zero Gravity
What we cover in this episode
- Zero Gravity's mission: breaking down barriers to elite careers for disadvantaged UK students
- The "knowing-doing gap"—why students struggle to act even when they know what to do
- Why their first prototype (a job suitability summary) didn't create the "wow moment" they expected
- The decision to use text chat over voice input and why guided prompts beat empty text boxes
- Context management techniques: removing stale tool calls, summarizing history, exposing tools conditionally
- Using different models for different tasks (GPT-5 Nano for structured outputs, lighter models for quick replies)
- Safeguarding architecture: moderation endpoints plus external verification with Unitary
- Building a failure taxonomy through internal red team/green team exercises
- What's next: long-term memory management for multi-year student journeys
Links & References
- Zero Gravity
- Unitary – AI-powered content moderation
- Blue Dot Impact AI Safety Course – free AI safety course Elliot recommended
Chapters
00:00 Introduction to Dan and Elliot00:45 Zero Gravity's Mission and Impact02:14 Introducing the AI Career Co-Pilot04:01 Challenges Faced by Disadvantaged Students06:49 Zero Gravity's Mentorship Program09:14 Building the AI Career Co-Pilot12:01 Early Prototypes and User Feedback17:05 Refining the AI Career Co-Pilot37:36 Introduction to Career Co-Pilot38:02 Current Student Interactions40:22 Technical Deep Dive42:14 Context Management Challenges44:43 Tool Call Optimization51:48 Safeguarding and Moderation57:52 Evaluating AI Performance01:04:09 Future Directions for Career Co-Pilot01:07:52 Concluding Thoughts1 hr 10 min - Automating the Full Customer Support Iceberg: How Gradient Labs Built a Multi-Agent Platform
Guests**
- Jack Taylor, Product Engineer, Gradient Labs
- Ibrahim Faruqi, AI Engineer, Gradient Labs
In this episode
- The iceberg metaphor: why frontline support is only the tip of automation potential
- How three agent types (inbound, back office, outbound) coordinate on complex tasks like fraud disputes
- Natural language procedures that let subject matter experts train agents without engineering bottlenecks
- The "turn" architecture: state machines that orchestrate agent logic across async, multi-day conversations
- Skills as modular agent capabilities—and how they're scoped deterministically per turn
- Defining "done" for outbound agents when the customer isn't the one ending the conversation
- Guardrails as classification problems: balancing recall and precision for regulatory compliance
- Ask a Human: a tool call that brings humans into the loop for approvals or missing APIs
- Auto-eval pipelines that flag conversations for manual review and feed labeled datasets
Links & References
- Gradient Labs
- Incident.io episode – Referenced in the conversation
Chapters00:00 Meet the Engineers: Jack and Ibrahim
00:39 The Role of Product Engineers in Tech01:21 Introduction to Gradient Labs02:11 The Three Pillars of Customer Support Automation04:32 The Evolution and Growth of Gradient Labs05:29 Building and Refining AI Agents06:39 Outbound Agent: Addressing Customer Problems09:12 Defining Success in Outbound Procedures17:08 Ensuring Compliance and Guardrails30:17 Understanding Agent Guardrails31:54 Complexities of Natural Language Input36:21 Skill Design and Management39:53 Deterministic Skill Execution41:54 Customer-Specific Guardrails44:21 APIs and Customer Tools Integration46:02 Ask A Human Tool48:24 Guardrails as Classification Problems57:12 Auto Eval System59:12 Future of Multi-Agent Systems1 hr 2 min - Building Mowie: How a Concierge Service Became an AI Marketing Platform
Guests
- Chris O'Connor – CEO, Mowie
- Jessica Valenzuela – Co-Founder, Mowie
What we cover in this episode
- How Mowie evolved from a concierge marketing service to an AI-powered platform
- The "document hierarchy" architecture: how Mowie builds and maintains context about each business
- Why they moved from structured schemas to loosely structured markdown for intermediate processing
- Using Simon Sinek's Golden Circle framework to validate early product-market fit
- How Mowie generates quarterly content calendars and weekly posts across email and social media
- The three mini-calendars: public events, business-specific events, and recommended campaigns
- Building traceability so customers can see which context documents influenced their content
- Using customer approvals, edits, and regeneration requests as lightweight evals
- Connecting marketing performance back to point-of-sale data for attribution
- What's next: deeper attribution, omnichannel expansion, and digital out-of-home displays
Resources & Links
- Mowie AI — AI marketing platform for SMBs
- Simon Sinek's Golden Circle — The framework Mowie used for early validation
Chapters00:00 Introduction to Mowie AI
00:06 Meet the Founders: Chris and Jessica00:45 Understanding the Target Customers01:35 Challenges Faced by SMBs in Marketing04:20 The Evolution of Mowie AI05:40 How Mowie AI Works for Businesses08:16 Onboarding and Data Collection14:56 Content Strategy and Calendar Creation22:29 Technical Challenges and Solutions29:41 Iterative Development and Feedback37:23 Automated Content Calendar Approval39:19 Content Calendar Creation Process40:14 Marketing Pillars and Campaigns42:11 Transparency and Traceability in Recommendations45:23 Generating Weekly and Quarterly Calendars48:24 Customizing Campaigns for Specific Events54:15 Evaluating Campaign Performance58:48 Customer Feedback and Document Hierarchy1 hr 8 min
About Just Now Possible
From the publisher's feed
How AI products come to life—straight from the builders themselves. In each episode, we dive deep into how teams spotted a customer problem, experimented with AI, prototyped solutions, and shipped…
real features. We dig into everything from workflows and agents to RAG and evaluation strategies, and explore how their products keep evolving. If you’re building with AI, these are the stories for you.