Methodology-led coaching
Structured sessions reflect TNM's coaching standards without turning the coach into an advice engine.
Updated
Leelou AI Coach for TNM Coaching
We translated TNM's coaching methodology into a product with structured sessions, memory, voice, text, multiple languages, accountability, and privacy-aware reporting.
AI coaching productCoaching / Training
View Live Website
Watch Leelou voice coaching in action
See how a user starts a Leelou session, switches into voice mode, and continues a live coaching conversation.
95%
of onboarded regular users completed at least one session
45%
average package completion among onboarded regular users
13 min
average session length shown in the analytics
The Starting Point
TNM had around 25 years of coaching expertise and a proprietary methodology, but no AI product that could carry that knowledge into a new format. Off-the-shelf conversational tools could produce answers, but they could not represent the way TNM wanted coaching to feel or behave.
Human Methodology, Not Generic Chat
The product had to guide reflection without turning into an advice engine. It also needed continuity across sessions, useful reporting, and clear boundaries when a conversation moved beyond coaching.
Methodology fidelity
The AI needed to reflect TNM's coaching techniques and quality standards.
A coaching posture
The product should nudge users toward their own thinking instead of supplying direct answers.
Responsible boundaries
The system needed to recognize situations that required professional care outside the coaching product.
Our Role
We learned the methodology with TNM, translated it into product behavior, built the conversational experience and surrounding platform, and refined it through repeated testing with TNM coaches.
Learn the domain
We listened to TNM's coaches and turned their techniques and quality standards into product requirements.
Design the AI behavior
We shaped how Leelou asks, remembers, nudges, and maintains the boundary between coaching and direct advice.
Iterate toward quality
We continued testing with TNM coaches rather than treating the first conversational demo as the finished product.
The Product Behind the Conversation
Leelou combines a methodology-led coaching workflow with the surrounding product capabilities needed for ongoing individual and organizational use.
Text and voice sessions
Users can move between text and voice while Leelou keeps the session context and coaching posture intact.
Privacy-aware reporting
Organizations see useful aggregate engagement signals without exposing private coaching conversations.
Iteration with domain experts
Repeated coach-led testing helped move the product beyond the first conversational demo.
What the Product Had to Solve
A useful coaching product needed more than a fluent conversation. It had to preserve its coaching posture, carry context forward, support different ways of interacting, and protect private conversations.
Consistent coaching posture
Leelou needed to encourage reflection without slipping into direct advice.
Continuity across sessions
Relevant context had to carry forward so each session could build on the last and support accountability.
Flexible interaction
Voice, text, and supported languages needed to feel like one coherent coaching experience.
Privacy-aware insight
Organizations needed useful engagement signals without access to private coaching conversations.
The Product Around the Conversation
Leelou combines the coaching workflow with the product capabilities required for continued individual and organizational use.
Text, voice, and multiple languages
Users can engage with the coaching experience through different interaction modes and supported languages.
Memory and accountability
Session continuity and SMS or email follow-up help users carry their thinking forward.
Privacy-aware HR reporting
Organizational reporting is designed around useful aggregate signals rather than exposing private coaching content.
Conversation boundaries
Guardrails intervene when the discussion moves outside the intended coaching context.
The Outcome
Leelou AI became a working coaching product. Among onboarded regular users, 95% completed at least one session, average package completion was 45%, and the analytics showed a 13-minute average session length. Retained-user counts are not lifetime reach because inactive users and sessions may be deleted under TNM's GDPR retention process.
What This Proves
Productizing expertise requires more than prompting a model. The team building the product has to learn the domain, translate judgment into behavior, test with experts, and keep refining until the experience reflects the standard behind it.
Can your expertise become an AI product?
We can help translate a serious methodology into product behavior, workflows, guardrails, and a complete user experience.
Product walkthrough
Inside the product
1 / 3
Earlier view
01
The member home screen keeps package status, session length, and the next action visible before coaching begins.
Client video testimonial
Zoran Todorovic, Senior Partner, TNM Coaching shares their experience working with Adamant Code.
Turning Human Complexity Into an AI Coach
Zoran Todorovic, Senior Partner, TNM Coaching
What TNM Says
TNM on the work required to translate human coaching into a usable AI product.
“You didn't just build features. You listened. The challenge was not only developing technology, but translating the human complexity of coaching into something usable.”
Zoran
TNM Coaching
What is your team working around every day?
Bring one manual process, disconnected workflow or software problem. We’ll discuss what needs to work differently, the constraints involved and a sensible next step.
Talk through your workflow
Other case studies
GTS Innovative AI-Assisted Marketplace
We translated a founder's market vision into 50+ screens, 15+ workflows, and a structured invention process for inventors, service providers, investors, and admins.
Full AI product buildMarketplace / Innovation
GTS Innovative had a clear market vision and rough wireframes, but the user journeys, permissions, product logic, and AI workflow still needed definition. We turned that starting point into a complete marketplace platform.
Ergo Global AI Customer Operations System
A typical 36-second website-chat response, 11,782 conversations and 3,019 personalised check-ins in five months.
AI support automation and operations platformErgonomics / Customer Operations
Ergo Global moved from staff-dependent chat and inconsistent post-assessment follow-up to a connected support operation that managed 11,782 conversations and sent 3,019 personalised check-ins in five months.
Explore the service and related reading
Product development for founders
Explore how we shape the first release, design the experience and build your product with one team.
Ongoing improvement and support
See how we agree a cadence for reliability, AI tuning, and focused improvements after launch.