Side project · AI diagramming

From messy AI outputs to clean, editable diagrams.

Bhava is my nights-and-weekends AI tool built with one part-time engineer. I lead everything from product discovery to shipped experiments-driving 60% activation, 5% landing conversion, $150–200 MRR, and −40% cost per diagram in four weeks.

Prompt strategy Trust signals Pricing & retention AI evals

Product discovery

Mapped workflows, ran 8 interviews, and sized activation gaps before touching UI.

Trust-led UX

Turned the prompt into a guided demo, added progress states, and rebuilt onboarding.

Growth experiments

Removed free mode, shipped usage-based pricing, and tracked retention + MRR weekly.

AI evaluation

Logged 100+ failed diagrams, clustered errors, and guided sub-agent strategy to lift accuracy.

60%

Activation lift

1,600+

Early users

25

Paying teams

4

Renewals sealed

Guided AI diagramming that feels reliable

I turned Bhava from a promising hack into a trust-first workspace where the AI shows its work, asks for the right context, and outputs clean, editable diagrams.

Lifted activation to 60% by pairing prompt presets, progress states, and failure logging with weekly eval loops.
Aligned monetization with value by removing free mode, adding usage-based billing, and tracking retention + MRR weekly.

Context

Why we built this

Every week, I watched designers redraw the same diagram-like déjà vu with arrows.

I'm a product designer at an ad-tech startup. By day, I'm deep in B2B dashboards. By night, I watch my team waste hours redrawing the same system diagram in Figma, Draw.io, Excalidraw, and Miro.

Same workflow. Four different tools. Different versions. Complete chaos.

So I started building Bhava-an AI tool that generates diagrams instantly. But more importantly, one that doesn't feel like a black box.

What Bhava looked like before vs after the trust redesign

This is early stage. We're 4 weeks post-launch with ~2,500 users and $250–300 MRR. I work on this part-time alongside my full-time job. One engineer friend helps part-time. Between us, I handle design, product, evals, UI fixes, pricing experiments, and customer interviews. He handles optimization and infrastructure.

This is the story of how we went from a fuzzy idea to 60% activation-and what I learned about building AI products people actually trust.

The problem

Broken workflows, broken trust

🔀

Diagramming was fragmented

Engineers used Draw.io
Designers used Figma
PMs used Miro
Same diagram, 4 places, 30+ minutes each time

🤔

AI tools fell short

Vague prompts → broken diagrams
No feedback while AI "thought" → mistrust
Failures with zero explanation

The activation problem: In early tests, only 38% of users created their first diagram. The other 62% bounced without trying.

"AI doesn't need to be perfect-it just needs to show it's trying."

Our bet: Build on top of Draw.io (largest user base) and make AI feel reliable, not random.

Approach

Designing for trust

Every design decision mapped back to a trust framework for AI research

Ability

Can the AI actually do the task?

Benevolence

Does it feel like it's helping me?

Integrity

Is it honest about what it can and can't do?

Reliability

Does it work consistently?

Discovery

Understanding the drop-off

Before redesigning anything, I spent 2 weeks analyzing user behavior-watching session recordings, tracking prompts, and interviewing people who churned.

Blank canvas paralysis

Users landed on an empty editor with no guidance, no examples. They froze.

Mode confusion

"Intelligent" vs "Basic" results varied wildly. Trust eroded fast.

No progress feedback

3–8 seconds of spinner. No updates. Pure anxiety.

Hidden export

Only 15% exported their first diagram. The happy path was invisible.

"I don't know what to type, so I just close the tab."

- Product manager, B2B SaaS

"The activation gap is usually a clarity gap-not a capability gap."

What I shipped

Six experiments that moved metrics

Each redesign tackled a specific trust or activation gap. Here's what worked.

First we fixed clarity, then trust, then monetisation.

Phase 1: Onboarding & Clarity

Getting users to understand what to do and how to start

Experiment 01

Homepage prompt became the product demo

Problem: Vague CTAs meant visitors signed up without understanding what to type.

Solution: Elevated a giant prompt box with example chips and a mini walkthrough so users preview the experience before creating an account.

1% → 5% Landing conversion (+4pp)

45s → 12s Time-to-first-prompt

Experiment 02

Guided prompt experience replaced the blank chat

Problem: New users froze on an empty chat and churned without generating anything.

Solution: Added diagram-type cards, contextual hints, and a three-step progress indicator that nudges people into action.

38% → 60% Activation (+22pp)

+18% Prompt quality scores

"Clarity unlocks activation. But trust keeps users coming back."

Phase 2: Trust & Quality

Building reliability into the product experience

Experiment 03

Removing free mode protected trust

Problem: The legacy "Basic" mode produced low-quality diagrams that tanked perceived reliability.

Solution: Sunset the free mode, offered one premium try, and introduced usage-gated access to keep output quality consistent.

30% Day-7 retention (stabilized)

−55% "Bad diagrams" support tickets

"Monetisation isn't just about pricing-it's about signalling reliability."

Phase 3: Pricing & Evaluation

Aligning value with sustainable monetisation

Experiment 04

Usage-based pricing matched value to spend

Problem: Unlimited $10/month plans were unprofitable and encouraged abuse.

Solution: Swapped to a $10 base plan with transparent credit packs and real-time usage tracking.

$30 First enterprise add-on purchase

−22% → +14% Contribution margin flip

Experiment 05

Usage clarity reduced support debt

Problem: Pricing changes created confusion-users couldn't tell where credits went.

Solution: Built an always-available tutorial and a usage dashboard detailing credits, modes, and expiry.

−60% Billing questions

+1.2 pts NPS on transparency

Experiment 06

Manual evals powered sub-agent quality

Problem: Diagram quality varied by type and we lacked clarity on failure patterns.

Solution: Logged ~100 failed diagrams, clustered errors, and routed high-volume types through specialized sub-agents.

+70% Flowchart success rate

Flat Costs (thanks to caching)

4 weeks post-launch

Current metrics

A snapshot of where things stand after the first month of shipping.

📈

Activation - 60%

+22pp from 38%

🎯

Landing conversion - 5%

Visitors → Sign ups

+4pp from 1%

💰

Cost per diagram - $0.048

After prompt caching

↓40% reduction

💵

MRR - $150–200

~30 paying customers

First month baseline

🔄

Day-7 retention - 30%

Active after one week

Stabilized post-pricing shift

⚡

Generation speed - 3.2s

p50 latency

7.8s at p95

Reflection

What broke, what worked

Failures

Template gallery: zero usage, removed quickly
Three free tries: people churned emails, costs spiked
Basic mode: poor quality eroded trust
Five-step onboarding: too long, trimmed to three

Wins

Homepage prompt lifted conversion 4pp
Progress indicators stopped mid-gen refreshes
Caching reduced costs by 40%
Quality-first approach kept users returning

"I learned that AI trust is built in microseconds, even a7-second latency feels fine only when users see progress."

Deeper reflections

Trust compounds, but so does mistrust. One broken diagram erodes more trust than five perfect ones build. That's why removing the "Basic" mode-even though it cut our free tier-was the right call. Quality consistency matters more than feature breadth in AI products.

Monetisation isn't just about pricing, it's about signalling reliability. When we introduced usage-based pricing, we weren't just managing costs-we were telling users "this output is valuable enough to meter." Paradoxically, charging more increased trust because it signalled we stood behind the quality.

Progress indicators are trust multipliers. The same 7-second generation time feels entirely different when users see "Analyzing structure... Generating nodes... Optimizing layout" versus a blank spinner. Transparency about what's happening builds confidence even when things take time.

The activation gap is usually a clarity gap. Our jump from 38% to 60% activation wasn't about making the product better-it was about making it clearer. Users didn't know what to type, so they didn't try. The moment we showed examples, they understood the possibility space.

What I'd do differently

Set up analytics on day one (not week two)-we lost critical early behavior data
Start manual evals earlier to catch quality issues before users did
Test pricing experiments faster-waiting cost us margin and user trust
Interview churned users within 24 hours while their frustration was fresh and specific

What's next