Henry Wang

Co-founder FlowGPT & Emochi & Kaon Lab| ex-AMZN

building an AI-native content platform with AI-native company

[Henry Wang @Henry_Flowgpt]

We (Emochi, with 10M+ users) stopped using benchmark scores for production decisions about 6 months ago.

The pattern was consistent: models ranking top on benchmarks underperformed in real usage. Models ranked lower drove better retention.

A few notes on what we learned:

[Henry Wang @Henry_Flowgpt]

Some recent thoughts on company efficiency https://t.co/o6OoJhdPih

[Henry Wang @Henry_Flowgpt]

Two things worth putting time developing agent in production
1. Providing accurate context
2. Writing good test cases

[Henry Wang @Henry_Flowgpt]

check this

[Henry Wang @Henry_Flowgpt]

Open-sourced Claude Code Web.

For people who can’t run Claude Code Client locally, or prefer a browser workspace over the TUI.

Runs with local Claude Code CLI or on a remote server via SSH tunnel.

Most importantly: you can change it into any skin you like.

[Henry Wang @Henry_Flowgpt]

Open-sourced Claude Code Web.

For people who can’t run Claude Code Client locally, or prefer a browser workspace over the TUI.

Runs with local Claude Code CLI or on a remote server via SSH tunnel.

Most importantly: you can change it into any skin you like.

[Henry Wang @Henry_Flowgpt]

https://t.co/hLkrgpw3db

[Henry Wang @Henry_Flowgpt]

Open-sourced Claude Code Web.

For people who can’t run Claude Code Client locally, or prefer a browser workspace over the TUI.

Runs with local Claude Code CLI or on a remote server via SSH tunnel.

Most importantly: you can change it into any skin you like.

[Henry Wang @Henry_Flowgpt]

https://t.co/K0oRG5jzlc internal free site leaked?

[Henry Wang @Henry_Flowgpt]

https://t.co/Sh0wse2JTY

[Henry Wang @Henry_Flowgpt]

Small tool that I built to help me give better interview:

input: JD + resume - output: questions for each round
input: transcript + JD - output: hiring suggestion with detailed reasons (so far 80%+ aligned with my decision)

[Henry Wang @Henry_Flowgpt]

@omooretweets lol agree

[Henry Wang @Henry_Flowgpt]

@RaVercettipmut Will be soon

[Henry Wang @Henry_Flowgpt]

We (Emochi, with 10M+ users) stopped using benchmark scores for production decisions about 6 months ago.

The pattern was consistent: models ranking top on benchmarks underperformed in real usage. Models ranked lower drove better retention.

A few notes on what we learned:

[Henry Wang @Henry_Flowgpt]

One takeaway for 2026: Eval infrastructure will determine product ceiling more than model selection.

The question isn't "which model is best." It's "which system learns fastest from real users."

Wrote up the full framework: https://t.co/RQXkDotJUM

[Henry Wang @Henry_Flowgpt]

We rebuilt the pipeline on three components:
1. Elo/TrueSkill on real conversations — filters out bad models in hours
2. Conversation-level A/B — not user-level (key distinction below)
3. Reward models trained on behavioral signals — closes the loop into training

[Henry Wang @Henry_Flowgpt]

Core issue: benchmarks optimize for "correct responses" on discrete tasks.

Consumer AI optimizes for "experiences that feel right" across continuous interactions. These objectives aren't aligned. At scale, they actively conflict.

[Henry Wang @Henry_Flowgpt]

@venturetwins My lesson learned from building Emochi is that the key is not only the model itself but the closed loop eval-feedback-iteration infrastructure. Happy to share more thoughts

[Michael Guan @dralaska_]

Interviews are broken. resumes mislead.

We helped 100k+ people land jobs & scaled to $10M ARR. now we’re rebuilding hiring from scratch.

meet WorkTrial AI — where companies see the real work before they hire.

[Henry Wang @Henry_Flowgpt]

If your product relies on user-facing prompt features, this post is for you. I’m sharing hard-won lessons from 10,000+ prompt iterations across complex, structure-sensitive workflows where every percentage point of success rate mattered.

https://t.co/EiiDdLhHLE

[Henry Wang @Henry_Flowgpt]

Sharing my experience to help people write better production-ready prompts - check out "The First Production-Ready Prompts Guide"

https://t.co/EiiDdLhHLE via @LinkedIn

[Henry Wang @Henry_Flowgpt]

Sharing my experience to help people write better production-ready prompts - check out "The First Production-Ready Prompts Guide"

https://t.co/EiiDdLhHLE via @LinkedIn