Hereβs to exploring new territory. π€
Hereβs to exploring new territory. π€
Iβm excited to be on that frontier this year β learning, designing, and building new ways of working, and helping others do the same.
Better decisions.
Faster learning.
More room for genuinely new possibilities.
Thatβs what excites me about Frontier Firm thinking.
Done well, itβs not about tools β itβs about redesigning how work happens.
That perspective makes one thing painfully obvious:
there is so much waste in how we work today.
Duplication. Friction. Unnecessary steps that drain energy and slow progress.
Iβve spent 25 years across every mode of the tech industry:
independent work, small teams, growing companies, and global enterprises.
My focus this year is simple:
β’ Continue transforming iSoftStone as Customer Zero
β’ Use those learnings to help clients transform with intention β not noise
At Microsoft Ignite last year, Microsoft laid out a clear blueprint for this next phase: the Frontier Firm.
That framework is now my playbook for 2026.
We all know AI is here.
The real question now is how we apply it responsibly and effectively.
2026 is shaping up to be a year of real transformation β for me personally, and for enterprises figuring out how AI actually changes the way we work and do business.
Helping with decorations at #msignite
Iβll also be at Microsoft Ignite next week.
If youβre attending, Iβd love to connect β whether to talk ideas, share perspectives, or just say hello.
A new chapter, but very much on the same road Iβve been traveling.
Now I get to stay close to technology while being even closer to customers and real-world solutions.
Our focus is Data & AI, and the team is as global as it is talented. In my first week alone Iβve already met great people across China, the U.S., India, Turkey, and Malaysia.
Iβm excited to share that Iβve joined iSoftStone as a Senior Client Partner.
It feels like a natural step after years in the Microsoft ecosystem β as an advocate, an engineering leader, and more recently an independent consultant.
Watch the @luckyfamilystry stories on YouTube or XiaoHongShu
www.youtube.com/@LuckyFamily...
www.xiaohongshu.com/user/profile...
βοΈ ChatGPT β story co-author
ποΈ Scenario β consistent character design
π¨ Photoshop β final polish, my go to for 20+ years
βοΈ Google Gemini β small expressive tweaks
Itβs amazing whatβs possible when tech meets storytelling.
A month ago, I started a new job search β next week, I start a new role π
In the meantime, Iβve been building something close to my heart β€οΈ
Iβve turned bedtime stories for my daughters into a bilingual picture-book series β Lucky Family Story β created with AI tools.
Iβm locked in! Time to prep. 5 conversations started today. Happy Friday π«‘ #getajob
Iβm officially #OpenToWork π
Built Microsoft Learn (200M+ MAU) β Scaled engineering org 2β200
Led Stripe Docs team through major upgrades
Spent the past year diving into AI workflows
Now ready for my next engineering leadership role. DMs open.
The precision of code + the creativity of natural language is where AI development shines.
How are you giving your AI coding agents just enough structure without killing creativity?
π My 6-Step Framework:
1οΈβ£ Define rules once (agents.md)
2οΈβ£ Break work into atomic steps
3οΈβ£ Use code examples
4οΈβ£ Enforce guardrails
5οΈβ£ Iterate with feedback loops
6οΈβ£ βΌοΈ Review commits like any other developer
When you vibe code with AI β only using natural language β you lose that precision.
AI coding agents shine when you give them instructions + constraints.
Add 2 rules β validate inputs + round down.
Code: 2 extra lines.
English: multiple sentences, careful ordering, and qualifiers.
Programming languages pack precision into tiny syntax.
βWell-defined type systems are key here.
In code:
const a = 2, b = 2.5;
const c = (a * b) / 4;
Short. Exact. No ambiguity.
Plain English? Long, careful sentences to avoid confusion. Word soup. π²
Most people think code is harder to βspeakβ than natural language.
I think thatβs backwards. π€
Code is simpler β and far more precise. Hereβs why π
11/
Happy Friday π
Go burn through your Claude usage limits. ποΈ
10/
My setup now:
π¬ Claude Code in VSCode for deep, conversational building
β‘ Cursor for lightning-fast manual refactors
Individually = impressive.
Together = fastest, cleanest workflow Iβve ever had.
9/
Claude might be my main driverβ¦
β¦but Cursor is still the fastest, smartest editor Iβve used.
Change an enum β Cursor predicts casing, tense, properties β across the project.
I just hit Tab. β¨
8/
π Tangent: People worry AI will cut juniors out of the loop.
But if AI like Claude can teach while assisting, we might see AI mentorship grow talent instead of replacing it.
7/
Before Claude, my specs were thousands of lines.
Now? About thirty.
Not side-by-side pair programming β over-the-shoulder.
Sometimes I drive. Sometimes Claude does. Sometimes⦠it has the better idea.