Engineer systems that
think, act, and ship.
Practical guides on building autonomous AI systems, scaling engineering teams, and technical leadership.
Latest Dispatches
The 200-Token System Prompt That Beats Your 4000-Token One
Long system prompts grow by accretion and quietly degrade quality through attention dilution, the curse of instructions, and contradictions. Here's the compaction discipline that gets a 200-token prompt to outscore a 4000-token one.
Adding a Modality Is a Privacy-Classification Event, Not a Feature Flag
Shipping vision input under the consent flow you wrote for text quietly multiplies your PII surface — EXIF metadata, adjacent-content leaks, and contract scope drift each demand their own classification, retention, and audit.
The Agent Accountability Stack: Who Owns the Harm When a Subagent Causes It
When a subagent sends the wrong email, deletes a record, or charges a customer incorrectly, liability is diffuse. Here's how to design audit trails and authorization checkpoints that create real accountability without killing autonomy.
Agent Identifiability: When Your Trace Can't Tell You Which Agent Did What
Multi-agent traces collapse into a hairball of identical agent.run spans the moment something breaks. The five-field identity model that fixes it — stable role, parent agent, instance ID, model and prompt version, outcome — and why your APM won't surface any of it by default.
The Agentic Debugger's Trap: When Your Agent Patches Faster Than You Can Diagnose
Agent-generated patches close bugs faster than engineers can diagnose them. The cost is a codebase whose failure modes only the agent understands.
The AI Bill of Materials: What Your Dependency Tree Looks Like When Procurement Asks
Most AI teams answer 'show us your dependency tree' with a Slack thread. AIBOM turns that into a query — a continuously generated inventory of models, prompts, tools, and datasets that satisfies regulators and procurement before they ask.
The AI Bystander Effect: Why Five-Team Launches Ship Eval Suites Nobody Watches
AI features fail the way bystanders fail to call 911 — not because nobody noticed, but because everyone assumed someone else owned the call. Why a single named DRI for output quality is the only fix that scales.
Your AI Feature Needs a Kill Switch That Isn't a Deploy
A standard deploy-rollback takes thirty minutes; a misbehaving LLM ships bad outputs to customers in seconds. Here is the off-switch primitive your AI feature needs before its first incident — the four-flag family, the detection signals that fire it, and the test discipline that keeps it real.
Your AI Feature Has No DRI: Why It's Drifting Without a Quarterly Goal Owner
AI features straddle product, engineering, research, and FinOps — and end up owned by none of them. Here's the org pattern that stops them from drifting between quarterly reviews.
Your AI Feature Is Only As Reliable As The ETL Pipeline Nobody Owns
Most AI quality regressions are upstream data problems wearing an AI costume. Data contracts, lineage, and paired on-call turn the invisible ETL seam into a first-class artifact.
AI Feature Soak Windows: Why a Two-Week Canary Misses What Actually Matters
Two-week canaries catch crashes; AI features fail by trends. A practical case for soak windows, slow-failure metrics, and a rollback path that stays warm long enough to matter.
AI Procurement Clauses Your Lawyers Haven't Learned to Ask For Yet
Standard SaaS templates miss the AI-specific clauses — training data exclusions, model pinning, output indemnity, audit rights — that decide whether your vendor relationship survives the next model swap.
About Tian Pan
I'm Tian Pan, an engineer-founder focused on agentic engineering — building autonomous AI systems and scaling engineering teams. I write practical guides on system design, technical leadership, and shipping with AI agents. Previously an early engineer at Uber, Brex, and IoTeX.
