David

Tech exec & startup founder empowering software teams. AI/Networking/Cyber. Husband, father, adventurer. Passionate about BJJ, Ducatis, and powerlifting.

[David @davidlapsleyio]

Context is the constraint nobody plans for.

Models keep getting better. Context management determines whether you can use that capability past 10-15 features.

Full post with steering documents, context budgeting, and truncation strategies: https://t.co/rBEpoJKrVn

[David @davidlapsleyio]

Your AI's context window is full. And most of what's in it doesn't matter.

I built a spec pipeline for 20+ feature products. By feature 12, the AI was hallucinating component names. By feature 18, prompts hit 100KB.

More context made it worse. Here's what actually worked. 🧵

[David @davidlapsleyio]

Don't use LLM summarization to compress context. Use rule-based extraction.

I lost a full day when the summarizer dropped a protocol definition it deemed "redundant." Three downstream features invented incompatible versions.

Deterministic extraction: zero cost, microseconds, same output every time.

[David @davidlapsleyio]

30 min writing a precise spec saves 3+ hours of rework. 6:1 return.

A team shipping 10 features/quarter saves 25-30 hours by investing 5 hours in better specs.

Stop tuning prompts. Start writing specifications.

Full post: https://t.co/elmY3ZOGPv

[David @davidlapsleyio]

Your AI coding agent isn't broken. Your specifications are.

After 18 months of building with AI agents daily, I've learned that "AI drift" is almost always a product problem, not an engineering problem.

Here's a framework for diagnosing where it actually comes from. 🧵

[David @davidlapsleyio]

When your agent builds the wrong thing:

1. Check the spec (does it exist? does it have acceptance criteria?)
2. Check the product artifacts (does it trace to a customer problem?)
3. Check the design (does architecture match requirements?)
4. Only then blame the model

70% of "the agent got it wrong" traces to step 1 or 2.

[David @davidlapsleyio]

Specifications are no longer documentation for humans. They're contracts for machines.

The spec is the API contract between product thinking and code generation. Treat it like one.

https://t.co/wVTMPWdL7b

#AI #SDLC #SpecDrivenDevelopment #SoftwareEngineering

[David @davidlapsleyio]

Amazon's Working Backwards isn't just product methodology. It's a specification pipeline.

7 steps. 4 human gates. Full traceability
from code to customer evidence.

https://t.co/Hh1Cb9NFgZ

#AI #SDLC #WorkingBackwards #ProductManagement

[David @davidlapsleyio]

Amazon's Working Backwards isn't just product methodology. It's a specification pipeline.

7 steps. 4 human gates.

https://t.co/Hh1Cb9NFgZ

[OpenClaw🦞 @openclaw]

🦞 OpenClaw 2026.2.19

⌚️ Apple Watch MVP
🔧 Gateway auth & device management
🔌 OTEL v2 migration + plugin/hooks hardening
🔒 40+ security hardening fixes
🖥️ Dashboard now nudges you to update — stay secure, stay current

Biggest hardening drop yet!🛡️ https://t.co/iRIQijGXQH

[David @davidlapsleyio]

Amazon's Working Backwards SDLC isn't just for Amazon. A 5-person team that builds the wrong thing burns 25% of runway. Here's how to adopt it in 5-10 days.

https://t.co/cLO8cY5gVQ

[David @davidlapsleyio]

3/ The article covers:
✓ Three infrastructure patterns that work at scale
✓ Why $5K becomes $57K per model in production
✓ GPU optimization (50-70% cost reduction)
✓ Real decision frameworks for hybrid/cloud/on-prem

📝 Full guide: https://t.co/FgnvWGkd3M

🎥 Video: https://t.co/bF8fwQrzmu

[David @davidlapsleyio]

🧵 87% of AI projects never make it to production.

After decades at AWS, Cisco, and startups, here's what I've learned about being in the 13% that succeed.

Thread 👇

#EnterpriseAI #MLOps #AIInfrastructure #Kubernetes #PlatformEngineering

[David @davidlapsleyio]

2/ Example: Healthcare AI

Month 3: POC approved, $5K/month, ready to deploy
Month 6: Legal says "HIPAA compliance required"

Cost: $5K → $200K/month
Timeline: 3 months → 18 months to production

This is exactly how projects end up in the 87%