SZL SENTIENT ZERO LABS
Newsletter for builders

Practical AI insights
for founders & engineers

Four focused series. 28 issues. Zero hype. Each ends with a checklist you can use immediately.

Subscribe for free Browse issues
28 Issues published
4 Focused series
28 Actionable checklists

Four series. 28 issues.

Whether you're deciding what to build, building it yourself, shipping production tooling, or wiring up memory — there's a series for you.

Founders 6 issues

Pragmatic AI for Founders

Evaluate AI opportunities, avoid the wrapper trap, measure real ROI, and build defensible AI products. Written for non-technical founders and product leaders.

  • Mental models for AI
  • Prompt engineering (without code)
  • Agent design for business
  • Build vs Buy strategy
Read the series →
Technical 8 issues

Agent Design Fieldbook

Design, build, and operate AI agents in production. An 8-layer architecture from data layer to RAG, with real code and battle-tested patterns.

  • 8-layer agent architecture
  • Schema design & field registries
  • Intent classification & filter extraction
  • Memory, ranking & RAG patterns
Read the series →
Tools 7 issues

Building Effective Tools for AI

Build production-grade MCP servers, A2A agents, and observable tool systems. Grounded in the open-source Recall memory layer.

  • MCP server design & deployment
  • A2A agent coordination patterns
  • Tool observability & tracing
  • Recall memory layer integration
Read the series →
Memory 7 issues

Memory in AI Systems

How AI agents store, score, manage, and retrieve memories across sessions. Grounded in the open-source Recall memory layer.

  • Extraction pipeline design
  • Importance & confidence scoring
  • Contradiction detection & decay
  • Hybrid retrieval & evaluation
Read the series →

What makes this different

01

Starts with a real story

Every issue opens with a concrete failure or success. No abstract theory — real systems, real outcomes.

02

One idea at a time

Each issue covers one concept deeply. You'll finish knowing it well enough to use it, not just recognize it.

03

Ends with a checklist

Every issue closes with a scorecard or checklist you can apply to your own product immediately.

Latest issues

Founders

#6
Build vs Buy vs Embed: AI Strategy That Actually Works Most AI strategy failures come from building when you should buy, buying vendors that can't handle your data layer, or measuring ROI without counting the disasters you prevented.
→ #5
Silent Failures and Monitoring AI in Production The scariest AI failures are silent -- no errors thrown, just slow degradation -- and monitoring drift is the only way to catch them before users leave.
→ #4
Where AI Breaks and The Data Layer Solution AI fails predictably in two ways -- hallucination and bad retrieval -- and designing your data layer first prevents 80% of production disasters.
→

Technical

#8
The Product Deep-Dive Layer: When Users Want More Than Specs When users want to go deep on a product -- reading reviews, understanding thermal performance, checking compatibility -- RAG lets you search unstructured knowledge that doesn't fit in structured columns.
→ #7
The Sort & Rank Layer: Ordering Results Intelligently Sorting isn't just ORDER BY -- define what 'best' means for each field, handle JSONB with SQL expressions, and let the LLM infer user intent from keywords like 'cheapest' or 'best'.
→ #6
The Memory Layer: Conversations That Persist Agents need memory -- not just chat history, but structured context (what was fetched, what was selected, what tokens were used) persisted to database for multi-turn conversations.
→

Tools

#7
The Tool Ecosystem in 2026 MCP is no longer an emerging standard — it's infrastructure, with real security threats, five open problems, and a clear picture of what teams can solve today versus what requires ecosystem-level coordination.
→ #6
Tool Observability Every tool call produces one record that answers three questions — did it succeed, how long did it take, and how much did it cost — and those three questions, asked consistently, are the foundation of everything useful you'll ever know about your tool layer in production.
→ #5
A2A — When Agents Need to Talk to Each Other A2A gives multi-agent systems a task lifecycle that makes every state in a sub-agent's execution visible, pausable, and recoverable — solving the coordination failures that async function calls cannot.
→

Memory

#7
Building a Memory System End-to-End Schema to governance — the complete implementation. Every component from the series assembled, every decision justified, and the migration path from SQLite to Postgres+pgvector.
→ #6
Memory Failures — Named and Fixable Six memory failure modes with detection queries and mitigations. Plus GDPR erasure: the single SQL call that satisfies Article 17.
→ #5
Four Design Patterns in Order Most teams jump to Pattern 3 (vector store) or Pattern 4 (episodic log). Most should start with Pattern 2. A decision matrix for which memory architecture your use case actually requires.
→

Get every issue in your inbox

No spam. No fluff. Unsubscribe anytime.