Weekly digest · 2026-W15
April 6, 2026 – April 12, 2026
6 entries · 24 min total · Foundations & Protocols (6) · Governance & Safety (3) · Infrastructure & Economics (1) · Enterprise & Strategy (1)
Entries
- Day 25 · April 12, 2026Agent Observability at ScaleTraditional Application Performance Monitoring (APM) tracks deterministic systems: HTTP latency, database query time, error rates. Agents break these assumptions in three critical ways:
- Day 24 · April 11, 2026Advanced Agent Testing & Red TeamingDay 21 of your Agentic AI learning journey dives into the red team. As agents proliferate in production — handling payments, browsing the web, writing code, and managing enterprise workflows — attackers are already…
- Day 23 · April 10, 2026Agent Security & Identity in the Economy 2.0How autonomous agents authenticate, authorise, pay, and are governed -- the complete 2026 security playbook for spending agents and agentic commerce.
- Day 22 · April 9, 2026The Agent Economy 2.0MPP + SPTs + MoonPay Wallets + Visa/Mastercard rails = the full payment stack for agents is now live in production. This is not a future vision -- real money is moving through these systems today.
- Day 21 · April 8, 2026Multi-Agent CommunicationAWS Bedrock, AG2, CopilotKit, Microsoft, Oracle are all in production with AG-UI. Its 16 event types are the "HTTP status codes" of agent-UI communication.
- Day 20 · April 6, 2026Attie by Bluesky -- The First Agentic AI App to Go ViralAttie is an AI assistant built by the Bluesky team that lets any user design their own social feed algorithm using plain natural language -- no code required.
Takeaways of the week
- 3 Instrument with OTEL first, choose backend second Add open 3 Instrument with OTEL first, choose backend second Add opentelemetry-sdk to your agent stack today. Pick Langfuse (OSS, self-hosted) or Arize Phoenix as your primary backend. The data flows the same -- you can switch backends without re-instrumenting. Day 25
- Health fi Tool Intelligence fi LLM Spans fi Memory/Retrieval Health fi Tool Intelligence fi LLM Spans fi Memory/Retrieval fi Drift & Anomaly. Don't try to pack everything into one graph. Use separate dashboard panels with linked drill-down traces. Day 25
- Run Garak on every agent before it ships Add Garak to your CI pipeline as a pre-deploy gate. It takes under 5 minutes to scan for the top 20 attack categories. If attack success rate exceeds your threshold, block the deploy. This is the minimum viable agentic security posture. Day 24
- Threat-model your delegation chains In any multi-agent system, draw the full delegation graph and mark every trust boundary. At each boundary, ask: what happens if the message arriving here was crafted by an attacker? SVID attestation and signed A2A cards are your primary defences. Day 24
- Payment agents need scoped, short-lived credentials SVI Ds (30-300s TTL) + OAuth scopes + MCC whitelists = the minimum viable security stack for any agent that can spend money. Day 23
- Fraud detection must be agent-native Classic velocity rules and device fingerprinting don't apply. Use SVID mismatch, scope creep attempts, and delegation chain breaks as your fraud signals. Day 23
Viral and open-source picks
- Straiker Ascend AI Day 24
- Project Glasswing by Anthropic Day 23
- Shopify isn't just building an AI feature -- it's Day 22
- Oh-my-codex (OMX) github Day 21
- Attie by Bluesky The first agentic AI app to go vi Day 20
Watch list
- Day 22 — Agent Observability at Scale: Building production-grade OTEL dashboards for agents, alerting on anomalous tool call patterns, and using LangSmith + Arize Phoenix to catch drift before it becomes an incident. Plus: the emerging Agent SRE role. Day 24