Older posts.
How to Do Canary Deployments with Argo Rollouts 1.10 (2026)
Step-by-step Argo Rollouts canary guide for 2026: install v1.10.1 with Helm and the Gateway API plugin v0.17.0, write a Rollout with weighted steps, add a Prometheus AnalysisTemplate, watch automated rollback, and fix the common errors.
14 minOct 20, 2026How to Build an MCP Server in Python and TypeScript (2026)
Build, test and ship an MCP server on the official SDKs: Python mcp 2.3.0 and TypeScript @modelcontextprotocol/server 2.3.1, with tools, resources, prompts, MCP Inspector, Claude Desktop, Claude Code and VS Code config, stateless HTTP, and packaging.
15 minOct 20, 2026How to Build an AI Agent With Tool Calling in Python (2026)
Build an AI agent from scratch in Python with the Anthropic Messages API: tool schemas, an agent loop driven by stop_reason, tool errors with is_error, max iterations, token budgets, JSON logs, and a second provider through an OpenAI-compatible API.
19 minOct 20, 2026How to Write a Blameless Postmortem: Template and Examples (2026)
A step-by-step guide to writing a blameless postmortem: when one is required, building the timeline from evidence, contributing factors instead of one root cause, why the 5 Whys misleads, owned action items, the review meeting, and a copy-paste markdown template.
15 minOct 20, 2026How to Set Up Backstage as an Internal Developer Portal (2026)
Step-by-step Backstage 1.55 setup for 2026: create-app on Node 22 or 24, PostgreSQL, GitHub sign-in, catalog-info.yaml, software templates, TechDocs, a Kubernetes deploy with the official Helm chart, alternatives, and fixes for common errors.
14 minOct 20, 2026How to Reduce AWS Lambda Cold Starts: Init Duration to SnapStart (2026)
Step-by-step guide to measuring and reducing AWS Lambda cold starts in 2026: read Init Duration, price the August 2025 INIT billing change, pick runtime and arm64, bundle and lazy-load, tune memory, enable SnapStart and provisioned concurrency, and fix common errors.
14 minOct 20, 2026How to Set Up Argo CD for GitOps: Step-by-Step Guide (2026)
Install Argo CD 3.5.5 with Helm chart 10.10.5, structure a GitOps repo, bootstrap with app-of-apps and ApplicationSet, configure sync policies, waves and hooks, add SSO and RBAC, deploy Helm and Kustomize apps, and fix OutOfSync, Degraded and ComparisonError.
14 minOct 20, 2026AI Gateways in 2026: Six Options Compared After LiteLLM's 40-Minute Backdoor
What an AI gateway (LLM gateway) does in 2026 and how LiteLLM, Portkey, Kong, Cloudflare, Envoy AI Gateway (now Agent Router) and OpenRouter compare on routing, budgets, caching and guardrails, plus the LiteLLM PyPI backdoor, three LiteLLM CVEs on CISA KEV, and build vs buy.
13 minOct 20, 2026AI Agent Failures in Production: 5 Incidents, 14 Failure Modes (2026)
What actually goes wrong when AI agents run in production: the Replit, Amazon Kiro, PocketOS and PromptPwnd incidents, the MAST taxonomy of 14 failure modes from 1,642 traces, cost loops, permission mistakes, and the guardrails that stopped them.
12 minOct 20, 2026AI Agent Frameworks Compared (2026): LangGraph, CrewAI, ADK and 7 More
AI agent frameworks compared for October 2026: LangGraph 1.2, CrewAI 1.15, OpenAI Agents SDK 0.24, Claude Agent SDK, Google ADK 2.12, Microsoft Agent Framework 1.22, Pydantic AI 2.57, Mastra and LlamaIndex, with stars, licences, versions and a picking guide.
12 minOct 5, 2026World Models in 2026: Genie 3 at 24 fps, Cosmos 3 at 64B, V-JEPA 2 Planning in 16 Seconds, and an $8.2B Exit to AMD
What a world model is in 2026 and what actually shipped: Genie 3 at 720p and 20 to 24 fps for a few minutes behind a $249.99 subscription, World Labs' Marble and Atlas and the $8.2 billion all-stock sale to AMD, NVIDIA Cosmos 3 at 64B, 16B and 4B under OpenMDW 1.1, V-JEPA 2 planning a robot action in 16 seconds against Cosmos's four minutes, LeCun's AMI Labs raising $1.03 billion at $3.5 billion, the Physics-IQ ceiling of 29.5 out of 100, what inference costs, and a V-JEPA 2 embedding script I ran on a laptop CPU.
14 minOct 5, 2026Workflow Automation in 2026: n8n Published 196 Advisories in Nine Months, 59,558 Hosts Sat Exposed, and the Code Alternative Raised at $12.55B
The no-code automation tools became agent runtimes this year and the security record followed: n8n went from a EUR 250M valuation to a reported $5.2B while publishing 196 GitHub security advisories in 2026 (19 critical), a CVSS 10.0 unauthenticated flaw left 59,558 hosts exposed per Shadowserver, and CISA added one n8n and six Langflow CVEs to its exploited list. Zapier MCP counts 25 million tool calls, Copilot Studio bills 5 credits per agent action, Agentforce ARR passed $1.5B, and Temporal raised $550M at $12.55B with 4,300 paying customers. Plus a hardened n8n queue-mode compose file.
15 minOct 5, 2026Model Collapse in 2026: The Loop Nobody Runs, a 40% Synthetic Phi-4, a 49.9% AI Web, and 300T Human Tokens Left
What the model-collapse research tested versus the headline: Shumailov's Nature loop deletes real data every generation and takes OPT-125m from 20 to 28 perplexity, while accumulating data bounds the error; my 100-generation Gaussian experiment shows median variance falling from 0.98 to 0.36 under replacement and holding at 0.98 under accumulation; how Phi-4 (40% synthetic), Llama 3, DeepSeek-R1 (800k samples), Qwen3, Kimi K2 and Nemotron-CC-v2 (38%) actually use it; Epoch's 300T-token stock, Graphite's 49.9% AI web, Cloudflare's 38,065:1 crawl ratio and the $1.5B Bartz settlement.
15 minOct 5, 2026The 2026 SaaS Selloff: IGV Fell 36%, Then Rose 45%. Revenue Grew 11% to 37% the Whole Time
The SaaSpocalypse checked against filings: Anthropic's Cowork plugins on 30 January, Thomson Reuters' worst day ever on 3 February, $285 billion gone in a day and nearly a trillion in a week, a second leg on Mythos in April, IGV down 36 percent to its 10 April low and up 45 percent since; against that, Q2 2026 revenue growth of 11 percent at Salesforce, 24 at ServiceNow, 36 at Datadog and 37 at Snowflake, median retention flat at 110 percent, median multiples from 4.9x to 3.0x to 4.2x, 4,000 Salesforce support roles, Klarna's reversal and $65 billion of Anthropic run-rate.
13 minOct 5, 2026Policy as Code for AI Agents in 2026: Cedar at the Gateway, Rego in the Hook, and the 11.2% the Model Still Lets Through
What actually enforces limits on AI agents in 2026: OPA 1.21 and Rego v1 after the founders moved to Apple, Cedar in Amazon Bedrock AgentCore Policy (GA 3 March 2026, 13 regions, default deny), Kyverno 1.19 retiring ClusterPolicy for CEL, Claude Code hooks that deny even in bypass mode, Codex's Seatbelt and bwrap sandboxes, the MCP 2026-07-28 authorization spec, and why none of it is optional while browser-agent injection success sits at 11.2% and OpenAI says the problem is unlikely to ever be fully solved. With a tested Rego policy and a Cedar policy for tool calls.
13 min