skyflo

Engineering log34 entries

The engineering log.

Essays and build notes on engineering harnesses, persistent missions, isolated specialist work, and local cross-mission memory.

Latest entryJul 16 2026·12 min read

What Is an Engineering Harness?

Coding agents made file-level work fast and left coordination — the actual bottleneck — untouched. Defining the engineering harness: one system that carries objectives across repositories, infrastructure, CI/CD, and production, with verification and memory that compounds.

Read the entry

2026

13 entries
Jul 08One Model Is the Wrong NumberMissions contain heterogeneous work: deep implementation, broad research, high-volume verification. Per-role model routing — frontier where it pays, fast where it doesn't, local where privacy demands — and why the harness is the durable layer.9 minJun 28The Case for Engineering MemoryEvery AI session starting from zero is an organizational tax. Engineering memory as infrastructure: personal, organizational, and outcome records — verified against evidence, written as a by-product of work, recalled by every future mission.10 minJun 21“Done” Is a Claim. Evidence Is the Standard.AI agents report success with total confidence, whether or not the work landed. Why verification must be structural: an independent agent, an explicit evidence chain from change to runtime, and completion as a provable state.9 minJun 14Your Change Does Not Live in One RepositoryReal engineering changes span repositories, infrastructure, pipelines, and runtime. Why single-repo agents plateau, what coordinated change requires, and how missions model it: pinned interfaces, delegated agents, and drift checks while work is open.11 minMar 15Why Kubernetes Observability Alone Is Not Enough and How AI-Powered Operations Can Change EverythingObservability surfaces signals. Operations require decisions and safe execution. This article explores the missing control loop between monitoring your cluster and actually fixing what breaks.8 minMar 04Why Approval Gates Must Be Architectural in DevOps AI AgentsApproval gates in DevOps AI agents cannot be UI toggles or confirmation prompts. They must be enforced at the execution engine level, below the model.10 minMar 01AI for CI/CD Pipeline Debugging with Jenkins and SkyfloHow Skyflo's Jenkins MCP tools work — from natural language build triggering to log analysis, parameter-aware job management, and cross-tool debugging.8 minFeb 28AI for Reducing MTTR in Kubernetes: From 45 Minutes to 5Why MTTR is still high despite better tooling, and how AI agents collapse each phase of incident resolution — detection, diagnosis, remediation, and verification.8 minFeb 27Why Human-in-the-Loop Is Non-Negotiable for Production AIReal failure scenarios, architectural safety gates, and why the approval layer must live in the engine — not the UI. A safety philosophy for AI infrastructure agents.8 minFeb 24Agentic AI vs Script Automation in DevOpsBash scripts are brittle. Raw AI is dangerous. Agentic AI — with typed tools, planning, and verification — gives you the best of both worlds. Here's why.9 minFeb 21Fixing a Latency Spike in payment-service: A Real Skyflo WalkthroughA full incident walkthrough showing Plan-Execute-Verify in action — from natural language query to root cause identification, approved fix, and verified resolution.10 minFeb 17How Skyflo Works Under the Hood: A Unified Agent Architecture for KubernetesA deep dive into LangGraph orchestration, MCP tool protocol design, and why typed tool execution prevents prompt injection in production infrastructure.12 minFeb 13Everything After Code Is a Bottleneck. AI Agents Are the Fix.AI coding assistants solved code generation, but deploying, operating, and keeping production alive remains manual and dangerous. This is the post-code bottleneck — and it's why the DevOps industry is converging on AI agents.9 min

2025

20 entries
Dec 14Token + Latency Analytics: Building a Dashboard That Engineers Actually UseTurning TTFT/TTR and cost into trends, budgets, and actionable insights across your conversations.9 minDec 07Slack as an Ops Console: Bringing Human‑in‑the‑Loop to Where Work HappensA single-tenant Slack bridge plan: streamed updates, approvals in-thread, and guardrails that don’t feel heavy.12 minNov 30Auto‑Summarization for Long Conversations: Keep Context, Cut the TaxA design for summarizing older turns when you approach context limits—without losing the details operators care about.10 minNov 23Programmatic Tool Calling: When an LLM Should Write Glue CodeLoops, batching, parallelism, and summarization—where code beats prompts, and how to sandbox it safely.13 minNov 16The Case for Tool Search: Shrinking Context Without Losing CapabilityA roadmap post: defer tool schemas until needed, reduce token bloat, and keep the agent accurate under pressure.12 minNov 09Kubernetes Metrics for AI Agents: `kubectl top` Tools and What They UnlockAdding read-only metrics tools so an agent can answer the question everyone asks first: “what’s hot right now?”8 minNov 02Helm Template as a Safety Primitive: Preview Before You Touch the ClusterRendering manifests with inline values, catching surprises early, and building a diff-first culture.7 minOct 26Kubernetes Rollbacks with Confidence: Rollout History + Undo as First‑Class ToolsShipping safe rollback primitives for deployments/daemonsets/statefulsets—and where approvals belong.8 minOct 19Designing a Terminal‑Inspired UI That’s Actually AccessibleFocus, live regions, contrast, and keyboard navigation—what we changed to make a command-center UI work for everyone.9 minOct 12Real‑Time Token Metrics: TTFT, TTR, Cached Tokens, and Cost (Trust Builders)Operators don’t trust black boxes. Here’s how we expose LLM latency and usage without spamming the UI.11 minOct 05FastMCP Streamable HTTP: Migrating Off Legacy SSE TransportWhy we moved, what broke, and how Streamable HTTP made MCP communication simpler and more reliable.10 minSep 28v0.3.2: Batch Approvals Without Losing Safety (Approve All, Safely)Designing bulk approval controls that respect read-only tools, remain idempotent, and keep the operator in control.9 minSep 21v0.3.1: Chat Queueing + Server‑Side History Search (UX for Real Operators)Why fast history, debounced search, and prompt queueing matter when you’re triaging an incident at 2am.8 minSep 14Storing Integration Credentials the Boring Way: Kubernetes Secrets + ReferencesHow Skyflo avoids leaking secrets into prompts, keeps credentials server-side, and still feels seamless in the UI.9 minSep 07Jenkins in Skyflo: Secure Auth, CSRF, and Parameter‑Aware BuildsA deep dive into the Jenkins toolset, integration-aware discovery, and why builds must be parameter-first.12 minAug 31v0.2.0: The Rebuild — From WebSockets to SSE and a Cleaner Agent CoreWhat we learned rebuilding Skyflo’s core loop, and why “simpler” was the biggest performance unlock.7 minAug 24SSE Done Right: Streaming Tokens + Tool Events Without Melting Your ProxyA hands-on guide to reliable server-sent events for long-running infra tasks, including NGINX hardening.8 minAug 17MCP in Practice: Standardizing DevOps Tools So AI Can’t Go RogueWhy Skyflo’s MCP server exists, how tools are validated, and what “readOnlyHint” really buys you in prod.11 minAug 10Inside Skyflo’s LangGraph Workflow: Plan → Execute → Verify (Without the Hype)How Skyflo compiles a compact graph, streams progress, and decides when to continue, stop, or request approval.10 minAug 03Why Human-in-the-Loop Is Non‑Negotiable for AI in Production OpsA practical look at approvals, safety gates, and why “agent autonomy” should still ship with guardrails.9 min

Entries before 2026 cover the open-source k8s-agent lineage.

RSS feed