Engineering log34 entries
The engineering log.
Build notes from the people making the harness: what shipped, what we cut, and what the work taught us.
Notes on AI coding agents, orchestration, multi-repo engineering, and persistent memory.
Latest entryJul 16 2026·12 min read
Why AI coding agents need an engineering harness
A category thesis for the layer around coding agents, with current Skyflo behavior separated from the complete architecture that remains a target.
Read the entry
The engineering harness
Agent orchestration, multi-repo missions, model routing, and engineering memory.
2026
4 entriesJul 08One Model Is the Wrong NumberEngineering roles have different model needs. The architecture case for per-role routing, the provider access Skyflo supports today, and the managed lane that remains Planned.9 minharnessai-agentsJun 28The Case for Engineering MemoryEvery AI session starting from zero is an organizational tax. How source-linked personal memory works today, and where Preview and Planned memory capabilities begin.10 minmemoryharnessJun 21“Done” Is a Claim. Evidence Is the Standard.Independent review is available today. This essay separates that current boundary from the planned CI, deployment, telemetry, and evidence-gated completion architecture.9 minverificationmissionsJun 14Your Change Does Not Live in One RepositorySeveral agents can edit several repositories. The remaining problem is keeping one contract, landing order, approval boundary, and review record across them.11 minmissionsharness
Open-source Kubernetes agent
Earlier entries about the separate Apache-2.0 Kubernetes operations project, not the harness.
2026
9 entriesMar 15Kubernetes observability stops before the fixObservability surfaces signals. Operations still require a bounded decision, an approval gate, typed execution, and verification.8 minobservabilitykubernetesMar 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 minsafetyapproval-gatesMar 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 minjenkinsci-cdFeb 28Reducing Kubernetes MTTR with an approval-gated AI agentHow an approval-gated Kubernetes agent can gather evidence, propose a bounded change, execute through typed tools, and verify the result.8 minmttrkubernetesFeb 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 minsafetysecurityFeb 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 advantages of both without hiding the control boundary.9 minai-agentsdevopsFeb 21An illustrative Skyflo walkthrough: investigating payment-service latencyA representative walkthrough of Plan, Approve, Execute, and Verify. The values and timings are examples, not measured customer results.10 minwalkthroughkubernetesFeb 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 minarchitecturelanggraphFeb 13The operational work coding agents still leave behindCoding agents can produce a change. Deployment, incident response, operational verification, and durable context still require a separate control loop.9 minai-agentsdevops
2025
20 entriesDec 14Token + Latency Analytics: Building a Dashboard That Engineers Actually UseTurning TTFT/TTR and cost into trends, budgets, and actionable insights across your conversations.9 minroadmapanalyticsDec 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 minslackintegrationsNov 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 minroadmapengineNov 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 minroadmaporchestrationNov 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 minroadmapcontextNov 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 minkubernetesmetricsNov 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 minhelmkubernetesOct 26Kubernetes Rollbacks with Confidence: Rollout History + Undo as First‑Class ToolsShipping safe rollback primitives for deployments/daemonsets/statefulsets-and where approvals belong.8 minkubernetesmcpOct 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 minaccessibilityuiOct 12Real-time token metrics: TTFT, TTR, cached tokens, and costOperators don’t trust black boxes. Here’s how we expose LLM latency and usage without spamming the UI.11 minobservabilitymetricsOct 05FastMCP Streamable HTTP: Migrating Off Legacy SSE TransportWhy we moved, what broke, and how Streamable HTTP made MCP communication simpler and more reliable.10 minmcpreliabilitySep 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 minreleaseuiSep 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 minreleaseuiSep 14Storing Integration Credentials the Boring Way: Kubernetes Secrets + ReferencesHow Skyflo stores integration credentials as Kubernetes Secret references without putting secrets in the prompt.9 minsecuritykubernetesSep 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 minjenkinsci-cdAug 31v0.2.0: The rebuild. From WebSockets to SSE and a simpler agent coreWhat changed when Skyflo replaced WebSockets with SSE and simplified the agent core.7 minreleasearchitectureAug 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 minssereliabilityAug 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 minmcptoolingAug 10Inside Skyflo’s LangGraph Workflow: Plan → Approve → Execute → VerifyHow Skyflo compiles a compact graph, streams progress, and decides when to continue, stop, or request approval.10 minarchitecturelanggraphAug 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 minsafetysecurity
The Kubernetes agent is a separate Apache-2.0 open-source project.
RSS feed