Skip to content
Blog

Thinking about AI infrastructure

Identity, governance, observability, and what it takes to ship autonomous software at scale.

Featured

Tutorial

Agents that debug agents

A workflow fails at 2am. Instead of a human paging through logs, an operator agent fetches the failed DAG, diagnoses the root cause, and drafts a fix behind an approval gate while you sleep.

Jul 2, 2026 · 36 min

Tutorial

The deployment that promotes itself

A self-tuning rollout deploys a new agent version at a small traffic weight, then an operator agent polls per-version failure rates and shifts weight itself, promoting on wins and rolling back on regressions.

Jul 2, 2026 · 30 min

Tutorial

Claude Code as a function

Call a multi-turn coding agent like Claude Code from your backend with a dollar budget cap, a turn limit, restricted tools, and typed output.

Jul 2, 2026 · 21 min

Tutorial

Build your own personal assistant

A reasoner with per-chat memory that reaches your other agents, plus a 70-line Telegram bridge you own. Text your personal stack from your phone.

Jul 2, 2026 · 27 min

Tutorial

Human approval gates in 20 lines

Suspend a running agent on a low-confidence decision, notify a reviewer, and resume exactly where it stopped. The wait state lives in the control plane, so it survives restarts.

Jul 2, 2026 · 30 min

Tutorial

Simulate a market with 200 agents

A market simulation where 200 trader reasoners read a shared order book from global memory, decide with a cheap model, and post orders back every round, while an orchestrator fans them out and code clears the price, all watchable live in the dashboard DAG.

Jul 2, 2026 · 33 min

Tutorial

The agent that finds its own tools

A reasoner that calls app.ai(tools="discover") sees every capability registered on the mesh at call time and invokes what it needs, so deploying a new agent tonight makes it callable by tomorrow with zero redeploys.

Jul 2, 2026 · 30 min

Tutorial

How we ran a 250-agent security audit for 90 cents

A full security audit that runs 166 to 255 agent calls and confirms 28 exploitable findings costs between 18 and 90 cents, because each call is small, routed to the right model, and capped.

Jul 2, 2026 · 24 min

Tutorial

Approve your agents from your phone

Notify yourself when an agent pauses, then approve or reject it with one tap from a lock screen. A five-line notify plus a twenty-line signed handler turns any pause into a phone gate.

Jul 2, 2026 · 36 min

Tutorial

An agent that ships new versions of itself

A self-improvement loop where a production agent records its own failures to memory, an improver agent reads them and writes a revised prompt, and that prompt ships as a new version the self-tuning rollout then canaries behind a human gate.

Jul 2, 2026 · 33 min

Tutorial

Pipelines that build themselves

An intake reasoner reads the input, decides which analysis dimensions it actually needs, then the orchestrator spawns exactly those specialists with prompts written at runtime, so the pipeline shape is a trace of what happened rather than a graph declared upfront.

Jul 2, 2026 · 30 min

Tutorial

A nightly maintenance fleet for your repos

One scheduled reasoner that clones your repos at 3am, runs a budget-capped coding agent on each, and leaves a morning summary and a stack of ready PRs behind an approval gate.

Jul 2, 2026 · 39 min

Tutorial

Thinking in reasoners

The capstone mental model for the personal stack. Five habits that turn a pile of prompts into a system, each shown as a small before and after, with the one table you need for deciding between app.ai and app.harness.

Jul 2, 2026 · 24 min

Tutorial

From LangGraph prototype to production

The mechanical path from a LangGraph StateGraph that works in a notebook to reasoners other services can call, retry, and run for 40 minutes.

Jul 2, 2026 · 24 min

Tutorial

One control plane for XGBoost and agents

Wrap a trained XGBoost model as a skill, serve 95% of traffic in milliseconds, and cascade the low-confidence remainder to a reasoner. Same tracing, same DAG, one ops story.

Jul 2, 2026 · 27 min

Tutorial

Your personal control plane

Run AgentField in local mode on your own laptop or homelab, register one agent, and call it over HTTP. This is the substrate the rest of the personal stack builds on.

Jul 2, 2026 · 24 min

Tutorial

Add an agent mesh to your existing FastAPI or Next.js app

Deploy a reasoning agent as a sidecar service and call it over REST from the app you already have. No framework adoption, no rewrite.

Jul 2, 2026 · 27 min

Tutorial

Agents that wake up when data changes

Declare @app.memory.on_change("order_*") and a handler fires whenever a matching key changes, written by any agent, in any scope. No cron, no broker, no consumer groups.

Jul 2, 2026 · 33 min

Tutorial

Agents that run for three days

Fire an agent with one POST, close the connection, and get a signed webhook when it finishes hours or days later, backed by a durable PostgreSQL queue with retries.

Jul 2, 2026 · 30 min

Blog — AgentField