Agents

Human-in-the-Loop That Ships: Approvals, Interrupts, and Resume in LangGraph

October 19, 2026

An approval step is not a confirm dialog bolted onto an agent. It is a durable pause, a decision record, and a resume path that has to survive a deploy. Here is how we build them.

Long-Term Agent Memory: What to Write, What to Read, and What to Forget

September 28, 2026

Cross-session memory is a small database your model writes without review. Split it by type, write on a decision instead of every turn, read narrowly, and measure interference as well as recall.

Subagents Without the Sprawl: When to Split a LangGraph Agent, and What It Costs

September 21, 2026 · TokenTailors

Multi-agent architectures are the default answer right now. Most teams need one or two subagents, not a org chart. Here is how to decide, and how to keep the split from eating your latency and your debuggability.

Latency Budgets for LLM Apps: Where the Seconds Actually Go

September 21, 2026 · TokenTailors

Time to first token, stage-level timing, prefix caching, parallel retrieval, and streaming: how to find and cut the seconds in a production LLM app without trading away quality.

Migrating to LangChain 1.0: create_agent, Middleware, and the Code You Get to Delete

September 17, 2026

A staged migration off AgentExecutor and legacy chains: what create_agent and agent middleware actually change, what to delete instead of port, and how to guard the refactor with evals.

Evaluating Agents: Score the Trajectory, Not Just the Final Answer

September 14, 2026 · TokenTailors

Final-answer pass rates hide the ways agents actually fail: wrong tool, right answer by luck, twelve steps where two would do. How to build trajectory evals for LangGraph agents.

Indirect Prompt Injection Is a Data Problem: Containing Untrusted Text in LangGraph Agents

September 14, 2026

Every retrieved document and tool response is untrusted input. Provenance tracking, capability limits, deterministic action gates, and the injection evals that tell you the defenses hold.

Context Engineering for Long-Running Agents: What to Keep, Compact, and Throw Away

September 11, 2026 · TokenTailors

An agent that works for five turns and degrades by thirty has a context problem, not a model problem. Budgets, tool-output pruning, compaction, and external memory in LangGraph — with the evals that tell you it worked.

Wiring MCP Tools Into a LangGraph Agent Without Losing Control

September 10, 2026 · TokenTailors

MCP makes it trivial to hand an agent thirty tools. Tool selection accuracy, schema discipline, permission boundaries, and how to measure whether the agent calls the right thing.

LangGraph Checkpointing in Practice: Durable Agents Without Ceremony

June 22, 2026

Checkpointing is the LangGraph feature that separates production agents from demo loops: resumable state, human-in-the-loop pauses, and replayable failures.