EdTech Tracker

← Coding lens

human in the loop

technique judged 99% likely a named technique or architecture

First seen
2025-10-27
Independent sources
13
Articles
35
Last 4 weeks vs prior
0 vs 9

See how it has spread across media tiers

Mentions over time

Articles per week (by publish date) using the term, in any spelling.
05102025-W432026-W272026-W41
Table view
WeekArticlesSources
2025-W4311
2026-W0322
2026-W0922
2026-W11101
2026-W1511
2026-W2421
2026-W2533
2026-W2711
2026-W3211
2026-W3311
2026-W3411
2026-W3811
2026-W3922
2026-W4063
2026-W4111

In their words

Repository navigation Add QEP428: No ai contributions permitted - #387 Conversation | Hi, maybe this strong take deserves a bit of context of why we want to go further than the previous "Human in the loop" policy So, for this reason, a huge +1 for me.

LangGraph splits this into checkpointers (thread-scoped: continuity, human-in-the-loop, time travel, fault tolerance) and stores (cross-thread facts and preferences); Microsoft Agent Framework's workflow engine likewise offers checkpointing and hydration.

For critical or destructive actions, we enforce a strict Human-in-the-Loop protocol mandated by the backend.

from typing import Protocol, Literal from dataclasses import dataclass @dataclass(frozen=True) class Proposal: decision_id: str capability: str action: dict # the structured, proposed change — NOT yet applied confidence: float routing: Literal["auto", "hitl_recommended", "hitl_required", "reject"] reasoning: list[str] evidence: list[dict] class Agent(Protocol): def propose(self, ctx: "Context") ->

Human in the loop for AI agents means a person approves, reviews or is notified about specific actions the agent takes, instead of trusting it end to end.

Human-in-the-Loop: For destructive actions (like sending a mass email or deleting an event), the server intercepts the intent, pauses execution, and forces the user to confirm the action in the UI.

She also covers human-in-the-loop control of autonomy, LLM-as-judge checks, open source models such as DeepSeek v3, and compliance in regulated environments.

In the rush to adopt AI and automation, many teams implement human-in-the-loop (HITL) frameworks.