Agent Template · parallel fan-out (map) · agents calling agents · token budget (quota)

Batch briefing: Durable Fan-Out with a Cost Ceiling

Durable parallel fan-out with a cost ceiling: a MAP node fans one child agent out per topic (two at a time), collecting a brief for each — a crashed worker resumes only the unfinished branches. Each worker checks a shared daily token budget BEFORE calling its model, so an over-budget fleet returns budget notices instead of burning tokens. Ships with a weekly schedule trigger, DISABLED until you arm it.

How It Works

A map node fans one child agent out per topic, two at a time; if the worker crashes, only the unfinished branches resume. Each worker starts with a token-budget quota, so the shared daily budget accumulates and over-budget branches return a notice instead of a brief.

It ships with a weekly schedule trigger that is disabled — arm it when you want unattended Monday-morning briefs.

Try It

In TheYgent, open Settings → Samples.
Fill the model slots below with models from your registry, then click Install on Batch briefing.
Open the installed agent and run it with the example input.

["on-device LLM inference", "vector databases", "EU data-residency rules"]

The Graph

Every node in the agent and where its output goes, read from the template itself.

sample-batch-briefing

Node	Type	Sends its output to
Topics	`input`	One worker per topic
One worker per topic	`map`	Briefs
Briefs	`output`	—

Child agent: sample-briefing-worker

Node	Type	Sends its output to
Topic	`input`	Shared daily budget
Shared daily budget	`quota`	Write the brief (on `allow`); Budget exhausted (on `deny`)
Write the brief	`llm`	Brief
Brief	`output`	—
Budget exhausted	`output`	—

More Templates

two models in one run

Hybrid reasoner

Two Models in One Run — Two models in one run: a local triage model classifies every request and a router sends easy ones to your local model and hard ones (coding, analysis, long-form) to an API model.

See the template → data privacy

Private SQL analyst

Data Privacy by Construction — A data-privacy pattern: the API model sees ONLY the database schema and your question — never a single row — and writes a SELECT statement; a deterministic guardrail refuses any statement that does not start with SELECT; the query then runs on a local SQLite MCP server and a LOCAL model reads the rows and answers.

See the template → human in the loop

Expense approver

Human in the Loop — Human in the loop with a real approve/reject: a local model assesses the risk of an expense request, the run then WAITS durably for a human decision, and a router either executes the (placeholder) payment step or refuses.

See the template → MCP from OpenAPI (REST)

Tool belt

Step Tools vs. LLM-Driven Tools — The two ways to use a tool, in one agent: a GraphQL API turned into an MCP server runs as a flow STEP (it always executes), while a REST API turned into an MCP server is WIRED TO the local model as a capability the model decides to call.

See the template → multi-model consensus

Second opinion

Multi-Model Consensus — Ask a local model AND an API model the same question independently, then a local judge reconciles the two answers into one — flagging any disagreement.

See the template → PII firewall

PII firewall

Privacy as a Router — A privacy router: a deterministic PII guardrail inspects every request BEFORE any model runs.

See the template → vision in a pipeline

Visual inspector

Vision in a Pipeline — Vision inside a pipeline, not a chat window: a local vision model inspects an image against your acceptance criteria, emits a structured pass/fail verdict, and a router sends the run down the matching branch — the skeleton of a visual QC line.

See the template → speech-to-text

Voice desk

Voice In, Voice Out — Voice in, voice out: speech-to-text transcribes the audio, a model answers in spoken prose, text-to-speech reads it back.

See the template → local image generation

Art department

Local Image Generation — Local image generation in a pipeline: a local model turns your rough brief into one vivid, concrete image prompt, and a local diffusion model paints it.

See the template → local RAG (pgvector)

Handbook Q&A

Retrieval as a Model Capability — Retrieval as a model capability, fully local: the installer creates a retrieval source in your own Postgres (pgvector), seeds it with a fictional TheYgent company handbook, and wires it to a local model as a search tool the model decides to call — answers cite the handbook section they came from.

See the template → self-correcting loop

Editorial loop

A Self-Correcting Agent — A self-correcting agent: a bounded LOOP re-runs a writer-critic child agent — draft, harsh self-critique, rewrite — until the child approves its own draft or three rounds are up.

See the template →