Agent Template · two models in one run · router · transform

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. Nothing is proxied — each branch calls its own model directly.

How It Works

A local triage model reads every request and answers with a one-word route — local or remote — as minified JSON. A transform node joins that route with the original question, and a router follows it: greetings, short factual questions, and simple rewrites go to your local model; coding, analysis, and long-form work go to an API model.

Two model bindings, one graph, and nothing proxied: each branch calls its own model directly, and the run trace shows which one answered.

Try It

  1. In TheYgent, open Settings → Samples.
  2. Fill the model slots below with models from your registry, then click Install on Hybrid reasoner.
  3. Open the installed agent and run it with the example input.
Write a Python function that merges two sorted lists in O(n).

The Graph

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

sample-hybrid-reasoner

Node Type Sends its output to
Request input Triage (local); Route + question (into question)
Triage (local) llm Route + question (into triage)
Route + question transform Route by difficulty
Route by difficulty router Answer locally (on local); Answer via API (on remote)
Answer locally llm Local answer
Answer via API llm API answer
Local answer output —
API answer output —

More Templates

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 → parallel fan-out (map)

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.

See the template →