# Hybrid reasoning in Canvas and Script view

*Agentforce Specialist Study Guide · AI Agents · Last updated October 15, 2026 · https://www.certifyforce.com/study-guide/agentforce-specialist/ai-agents/hybrid-reasoning-in-canvas-and-script-view*

How Canvas view and Script view edit one Agent Script, where hybrid reasoning draws the line between deterministic code and LLM calls, which lifecycle points spend an LLM call, and when a workflow should stay LLM-led.

- Certification: Salesforce Agentforce Specialist
- Exam section: AI Agents
- Study guide: https://www.certifyforce.com/study-guide/agentforce-specialist

**Official exam objective:**

> Explain the components and benefits of hybrid reasoning, including how Agent Script functions in Canvas and Script View.

## What the exam expects

- Explain that Canvas view, Script view and chatting with Agentforce all edit the same Agent Script, and what each surface offers.
- Explain how hybrid reasoning splits work between deterministic execution and LLM reasoning, and what triggers an LLM call.
- Identify which lifecycle points invoke the LLM and which never do, to budget model usage.
- Justify hybrid reasoning (auditability, cost, latency, predictability) and recognise when LLM-led reasoning is the better fit.
- Key terms: **hybrid reasoning** (deterministic code plus LLM reasoning in one agent); **logic instruction** (`->`, runs as code); **prompt instruction** (`|`, natural language the LLM interprets); **Canvas view** (block-based editor); **Script view** (direct code editor).

## Key facts

| Fact | Detail | Source |
|---|---|---|
| One artifact | Canvas and Script view edit the same Agent Script; configuration stays consistent | [Building Agents in Canvas View](https://help.salesforce.com/s/articleView?id=ai.agent_canvas.htm&language=en_US&type=5) |
| Canvas shortcuts | `/` inserts expressions such as if/else; `@` inserts subagents, actions and variables | [Agent Script](https://developer.salesforce.com/docs/ai/agentforce/guide/agent-script.html) |
| Committing | Warnings allow a commit; errors block it | [Building Agents in Canvas View](https://help.salesforce.com/s/articleView?id=ai.agent_canvas.htm&language=en_US&type=5) |
| Invalid script | Can make Canvas view unavailable until fixed in Script view | [Agentforce Builder Considerations](https://help.salesforce.com/s/articleView?id=ai.agent_considerations.htm&language=en_US&type=5) |
| LLM trigger | A node's prompt instructions trigger the LLM call; other nodes run as code | [Hybrid Reasoning](https://architect.salesforce.com/docs/architect/fundamentals/guide/hybrid-reasoning-agentforce-builder-agent-script) |
| Deterministic path audit | Results still pass through the trust layer with full audit logging | [Hybrid Reasoning](https://architect.salesforce.com/docs/architect/fundamentals/guide/hybrid-reasoning-agentforce-builder-agent-script) |
| Always deterministic | Graph traversal and state transitions | [Hybrid Reasoning](https://architect.salesforce.com/docs/architect/fundamentals/guide/hybrid-reasoning-agentforce-builder-agent-script) |
| Always an LLM call | Agent reasoning (choosing the next action) | [Hybrid Reasoning](https://architect.salesforce.com/docs/architect/fundamentals/guide/hybrid-reasoning-agentforce-builder-agent-script) |
| Action billing | Actions bill whether deterministic or LLM-chosen; utilities don't bill as actions | [Agentforce Builder Considerations](https://help.salesforce.com/s/articleView?id=ai.agent_considerations.htm&language=en_US&type=5) |
| Builder assistant | Not billed or metered; doesn't consume credits | [Learn About New Agentforce Builder](https://help.salesforce.com/s/articleView?id=005232662&language=en_US&type=1) |
| Simulate vs Live Test | Simulate uses mock data and changes nothing; Live Test runs actions and updates data | [Simulate and Live Test Modes](https://help.salesforce.com/s/articleView?id=ai.agent_simulate_and_live_modes.htm&language=en_US&type=5) |

## Check yourself

- Why can moving a business rule from a prompt instruction into Agent Script logic lower cost and latency?
- When should an agent lean on LLM reasoning instead of deterministic logic?
- When does Canvas view become unavailable?
- Which agent behaviour never involves the LLM?

## Sources

- [Hybrid Reasoning with New Agentforce Builder and Agent Script](https://architect.salesforce.com/docs/architect/fundamentals/guide/hybrid-reasoning-agentforce-builder-agent-script)
- [Building Agents in Canvas View](https://help.salesforce.com/s/articleView?id=ai.agent_canvas.htm&language=en_US&type=5)
- [Agent Script](https://developer.salesforce.com/docs/ai/agentforce/guide/agent-script.html)
- [Learn About New Agentforce Builder with Agent Script](https://help.salesforce.com/s/articleView?id=005232662&language=en_US&type=1)
- [Agentforce Builder Considerations](https://help.salesforce.com/s/articleView?id=ai.agent_considerations.htm&language=en_US&type=5)
- [Explore Agentforce Builder](https://help.salesforce.com/s/articleView?id=ai.agent_builder_tour.htm&language=en_US&type=5)
- [Agent Script Language Characteristics](https://developer.salesforce.com/docs/ai/agentforce/guide/ascript-lang.html)
- [Example: More Reliable Agent Instructions with Agent Script](https://help.salesforce.com/s/articleView?id=ai.agent_example_script_before_after.htm&language=en_US&type=5)
- [Simulate and Live Test Modes](https://help.salesforce.com/s/articleView?id=ai.agent_simulate_and_live_modes.htm&language=en_US&type=5)

## About the full unit

The "Core concepts", "Exam traps" and "Worked scenario" sections of this unit, its 12 linked practice questions, and unlimited timed mock exams are included with the Agentforce Specialist pack (USD $19): https://www.certifyforce.com/practice-exams