Build Agents with Weaver
Weaver is the prompt-first interface in SmythOS that lets you build AI agents by simply describing what you want. Unlike traditional agent builder tools that ask you to think like a developer, Weaver is task-oriented: you describe goals; Weaver builds.
Weaver transforms your text instructions into complete, testable workflows without needing to write a single line of code. It’s where your prompt becomes agent... and your typing becomes Smyth-ing.
Understand Agent Weaver in 3 Minutes
While Studio gives you a classic drag-and-drop canvas for building agents manually, Weaver starts with natural conversation in a single prompt box.
Just describe what you need. Weaver thinks, plans, and builds it for you; piece by piece.
Here’s how it works:
-
You describe your goal
e.g. "Help me write SEO-optimized articles for my blog about calculators" -
Weaver interprets your intent
It enters a “Thinking...” state where it analyzes what kind of agent you might need. -
It asks clarifying questions
Weaver ensures it gets things right by prompting you for context like:- Which platforms you publish to
- What type or tone of content you prefer
- Whether you need research assistance or just writing
-
It proposes a workflow plan
Example:- Generate blog structure
- Write full content
- Research topics
- Publish (optional)
-
Weaver auto-creates the workflow
Using skills from the SmythOS library, Weaver:- Picks components
- Connects them based on data needs
- Assigns inputs/outputs, types, and even color codes
-
You test, tweak, and ship within chat
Just type. No config panels, no handoffs, no code.
Behind the scenes, Weaver behaves like a LLM orchestration engine paired with a smart schema-aware composer, but you never see the wiring unless you want to.
-> Try a prompt like:
This makes Weaver the fastest way to build AI agents in SmythOS.
Why We Built Weaver
Before Weaver, building an agent felt like coding a backend from scratch: wiring APIs, managing logic, handling retries... all before the real work even started. That's why Weaver is so powerful. It is a true no-code agent orchestration tool. Now you just ask for what you want. Explain what you need to Weave your AI agent:
Prompt → Skill Suggestions → Visual Flow → Live Test → Fix/Deploy
It’s not just easier... it’s friendlier, faster, and far more forgiving for anyone.
- All SmythOS plans (free and paid) include free credits to use tools in the app, including Agent Weaver.
- After exhausting credits: Users are limited to 5 requests per 24 hours.
- Credit restoration: Credits are automatically restored at the beginning of each month.
Key Features of Weaver
Capability | Description |
---|---|
Prompt-Based Build | Start with plain text. Weaver handles planning and assembly. |
Auto-Linked Components | It chooses components from the SmythOS library and wires them automatically. |
Live Testing | Test agents directly in chat. |
AI-Powered Fixes | Use the “Fix with AI” option for broken or misconfigured components. |
Zero-Code Deployment | Launch agents to API or Web UI instantly. |
Quick Links
Prompt Guide
How to write prompts that generate the right workflows
Quickstart
Launch your first AI agent in minutes
Best Practices
Strategies for modular and testable agent design
How to Get Started with Weaver
We call this flow Chat-to-Agent:
- Describe the agent:
Create an agent that writes SEO articles and posts to WordPress.
- (Optionally) list its skills:
The agent should have the following skills...It should write SEO-optimised articles, extract primary and secondary keywords, and post content to Wordpress.
- Weaver thinks aloud and asks smart questions
Weaver responds with a preview of its planned workflows, then follows up with clarifying questions like:- What kind of blogs are you targeting?
- Do you want keyword extraction to be optional or required?
- Which CMS platform are you using — WordPress.com or self-hosted?
- Weaver maps those into 3 components:
- GenAI LLM (to write the article)
- Classifier (to extract keywords)
- APICall (to post the content)
- It wires them into a functional layout... like magic, but with schema integrity. Weaver also sets names, descriptions, inputs, and outputs, ensuring clarity and relevance.
- Test the agent directly in chat.
- Fix any breakage with a single click or asking Weaver to fix the issues by prompting it.
- Deploy and go live without writing any code.
Weaver even lets you attach images or flow diagrams to describe what you want.
Great for visual thinkers, or folks who like whiteboarding their way through a build.
Fixing with AI
Component break? Happens to the best of us. Weaver gives you:
- Input/output previews
- A "Fix with AI" button
- The ability to select and debug multiple components (
Cmd/Ctrl + click
is your friend) - Weaver rewrites only what’s broken or selected -> Your agent keeps running; no blanket rebuild required.
Inside Weaver
Weaver combines:
- Prompt parsing to identify goals and intent
- Skill suggestion based on our core component library
- Dependency mapping to auto-wire your logic
- Live doc search to answer product questions... yes, even "How do I upgrade?"
It’s fast, helpful, and never passive-aggressive.
Understand Key Concepts of Weaver
Term | Meaning |
---|---|
Agent | Task-running bot powered by LLMs & skills |
Workflow | Sequence of components linked by inputs/outputs |
Component | A single block that performs a task (API call, generation, classification, etc.) (● mandatory · ○ optional) |
You can learn more about input/output design and flow behavior in the Weaver I/O guide, and explore how Weaver handles broken logic in the debugging section.
Start Building with Weaver
Weaver supports both simple and multi-step use cases for building agents, such as:
- Blog writing and publishing
- Email sequence automation
- Market research + summarization
- Internal reporting workflows
Weaver encourages:
- Task-based thinking (“extract keywords” > “run NLP”)
- Smaller, focused workflows
- Reuse over reinvention
Who Should Use Weaver? (Hint: Probably You Soon)
- Ops leads converting checklists into automations
- PMs prototyping in a SmythOS AI design environment
- Analysts who want results
- Developers who’d rather start at 80 % than 0 %
If you’ve ever thought “I know what I want, I just don’t know how to build it,” Weaver’s for you.